Datasets:

siavava

/

ai-tech-articles

like 7

"AI lab DeepMind cracked the protein folding problem, changing biology with AlphaFold - Vox"

"https://www.vox.com/future-perfect/22045713/ai-artificial-intelligence-deepmind-protein-folding"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Science AI has cracked a problem that stumped biologists for 50 years. It’s a huge deal. A breakthrough on the “protein folding problem” can help us understand disease and discover new drugs. By Sigal Samuel Dec 3, 2020, 2:00pm EST Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: AI has cracked a problem that stumped biologists for 50 years. It’s a huge deal. Reddit Pocket Flipboard Email Ann Johansson/Corbis via Getty Images This story is part of a group of stories called Finding the best ways to do good. DeepMind, an AI research lab that was bought by Google and is now an independent part of Google’s parent company Alphabet, announced a major breakthrough this week that one evolutionary biologist called “a game changer.” “This will change medicine,” the biologist, Andrei Lupas, told Nature. “It will change research. It will change bioengineering. It will change everything.” The breakthrough: DeepMind says its AI system, AlphaFold, has solved the “protein folding problem” — a grand challenge of biology that has vexed scientists for 50 years. Proteins are the basic machines that get work done in your cells. They start out as strings of amino acids (imagine the beads on a necklace) but they soon fold up into a unique three-dimensional shape (imagine scrunching up the beaded necklace in your hand). That 3D shape is crucial because it determines how the protein works. If you’re a scientist developing a new drug, you want to know the protein’s shape because that will help you come up with a molecule that can bind to it, fitting into it to alter its behavior. The trouble is, predicting which shape a protein will take is incredibly hard. Every two years, researchers who work on this problem try to prove how good their predictive powers are by submitting a prediction about the shapes that certain proteins will take. Their entries are judged at the Critical Assessment of Structure Prediction (CASP) conference, which is basically a fancy science contest for grown-ups. By 2018, DeepMind’s AI was already outperforming everyone at CASP, provoking some melancholic feelings among the human researchers. DeepMind took home the win that year, but it still hadn’t solved the protein folding problem. Not even close. This year, though, its AlphaFold system was able to predict — with impressive speed and accuracy — what shapes given strings of amino acids would fold up into. The AI is not perfect, but it’s pretty great: When it makes mistakes, it’s generally only off by the width of an atom. That’s comparable to the mistakes you get when you do physical experiments in a lab, except that those experiments are much slower and much more expensive. “This is a big deal,” John Moult, who co-founded and oversees CASP, told Nature. “In some sense the problem is solved.” Why this is a big deal for biology The AlphaFold technology still needs to be refined, but assuming the researchers can pull that off, this breakthrough will likely speed up and improve our ability to develop new drugs. Let’s start with the speed. To get a sense of how much AlphaFold can accelerate scientists’ work, consider the experience of Andrei Lupas , an evolutionary biologist at the Max Planck Institute in Germany. He spent a decade — a decade! — trying to figure out the shape of one protein. But no matter what he tried in the lab, the answer eluded him. Then he tried out AlphaFold and he had the answer in half an hour. AlphaFold has implications for everything from Alzheimer’s disease to future pandemics. It can help us understand diseases, since many (like Alzheimer’s) are caused by misfolded proteins. It can help us find new treatments, and also help us quickly determine which existing drugs can be usefully applied to, for example, a new virus. When another pandemic comes along, it could be very helpful to have a system like AlphaFold in our back pocket. “We could start screening every compound that is licensed for use in humans,” Lupas told the New York Times. “We could face the next pandemic with the drugs we already have.” But for this to be possible, DeepMind would have to share its technology with scientists. The lab says it’s exploring ways to do that. Why this is a big deal for artificial intelligence Over the past few years, DeepMind has made a name for itself by playing games. It has built AI systems that crushed pro gamers at strategy games like StarCraft and Go. Much like the chess matches between IBM’s Deep Blue and Garry Kasparov, these matches mostly served to prove that DeepMind can make an AI that surpasses human abilities. Now, DeepMind is proving that it has grown up. It has graduated from playing video games to addressing scientific problems with real-world significance — problems that can be life-or-death. The protein folding problem was a perfect thing to tackle. DeepMind is a world leader in building neural networks, a type of artificial intelligence loosely inspired by the neurons in a human brain. The beauty of this type of AI is that it doesn’t require you to preprogram it with a lot of rules. Just feed a neural network enough examples of something, and it can learn to detect patterns in the data, then draw inferences based on that. So, for example, you can present it with many thousands of strings of amino acids and show it what shape they folded into. Gradually, it detects patterns in the way given strings tend to shape up — patterns that human experts may not have detected. From there, it can make predictions about how other strings will fold. This is exactly the sort of problem at which neural networks excel, and DeepMind recognized that, marrying the right type of AI to the right type of puzzle. (It also integrated some more complex knowledge — about physics and evolutionarily related amino acid sequences, for example — though the details remain scant as DeepMind is still preparing a peer-reviewed paper for publication.) Other labs have already harnessed the power of neural networks to make breakthroughs in biology. At the beginning of this year, AI researchers trained a neural network by feeding it data on 2,335 molecules known to have antibacterial properties. Then they used it to predict which other molecules — out of 107 million possibilities — would also have these properties. In this way, they managed to identify brand-new types of antibiotics. DeepMind researchers are capping the year with another achievement that shows just how much AI has matured. It’s genuinely great news for a generally terrible 2020. Sign up for the Future Perfect newsletter and we’ll send you a roundup of ideas and solutions for tackling the world’s biggest challenges — and how to get better at doing good. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via In This Stream The rapid development of AI has benefits — and poses serious risks Elon Musk wants to merge humans with AI. How many brains will be damaged along the way? AI has cracked a problem that stumped biologists for 50 years. It’s a huge deal. The case for taking AI seriously as a threat to humanity 55 Next Up In Future Perfect Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. The Latest Most of Israel’s weapons imports come from the US. Now Biden is rushing even more arms. By Jonathan Guyer Formula 1 grew too fast. Now its new fans are tuning out. By Izzie Ramirez The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained By A.W. Ohlheiser and Li Zhou Your phone is the key to your digital life. Make sure you know what to do if you lose it. By Sara Morrison Alex Murdaugh stands guilty of killing his wife and son. That’s just scratching the surface. By Aja Romano Is the green texting bubble about to burst? By Sara Morrison Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"The Reluctant Prophet of Effective Altruism | The New Yorker"

"https://www.newyorker.com/magazine/2022/08/15/the-reluctant-prophet-of-effective-altruism"

"Newsletter To revisit this article, select My Account, then View saved stories Close Alert Search The Latest News Books & Culture Fiction & Poetry Humor & Cartoons Magazine Puzzles & Games Video Podcasts Goings On Shop Open Navigation Menu Find anything you save across the site in your account Close Alert Annals of Inquiry The Reluctant Prophet of Effective Altruism By Gideon Lewis-Kraus Facebook X Email Print Save Story “The world’s long-run fate depends in part on the choices we make in our lifetimes,” the philosopher William MacAskill writes. Photograph by Ulysses Ortega for The New Yorker Save this story Save this story Save this story Save this story The philosopher William MacAskill credits his personal transfiguration to an undergraduate seminar at Cambridge. Before this shift, MacAskill liked to drink too many pints of beer and frolic about in the nude, climbing pitched roofs by night for the life-affirming flush; he was the saxophonist in a campus funk band that played the May Balls, and was known as a hopeless romantic. But at eighteen, when he was first exposed to “Famine, Affluence, and Morality,” a 1972 essay by the radical utilitarian Peter Singer, MacAskill felt a slight click as he was shunted onto a track of rigorous and uncompromising moralism. Singer, prompted by widespread and eradicable hunger in what’s now Bangladesh, proposed a simple thought experiment: if you stroll by a child drowning in a shallow pond, presumably you don’t worry too much about soiling your clothes before you wade in to help; given the irrelevance of the child’s location—in an actual pond nearby or in a metaphorical pond six thousand miles away—devoting resources to superfluous goods is tantamount to allowing a child to drown for the sake of a dry cleaner’s bill. For about four decades, Singer’s essay was assigned predominantly as a philosophical exercise: his moral theory was so onerous that it had to rest on a shaky foundation, and bright students were instructed to identify the flaws that might absolve us of its demands. MacAskill, however, could find nothing wrong with it. By the time MacAskill was a graduate student in philosophy, at Oxford, Singer’s insight had become the organizing principle of his life. When he met friends at the pub, he ordered only a glass of water, which he then refilled with a can of two-per-cent lager he’d bought on the corner; for dinner, he ate bread he’d baked at home. The balance of his earnings was reserved for others. He tried not to be too showy or evangelical, but neither was he diffident about his rationale. It was a period in his life both darkly lonesome and ethically ablaze. As he put it to me recently, “I was very annoying.” In an effort to shape a new social equilibrium in which his commitments might not be immediately written off as mere affectation, he helped to found a moral crusade called “effective altruism.” The movement, known as E.A. to its practitioners, who themselves are known as E.A.s, takes as its premise that people ought to do good in the most clear-sighted, ambitious, and unsentimental way possible. Among other back-of-the-envelope estimates, E.A.s believe that a life in the developing world can be saved for about four thousand dollars. Effective altruists have lashed themselves to the mast of a certain kind of logical rigor, refusing to look away when it leads them to counterintuitive, bewildering, or even seemingly repugnant conclusions. For a time, the movement recommended that inspirited young people should, rather than work for charities, get jobs in finance and donate their income. More recently, E.A.s have turned to fretting about existential risks that might curtail humanity’s future, full stop. Effective altruism, which used to be a loose, Internet-enabled affiliation of the like-minded, is now a broadly influential faction, especially in Silicon Valley, and controls philanthropic resources on the order of thirty billion dollars. Though MacAskill is only one of the movement’s principal leaders, his conspicuous integrity and easygoing charisma have made him a natural candidate for head boy. The movement’s transitions—from obscurity to power; from the needs of the contemporary global poor to those of our distant descendants—have not been altogether smooth. MacAskill, as the movement’s de-facto conscience, has felt increasing pressure to provide instruction and succor. At one point, almost all of his friends were E.A.s, but he now tries to draw a line between public and private. He told me, “There was a point where E.A. affairs were no longer social things—people would come up to me and want to talk about their moral priorities, and I’d be, like, ‘Man, it’s 10 p.m. and we’re at a party!’ ” On a Saturday afternoon in Oxford, this past March, MacAskill sent me a text message about an hour before we’d planned to meet: “I presume not, given jetlag, but might you want to go for a sunset swim? It’d be very very cold!” I was out for a run beside the Thames, and replied, in an exacting mode I hoped he’d appreciate—MacAskill has a way of making those around him greedy for his approval—that I was about eight-tenths of a mile from his house, and would be at his door in approximately five minutes and thirty seconds. “Oh wow impressive!” he replied. “Let’s do it!” MacAskill limits his personal budget to about twenty-six thousand pounds a year, and gives everything else away. He lives with two roommates in a stolid row house in an area of south Oxford bereft, he warned me, of even a good coffee shop. He greeted me at his door, praising my “bias for action,” then led me down a low and dark hallway and through a laundry room arrayed with buckets that catch a perpetual bathroom leak upstairs. MacAskill is tall and sturdily built, with an untidy mop of dark-blond hair that had grown during the pandemic to messianic lengths. In an effort to unwild himself for reëntry, he had recently reduced it to a dimension better suited to polite society. MacAskill allowed, somewhat sheepishly, that lockdown had been a welcome reprieve from the strictures of his previous life. He and some friends had rented a home in the Buckinghamshire countryside; he’d meditated, acted as the house exercise coach, and taken in the sunset. He had spent his time in a wolf-emblazoned jumper writing a book called “What We Owe the Future,” which comes out this month. Now the world was opening up, and he was being called back to serve as the movement’s shepherd. He spoke as if the life he was poised to return to were not quite his own—as if he weren’t a person with desires but a tabulating machine through which the profusion of dire global need was assessed, ranked, and processed. “Any of you boys interested in fresh gossip for your diaries?” Cartoon by Frank Cotham Copy link to cartoon Copy link to cartoon Link copied Shop Shop He was doing his best to retain a grasp on spontaneity, and we set off on the short walk to the lake. Upon our arrival, MacAskill vaulted over a locked gate that led to a small floating dock, where he placed a Bluetooth speaker that played a down-tempo house remix of the 1974 pop hit “Magic.” The water temperature, according to a bath-toy thermometer, was about fifty degrees. He put on a pair of orange sunglasses with tinted lenses, which enhanced the sunset’s glow, and stripped off his shirt, revealing a long abdominal scar, the result of a fall through a skylight as a teen-ager. He reassured me, “If all you do is just get in and get out, that’s great.” I quickly discharged my duty and then flung myself, fingers blue, back onto the dock. MacAskill did a powerful breaststroke out into the middle of the lake, where he floated, freezing, alone and near-invisible in the polarized Creamsicle sunset. Then he slowly swam back to resume his obligations. MacAskill, who was born in 1987 as William Crouch, grew up in Glasgow and attended a vaunted private school. He excelled at almost everything but was the first to make fun of himself for singing off-key, juggling poorly, and falling out of treehouses. Though his mother grew up in conditions of rural Welsh privation, his family had little political color—as a child, he was given to understand that all newspapers were right-leaning tabloids. From an early age, however, he demonstrated a precocious moral zeal. At fifteen, when he learned how many people were dying of AIDS , he set out to become a successful novelist and give away half of his earnings. He volunteered for a disabled-Scout group and worked at a care home for the elderly, which his parents found baffling. In his milieu, the brightest graduates were expected to study medicine in Edinburgh, but MacAskill, as class dux, or valedictorian, won a place to read philosophy at Cambridge. Robbie Kerr, MacAskill’s closest schoolmate, told me, “The Glasgow attitude was best summed up by a school friend’s parent, who looked at Will and said, ‘Philosophy. What a waste. That boy could have cured cancer.’ ” MacAskill found Cambridge intellectually and socially satisfying: he discussed meta-ethics on shirtless walks, and spent vacations at friends’ homes in the South of France. But he also remembers feeling adrift, “searching for meaning.” “There weren’t a lot of opportunities for moral activism,” he told me. He spent a summer volunteering at a rehabilitation center in Ethiopia and, after graduation, another as a “chugger,” a street canvasser paid to convert pedestrians to charitable causes. “We used to say it only cost twenty pence to save a life from polio, and a lot of other stuff that was just wrong,” he said, shaking his head. Nevertheless, he continued, “it was two months of just sitting with extreme poverty, and I felt like other people just didn’t get it.” In graduate school, “I started giving three per cent, and then five per cent, of my income,” he said. This wasn’t much—he was then living on a university stipend. “I think it’s O.K. to tell you this: I supplemented my income with nude modelling for life-drawing classes.” The postures left him free to philosophize. Later, he moved on to bachelorette parties, where he could make twice the money “for way easier poses.” He told me, “I was in the game for being convinced of a cause, and did a bunch of stuff that was more characteristically far-lefty. I went to a climate-justice protest, and a pro-Palestinian protest, and a meeting of the Socialist Workers Party.” None passed muster, for reasons of efficacy or intellectual coherence. “I realized the climate protest was against cap-and-trade, which I was for. The Socialist Workers Party was just eight people with long hair in a basement talking about the glory of the Russian Revolution.” He surveyed working philosophers and found that none felt like they’d done anything of real consequence. George Marshall, a friend from Cambridge, told me, “He was at dinner in Oxford—some sort of practical-ethics conference—and he was just deeply shocked that almost none of the attendees were vegetarians, because he thought that was the most basic application of ethical ideas.” When MacAskill was twenty-two, his adviser suggested that he meet an Australian philosopher named Toby Ord. In activist circles, MacAskill had found, “there was this focus on the problems—climate is so bad!—along with intense feelings of angst, and a lack of real views on what one could actually do. But Toby was planning to give money in relatively large amounts to focussed places, and trying to get others to do the same—I felt, ‘Oh, this is taking action.’ ” At the time, Ord was earning fifteen thousand pounds a year and was prepared to give away a quarter of it. “He’d only had two half-pints in his time at Oxford,” MacAskill said. “It was really hardcore.” Unlike, say, someone who donates to cystic-fibrosis research because a friend suffers from the disease—to take a personal example of my own—Ord thought it was important that he make his allocations impartially. There was no point in giving to anyone in the developed world; the difference you could make elsewhere was at least two orders of magnitude greater. Ord’s ideal beneficiary was the Fred Hollows Foundation, which treats blindness in poor countries for as little as twenty-five dollars a person. MacAskill immediately signed on to give away as much as he could in perpetuity: “I was on board with the idea of binding my future self—I had a lot of youthful energy, and I was worried I’d become more conservative over time.” He recalled the pleasure of proving that his new mentor’s donations were suboptimal. “My first big win was convincing him about deworming charities.” It may seem impossible to compare the eradication of blindness with the elimination of intestinal parasites, but health economists had developed rough methods. MacAskill estimated that the relief of intestinal parasites, when measured in “quality-adjusted life years,” or QALY s, would be a hundred times more cost-effective than a sight-saving eye operation. Ord reallocated. If Peter Singer’s theory—that any expenditure beyond basic survival was akin to letting someone die—was simply too taxing to gain wide adherence, it seemed modest to ask people to give ten per cent of their income. This number also had a long-standing religious precedent. During the next six months, MacAskill and Ord enjoined their friends and other moral philosophers to pledge a secular tithe. MacAskill told me, “I would quote them back to themselves—you know, ‘If someone in extreme poverty dies, it’s as if you killed them yourself,’ and other really severe pronouncements—and say, ‘So, would you like to sign?’ ” Singer said yes, but almost everyone else said no. On November 14, 2009, in a small room in Balliol College, MacAskill and Ord announced Giving What We Can. MacAskill said, “At the launch, we had twenty-three members, and most of them were friends of Toby’s and mine.” When MacAskill took his vow of relative poverty, he worried that it would make him less attractive to date: “It was all so weird and unusual that I thought, Out of all the people I could be in a relationship with, I’ve just cut out ninety-nine per cent of them.” This prediction was incorrect; in 2013, he married another Scottish philosopher and early E.A., and the two of them took her grandmother’s surname, MacAskill. Later, a close relative found out what MacAskill had been doing with his stipend and told him, “That’s unethical!” If he wasn’t using his scholarship, he should return it to the university. He loves his family, he told me, “but I guess if I’d spent that money on beer it would have been O.K.” Like agriculture, echolocation, and the river dolphin, the practice that would become effective altruism emerged independently in different places at around the same time. Insofar as there was a common ancestor, it was Peter Singer. Holden Karnofsky and Elie Hassenfeld, young analysts at the hedge fund Bridgewater Associates, formed a club to identify the most fruitful giving opportunities—one that relied not on crude heuristics but on hard data. That club grew into an organization called GiveWell, which determined that, for example, the most cost-effective way to save a human life was to give approximately four thousand dollars to the Against Malaria Foundation, which distributes insecticide-treated bed nets. In the Bay Area “rationalist” community, a tech-adjacent online subculture devoted to hawkish logic and quarrelsome empiricism, bloggers converged on similar ideas. Eliezer Yudkowsky, one of the group’s patriarchs, instructed his followers to “purchase fuzzies and utilons separately.” It was fine to tutor at-risk kids or volunteer in a soup kitchen, as long as you assigned those activities to a column marked “self-interest.” But the pursuit of a warm glow should be separate from doing the most impartial good. When I asked Singer why the late two-thousands were a time of great ferment for applied consequentialism, he cited the Internet: “People will say, ‘I’ve had these ideas since I was a teen-ager, and I thought it was just me,’ and then they got online and found that there were others.” Julia Wise, then an aspiring social worker, had been giving for years to the point of extreme personal sacrifice; she met Ord in the comments section of the economist Tyler Cowen’s blog, and made the Giving What We Can pledge. She told me that she was attracted on a “tribal basis” to the movement’s sense of “global solidarity.” Proto-E.A. attracted people who longed to reconcile expansive moral sensibilities with an analytical cast of mind. They tended to be consequentialists—those who believe that an act should be evaluated not as it conforms to universal rules but based on its results—and to embrace utilitarianism, a commitment to the greatest good for the greatest number. Their instinct was to see moral interventions as grand optimization problems, and they approached causes on the basis of three criteria: importance, tractability, and neglectedness. They were interested in thought experiments like the trolley problem, in part because they found such exercises enlivening and in part because it emphasized that passive actors could be culpable. It also made plain the very real dilemma of resource constraints: if the same amount of money could save one person here or five people there, there was no need for performative hand-wringing. As the rationalists put it, sometimes you just had to “shut up and multiply.” A kind of no-hard-feelings, debate-me gladiatorialism was seen as a crucial part of good “epistemic hygiene,” and a common social overture was to tell someone that her numbers were wrong. On GiveWell’s blog, MacAskill and Karnofsky got into a scrap about the right numbers to assign to a deworming initiative. Before Wise met MacAskill, she had e-mailed to say that he had got some other numbers wrong by an order of magnitude. “A few months later, here I was having a beer with Will,” she said. In late 2011, in the midst of the Occupy movement, MacAskill gave a talk at Oxford called “Doctor, NGO Worker, or Something Else Entirely? Which Careers Do the Most Good.” That year saw the launch of 80,000 Hours, an offshoot of Giving What We Can designed to offer “ethical life-optimisation” advice to undergraduates. His advice, which became known as “earning to give,” was that you—and the “you” was pretty explicitly high-calibre students at élite institutions—could become a doctor in a poor country and possibly save the equivalent of a hundred and forty lives in your medical career, or you could take a job in finance or consulting and, by donating intelligently, save ten times as many. “They like you because you’re allergic to them.” Cartoon by Amy Hwang Copy link to cartoon Copy link to cartoon Link copied Shop Shop A young Oxonian named Habiba Islam was at that talk, and it changed her life. “I was the head of Amnesty International at university, I was volunteering at the local homeless shelter in Oxford—that kind of thing,” she told me. “I know people who were committed to climate change as their thing—a pretty good guess for what’s important—before getting involved in E.A.” Islam was considering a political career; 80,000 Hours estimated that an Oxford graduate in Philosophy, Politics, and Economics who embarked on such a path has historically had about a one-in-thirty chance of becoming an M.P. She took the pledge, agreeing to give away everything above twenty-five thousand pounds a year, and became a consultant for PwC. She told me, “It was just obvious that we privileged people should be helping more than we were.” Matt Wage, a student of Singer’s at Princeton, decided that, instead of pursuing philosophy in grad school, he would get a job at the trading firm Jane Street. If you rescued a dozen people from a burning building, he thought, you would live out the rest of your days feeling like a hero; with donations, you could save that many lives every year. “You can pay to provide and train a guide dog for a blind American, which costs about $40,000,” Wage told the reporter Dylan Matthews, for a Washington Post piece called “Join Wall Street. Save the world.” “But with that money you could also cure between 400 and 2,000 people in developing countries of blindness from glaucoma.” Matthews, convinced by his sources in the movement, went on to donate a kidney. “You go to an E.A. conference and things feel genuinely novel,” he said. “Someone will give a talk about how, if we regulate pesticides differently, we can reduce suicide. I don’t have to agree with everything they say, or think Will is the Pope, for it to be a very useful way to think about what deserves attention.” In the movement’s early years, MacAskill said, “every new pledge was a big deal, a cause for celebration.” As E.A. expanded, it required an umbrella nonprofit with paid staff. They brainstormed names with variants of the words “good” and “maximization,” and settled on the Centre for Effective Altruism. Wise donated thousands of dollars; it was the first time her money was going not to “object-level” work but to movement-building. She said, “I was an unemployed social worker, but I felt so optimistic about their work that I gave them most of my savings.” In 2015, MacAskill was hired as an associate professor at Oxford and, at twenty-eight, was said to be the youngest such philosophy professor in the world. It should have been a moment of vindication, but he felt conflicted. “It was easy and high-status,” he said. “But I didn’t want to be too comfortable.” The same year, his marriage deteriorated—he kept the surname; his ex didn’t—and he published his first book, “Doing Good Better,” an extended case that Westerners were in a situation akin to “a happy hour where you could either buy yourself a beer for five dollars or buy someone else a beer for five cents.” That summer, 80,000 Hours was accepted into Y Combinator, a prestigious startup incubator. The Effective Altruism Global summit was held at the Googleplex, and Elon Musk appeared on a panel about artificial intelligence. (MacAskill told me, “I tried to talk to him for five minutes about global poverty and got little interest.”) By then, GiveWell had moved to San Francisco, and the Facebook co-founder Dustin Moskovitz and his wife, the former journalist Cari Tuna, had tasked its new project—later known as Open Philanthropy—with spending down their multibillion-dollar fortune. Open Philanthropy invested in international development and campaigns for broiler-chicken welfare, and expanded into causes like bail reform. For the first time, MacAskill said, the fledgling experiment felt like “a force in the world.” MacAskill, too, was newly a force in the world. For all E.A.’s aspirations to stringency, its numbers can sometimes seem arbitrarily plastic. MacAskill has a gap between his front teeth, and he told close friends that he was now thinking of getting braces, because studies showed that more “classically” handsome people were more impactful fund-raisers. A friend of his told me, “We were, like, ‘Dude, if you want to have the gap closed, it’s O.K.’ It felt like he had subsumed his own humanity to become a vehicle for the saving of humanity.” The Centre for Effective Altruism now dwells, along with a spate of adjacent organizations with vaguely imperious names—the Global Priorities Institute, the Forethought Foundation—in Trajan House, an Oxford building that overlooks a graveyard. Nick Bostrom, a philosopher whose organization, the Future of Humanity Institute, also shares the space, disliked the building’s name, which honors a philanthropic Roman emperor, and proposed that it be called Corpsewatch Manor. The interior, with shelves of vegan nutritional bars and meal-replacement smoothies, resembles that of a pre-fiasco WeWork. MacAskill struggles with the opportunity cost of his time. He told me, “It’s always been an open question: What weight do I give my own well-being against the possible impact I can have?” Many evenings, he has a frozen vegan dinner at the office. (He wasn’t sure, when feeding me, whether the microwave time for two dishes would scale linearly.) He schedules his days down to the half hour. He and one of his assistants recently discussed reducing some slots to twenty-five minutes, but they ultimately decided that it might seem insulting. In a rare free moment, MacAskill, who wears tight-fitting V necks that accentuate his lack of sartorial vanity and his biceps, took me on a tour of the movement’s early sites. We passed Queen’s Lane Coffee House. “That’s where Bentham discovered utilitarianism,” he commented. “There should be a plaque, but the current owners have no idea.” Most of the colleges were closed to visitors, but MacAskill had perfected the flash of an old I.D. card and a brazen stride past a porter. He paused reverently outside All Souls College, where the late moral philosopher Derek Parfit, one of the guiding lights of E.A., spent his life in a tower. Parfit believed that our inherited moral theories were constructed on religious foundations, and aspired to build a comprehensive secular moral framework. Effective altruism, in that spirit, furnishes an all-encompassing world view. It can have an ecclesiastical flavor, and early critics observed that the movement seemed to be in the business of selling philanthropic indulgences for the original sin of privilege. It has a priestly class, whose posts on E.A.’s online forum are often received as encyclicals. In the place of Mass, E.A.s endure three-hour podcasts. There is an emphasis on humility, and a commandment to sacrifice for the sake of the neediest. Since its inception, GiveWell has directed the donation of more than a billion dollars; the Against Malaria Foundation alone estimates that its work to date will save a hundred and sixty-five thousand lives. There have been more than seven thousand Giving What We Can pledges, which total almost three billion dollars. In an alternate world, a portion of that sum would presumably have been spent on overpriced tapas in San Francisco’s Mission District. As effective altruism became a global phenomenon, what had been treated as a fringe curiosity became subject to more sustained criticism. A panel convened by the Boston Review described E.A.s as having cast their lot with the status quo. Though their patronage might help to alleviate some suffering on the margins, they left the international machine intact. As hard-nosed utilitarians, they bracketed values—like justice, fairness, and equality—that didn’t lend themselves to spreadsheets. The Stanford political scientist Rob Reich wrote, “Plato identified the best city as that in which philosophers were the rulers. Effective altruists see the best state of affairs, I think, as that in which good-maximizing technocrats are in charge. Perhaps it is possible to call this a politics: technocracy. But this politics is suspicious of, or rejects, the form of politics to which most people attach enormous value: democracy.” The Ethiopian American A.I. scientist Timnit Gebru has condemned E.A.s for acting as though they are above such structural issues as racism and colonialism. Few of these appraisals were new; many were indebted to the philosopher Bernard Williams, who noted that utilitarianism might, in certain historical moments, look like “the only coherent alternative to a dilapidated set of values,” but that it was ultimately bloodless and simpleminded. Williams held that the philosophy alienated a person “from the source of his actions in his own convictions”—from what we think of as moral integrity. Its means-end rationality could seem untrustworthy. Someone who seeks justification for the impulse to save the life of a spouse instead of that of a stranger, Williams famously wrote, has had “one thought too many.” The Oxford philosopher Amia Srinivasan, whom MacAskill considers a friend, wrote a decidedly mixed critique in the London Review of Books , calling MacAskill’s first book “a feel-good guide to getting good done.” She noted, “His patter is calculated for maximal effect: if the book weren’t so cheery, MacAskill couldn’t expect to inspire as much do-gooding.” She conceded the basic power of the movement’s rhetoric: “I’m not saying it doesn’t work. Halfway through reading the book I set up a regular donation to GiveDirectly,” one of GiveWell’s top recommended charities. But she called upon effective altruism to abandon the world view of the “benevolent capitalist” and, just as Engels worked in a mill to support Marx, to live up to its more thoroughgoing possibilities. “Effective altruism has so far been a rather homogenous movement of middle-class white men fighting poverty through largely conventional means, but it is at least in theory a broad church.” She noted, encouragingly, that one element was now pushing for “systemic change” on issues like factory farming and immigration reform. Some E.A.s felt that one of the best features of their movement—that, in the context of near-total political sclerosis, they had found a way to do something —had been recast as a bug. The movement’s self-corrections, they believed, had been underplayed: a high-paying job at a petrochemical firm, for example, was by then considered sufficiently detrimental that no level of income could justify it. But others found Srinivasan’s criticisms harsh but fair. As Alexander Berger, the co-C.E.O. of Open Philanthropy, told me, “She was basically right that early E.A. argued for the atomized response—that you as an individual should rationally and calculatedly allocate a portion of your privilege to achieve the best outcomes in the world, and this doesn’t leave much space for solidarity.” During the next few years, however, the movement gained a new appreciation for the more sweeping possibilities of systemic change—though perhaps not in the ways Srinivasan had envisioned. “You can’t just put on the uniform whenever you don’t want to have a conversation, Barry.” Cartoon by Asher Perlman Copy link to cartoon Copy link to cartoon Link copied Shop Shop One of the virtues of effective altruists—which runs counter to their stereotype as mere actuaries—is that, when they feel like it, they’re capable of great feats of imagination. A subset of them, for example, has developed grave concern about the suffering of wild animals: Should we euthanize geriatric elephants? Neutralize predator species? What should be done about the bugs? The prime status marker in a movement that has abjured financial reward is a reputation for punctilious (and often contrarian) intelligence. The community has a tendency to overindex on perceived cerebral firepower, which makes even leading lights like MacAskill feel a perennial sense of imposture. This means that genuinely bizarre ideas, if argued with sufficient virtuosity, get a fair hearing. Holden Karnofsky told me, “If you read things that E.A.s are saying, they sound a lot crazier than what they’re actually doing.” But the movement—constrained by methodological commitments rather than by substantive moral ones—has proved vulnerable to rapid changes in its priorities from unexpected quarters. In retrospect, “Doing Good Better” was less a blueprint for future campaigns than an epitaph for what came to be called the “bed-nets era.” During the next five years, a much vaster idea began to take hold in the minds of the movement’s leaders: the threat of humanity’s annihilation. Such concerns had been around since the dawn of the nuclear age. Parfit had connected them to an old utilitarian argument, that the protection of future lives was just as important as the preservation of current ones. The philosopher Nick Bostrom contended that, if humanity successfully colonized the planets within its “light cone”—the plausibly reachable regions of the universe—and harnessed the computational power of the stars to run servers upon which the lives of digital consciousnesses might be staged, this could result in the efflorescence of approximately ten to the power of fifty-eight beings. For any decision we made now, an astronomical number of lives hung in the balance. In the first month of the pandemic, Toby Ord published a book called “The Precipice.” According to Ord’s “credences,” the chances of human extinction during the next century stand at about 1–6, or the odds of Russian roulette. The major contributor to existential risk was not climate change—which, even in a worst-case scenario, is unlikely to render the planet wholly uninhabitable. (New Zealand, for example, might be fine.) Instead, he singles out engineered pathogens and runaway artificial intelligence. DNA editing might allow a scientist to create a superbug that could wipe us out. A well-intentioned A.I. might, as in one of Bostrom’s famous thought experiments, turn a directive to make paper clips into an effort to do so with all available atoms. Ord imagines a power-hungry superintelligence distributing thousands of copies of itself around the world, using this botnet to win financial resources, and gaining dominion “by manipulating the leaders of major world powers (blackmail, or the promise of future power); or by having the humans under its control use weapons of mass destruction to cripple the rest of humanity.” These risks might have a probability close to zero, but a negligible possibility times a catastrophic outcome is still very bad; significant action is now of paramount concern. “We can state with confidence that humanity spends more on ice cream every year than on ensuring that the technologies we develop do not destroy us,” Ord writes. These ideas were grouped together under the new heading of “longtermism.” When Ord first mentioned existential risk, MacAskill thought that it was a totally crackpot idea. He was uneasy about how it related to his own priorities, and remembers attending a meeting about A.I. risk and feeling frustrated by the vagueness of the potential impacts. But profound improvements in the past half decade (DeepMind’s AlphaGo, OpenAI’s GPT-3), combined with arguments about the exponential gains in computational power compared to biological benchmarks, cited by Ajeya Cotra, of Open Philanthropy, brought him around. Ord believed that if we made it through the next century or two we would have about even odds of achieving the best possible long-haul future—a universe filled with the descendants of humanity, living lives of untold, unimaginable, and unspecified freedom and pleasure. MacAskill worries in his new book that annihilation per se might not be the only risk. He believes in the radical contingency of moral progress; he argues, for example, that, without the agitation of a small cohort of abolitionists, slavery might have lasted much longer. Even a benign A.I. overlord, by contrast, might produce “value lock-in”: a world governed by code that forever stalls the arc of moral progress. (On the other hand, if we don’t avail ourselves of the possibilities of A.I., we might face technological stagnation—in over our heads on a deteriorating planet.) MacAskill understands that worries about a sci-fi apocalypse might sound glib when “there are real problems in the world facing real people,” he writes. The distant future, however, is likely to be even more crowded with real people. And if spatial distance is irrelevant to our regard for starvation overseas, temporal distance should be an equally poor excuse. “I now believe the world’s long-run fate depends in part on the choices we make in our lifetimes,” he writes. This amounts to nothing less than a “moral revolution.” In 2012, while MacAskill was in Cambridge, Massachusetts, delivering his earning-to-give spiel, he heard of a promising M.I.T. undergraduate named Sam Bankman-Fried and invited him to lunch. Bankman-Fried’s parents are scholars at Stanford Law School, and he had been raised as a card-carrying consequentialist. He had recently become vegan and was in the market for a righteous path. MacAskill pitched him on earning to give. Bankman-Fried approached an animal-welfare group and asked its members whether they had more use for his volunteer time or for his money, and they strongly preferred the money. The next year, Bankman-Fried invited MacAskill to stay at his coed nerd frat, where everyone slept in the attic to preserve the living area for video and board games. In 2014, Bankman-Fried graduated with a degree in physics, and went to work at Jane Street. He says that he donated about half his salary, giving some to animal-welfare organizations and the rest to E.A. movement-building initiatives. In 2017, he started Alameda Research, a crypto-trading firm that sought to exploit an arbitrage opportunity wherein bitcoin, for various reasons, traded higher on Japanese exchanges. The scheme was elaborate, and required that his employees spend a lot of time in bank branches, but he made a ten-per-cent profit on every trade. One crypto impresario told me, “We all knew that was possible in theory, but S.B.F. was the one who actually went and did it.” In 2019, Bankman-Fried founded a user-friendly crypto exchange called FTX. One of the exchange’s most profitable products is not yet legal in the United States; he shopped for more congenial jurisdictions and set up in the Bahamas. By the time Bankman-Fried was twenty-nine, Forbes estimated his net worth at about twenty-six billion dollars, making him the twenty-fifth-richest American. At least three of his co-workers, depending on the fluctuating price of crypto assets, are also E.A. billionaires. Nishad Singh had been working an earning-to-give job at Facebook when Bankman-Fried invited him to join. Singh told me, “I had been somewhat dishonest with myself. I might have been picking a path that let me lead the life I wanted to lead, but I was not picking the path of maximal good.” Bankman-Fried has refined the persona of a dishevelled, savantlike techno-fakir. He has been widely advertised for his fiscal chastity—he drives a Toyota Corolla and, on the rare occasion that he leaves the office, lives with nine roommates. Even when beds are ready to hand, he pitches down on a beanbag. According to the Times , visitors are sometimes scheduled to arrive for meetings during his naps; they watch from a conference room as he wakes up and pads over in cargo shorts. But his marketing efforts have been splashy. FTX spent an estimated twenty million dollars on an ad campaign featuring Tom Brady and Gisele Bündchen, and bought the naming rights to the Miami Heat’s arena for a hundred and thirty-five million dollars. Last year, MacAskill contacted Bankman-Fried to check in about his promise: “Someone gets very rich and, it’s, like, O.K., remember the altruism side? I called him and said, ‘So, still planning to donate?’ ” Bankman-Fried pledged to give nearly all his money away; if suitable opportunities are found, he’s willing to contribute more than a billion dollars a year. Bankman-Fried had longtermist views before they held sway over MacAskill, and has always been, MacAskill remembers, “particularly excited by pandemics”—a normal thing to hear among E.A.s. Bankman-Fried set up a foundation, the FTX Future Fund, and hired the longtermist philosopher Nick Beckstead as C.E.O. This past December, MacAskill finished the manuscript of his new book, and hoped to spend more time with his partner, Holly Morgan, an early E.A. and the biggest single input to his stability. Instead, Bankman-Fried enlisted him as a Future Fund adviser. (He offered MacAskill a “generous” six-figure salary, but MacAskill replied that he was just going to redistribute the money anyway.) Overnight, the funds potentially available to E.A. organizations more than doubled, and MacAskill was in a position not only to theorize but to disburse on a grand scale. The Future Fund’s initial ideas included the development of early-detection systems for unknown pathogens, and vast improvements in personal protective equipment—including a suit “designed to allow severely immunocompromised people to lead relatively normal lives.” With the organization’s support, someone might buy a large coal mine to keep the coal in the ground—not only to reduce our carbon footprint but to insure that humanity has available deposits should some desperate future generation have to reindustrialize. The foundation was keen to hear proposals for “civilizational recovery drills,” and to fund organizations like ALLFED , which develops food sources that could, in a nuclear winter, be cultivated without sunlight. (So far, it’s mostly mushrooms, but seaweed shows promise.) Inevitably, there were calls for bunkers where, at any given time, a subset of humanity would live in a sealed ark. Along with the money came glamorous attractors. Last week, Elon Musk tweeted, of MacAskill’s new book, “This is a close match for my philosophy.” (For a brief period, Musk reportedly assigned responsibility for the charitable distribution of nearly six billion dollars to Igor Kurganov, a former professional poker player and a onetime housemate of MacAskill’s; in MacAskill’s book, Kurganov is thanked for “unfettered prances round the garden.”) MacAskill has long been friendly with the actor Joseph Gordon-Levitt, who told me, “Last year, Will called me up about ‘What We Owe the Future,’ to talk about what it might be like to adapt the book for the screen.” MacAskill felt that such movies as “Deep Impact” and “Armageddon” had prompted governments to take the asteroid threat more seriously, and that “The Terminator” ’s Skynet wasn’t a bad way to discuss the menace of A.I. Gordon-Levitt said, “We’ve started figuring out how it could work to build a pipeline from the E.A. community to my creative one, and seeing if we can’t get some of these ideas out there into the world.” “Remember, he created us in his image a really long time ago.” Cartoon by Zachary Kanin Copy link to cartoon Copy link to cartoon Link copied Shop Shop Bankman-Fried has made an all-in commitment to longtermism. In May, I spoke with him over video chat, and he seemed almost willfully distracted: he didn’t bother to hide the fact that he was doing things on several monitors at once. (As a child, his brother has said, Bankman-Fried was so bored by the pace of regular board games that it became his custom to play multiple games at once, ideally with speed timers.) He told me that he never had a bed-nets phase, and considered neartermist causes—global health and poverty—to be more emotionally driven. He was happy for some money to continue to flow to those priorities, but they were not his own. “The majority of donations should go to places with a longtermist mind-set,” he said, although he added that some intercessions coded as short term have important long-term implications. He paused to pay attention for a moment. “I want to be careful about being too dictatorial about it, or too prescriptive about how other people should feel. But I did feel like the longtermist argument was very compelling. I couldn’t refute it. It was clearly the right thing.” The shift to longtermism, and the movement’s new proximity to wealth and power—developments that were not uncorrelated—generated internal discord. In December, Carla Zoe Cremer and Luke Kemp published a paper called “Democratising Risk,” which criticized the “techno-utopian approach” of longtermists. Some E.A.s, Cremer wrote in a forum post, had attempted to thwart the paper’s publication: “These individuals—often senior scholars within the field—told us in private that they were concerned that any critique of central figures in EA would result in an inability to secure funding.” MacAskill responded solicitously in the comments, and when they finally had a chance to meet, in February, Cremer presented a list of proposed “structural reforms” to E.A., including whistle-blower protections and a broad democratization of E.A.’s structure. Cremer felt that MacAskill, the movement leader who gave her the most hope, had listened perfunctorily and done nothing. “I can’t wear the E.A. hoodie to the gym anymore,” she told me. “Many young people identify with E.A. as a movement or a community or even a family—but underneath this is a set of institutions that are becoming increasingly powerful.” Last year, the Centre for Effective Altruism bought Wytham Abbey, a palatial estate near Oxford, built in 1480. Money, which no longer seemed an object, was increasingly being reinvested in the community itself. The math could work out: it was a canny investment to spend thousands of dollars to recruit the next Sam Bankman-Fried. But the logic of the exponential downstream had some kinship with a multilevel-marketing ploy. Similarly, if you assigned an arbitrarily high value to an E.A.’s hourly output, it was easy to justify luxuries such as laundry services for undergraduate groups, or, as one person put it to me, wincing, “retreats to teach people how to run retreats.” Josh Morrison, a kidney donor and the founder of a pandemic-response organization, commented on the forum, “The Ponzi-ishness of the whole thing doesn’t quite sit well.” One disaffected E.A. worried that the “outside view” might be neglected in a community that felt increasingly insular. “I know E.A.s who no longer seek out the opinions or input of their colleagues at work, because they take themselves to have a higher I.Q.,” she said. “The common criticism thrown at the Tory Party here is that they go straight from Oxford to a job in Parliament. How could they possibly solve problems that they themselves have never come into contact with? They’ve never been at the coalface. The same criticism could be said of many E.A.s.” The community’s priorities were prone to capture by its funders. Cremer said, of Bankman-Fried, “Now everyone is in the Bahamas, and now all of a sudden we have to listen to three-hour podcasts with him, because he’s the one with all the money. He’s good at crypto so he must be good at public policy . . . what?!” The bed-nets era had been chided as myopic, but at least its outcomes were concrete. The same could not be said of longtermism. Among the better objections was a charge of “cluelessness,” or the recognition that we have trouble projecting decades down the line, let alone millennia. It does, in any case, seem convenient that a group of moral philosophers and computer scientists happened to conclude that the people most likely to safeguard humanity’s future are moral philosophers and computer scientists. The movement had prided itself on its resolute secularism, but longtermist dread recalled the verse in the Book of Revelation that warns of a time when the stars will fall from the sky like unripe figs. Rob Reich, the Stanford political scientist, who once sat on the board of GiveWell, told me, “They are the secular apocalypticists of our age, not much different than Savonarola—the world is ending and we need a radical break with our previous practices.” Longtermism is invariably a phenomenon of its time: in the nineteen-seventies, sophisticated fans of “Soylent Green” feared a population explosion; in the era of “The Matrix,” people are prone to agonize about A.I. In the week I spent in Oxford, I heard almost nothing about the month-old war in Ukraine. I could see how comforting it was, when everything seemed so awful, to take refuge on the higher plane of millenarianism. Longtermism also led to some bizarre conclusions. Depending on the probabilities one attaches to this or that outcome, something like a .0001-per-cent reduction in over-all existential risk might be worth more than the effort to save a billion people today. (In the literature, this argument is called “fanaticism,” and, though it remains a subject of lively scholastic debate in E.A. circles, nobody openly endorses it.) Referring to such regrettable episodes as all previous epidemics and wars, Nick Bostrom once wrote, “Tragic as such events are to the people immediately affected, in the big picture of things—from the perspective of humankind as a whole—even the worst of these catastrophes are mere ripples on the surface of the sea of life.” Nick Beckstead, the philosopher at the helm of the Future Fund, remarked in his 2013 dissertation, “Richer countries have substantially more innovation, and their workers are much more economically productive. By ordinary standards—at least by ordinary enlightened humanitarian standards—saving and improving lives in rich countries is about equally as important as saving and improving lives in poor countries, provided lives are improved by roughly comparable amounts. But it now seems more plausible to me that saving a life in a rich country is substantially more important than saving a life in a poor country.” Beckstead’s comment may formalize what many philanthropists already do: the venture capitalist John Doerr recently gave a billion dollars to already over-endowed Stanford to bankroll a school for studying climate change. But such extreme trade-offs were not an easy sell. As Holden Karnofsky once put it, most people who sit down to reason through these things from a place of compassion don’t expect to arrive at such conclusions—or want to. E.A. lifers told me that they had been unable to bring themselves to feel as though existential risk from out-of-control A.I. presented the same kind of “gut punch” as global poverty, but that they were generally ready to defer to the smart people who thought otherwise. Nishad Singh told me that he, like many longtermists, continues to donate to alleviate current misfortune: “I still do the neartermist thing, personally, to keep the fire in my belly.” One of the ironies of the longtermist correction was that, all of a sudden, politics was on the table in a new way. In 2020, Bankman-Fried donated more than five million dollars to Joe Biden’s campaign, making him one of the top Democratic contributors. Given anxieties about the nuclear codes, his action wasn’t hard to justify. But Bankman-Fried has his own interests—the only times he’s been known to wear pants is in front of Congress, where he urges crypto deregulation—and electoral interventions are slippery. This year, Bankman-Fried’s super PAC gave more than ten million dollars to support Carrick Flynn, the first explicitly E.A.-affiliated congressional candidate, in a crowded Democratic primary in a new Oregon district. Flynn ran on a longtermist message about pandemic preparedness. (His background was in A.I. safety, but this was clearly a non-starter.) He did little to tailor his platform to the particular needs of the local constituency, which has a substantial Latino population, and he lost by a large margin. Part of the initial attraction of the movement, for a certain sort of person, was that E.A. existed in a realm outside the business of politics as usual. Now its biggest funder was doing something that looked a lot like an attempt to buy an open congressional seat. There wasn’t necessarily anything wrong, from a means-end perspective. But it did seem as though, overnight, the ground had shifted underneath the movement’s rank and file. From the perspective of the early days of hard benchmarks, the opportunity cost of ten million dollars spent on a long-shot primary was about twenty-five hundred lives. One of the reasons MacAskill is so venerated by his followers is that, despite his rarefied intellect, he seems to experience the tensions of the movement on a somatic level. In late March, he gave a talk at EAGxOxford, a conference of some six hundred and fifty young E.A.s. MacAskill had celebrated his thirty-fifth birthday the night before—a small group of largely E.A.-unaffiliated friends had gone out into the fields in pagan costumes to participate in a Lithuanian rite of spring. MacAskill told me that he’d never been happier with his life, and he definitely looked a little worse for wear. At the conference, he was introduced, to rapturous applause, under a portrait of George III wearing a gold damask suit. The room featured a series of ornately carved wooden clocks, all of which displayed contrary times; an apologetic sign read “Clocks undergoing maintenance,” but it was an odd portent for a talk about the future. Afterward, MacAskill had a difficult time negotiating his exit from the marbled hall—he was constantly being stopped for selfies, or interrupted to talk about some neglected nuclear risk by a guy dressed like Mad Max, or detained by a teen-ager who wanted to know how he felt about the structural disadvantages that kept poor countries poor. One young woman, two months shy of her high-school graduation, told him that she had stayed up all night fretting—she felt bad that she had paid for private lodging for the weekend, and wanted to know how to harmonize her own appetites with the needs of others. When MacAskill speaks, he often makes a gesture that resembles the stringing of gossamer in midair, as if threading narrow bridges across pitfalls in understanding. He told the young woman that he tried to cultivate his own disposition so that the contradictions disappeared: “E.A. has motivated me to do stuff that’s hard or intimidating or makes me feel scared, but our preferences are malleable, and these activities become rewarding.” He warned her, however, that it was “pretty easy to justify anything on altruistic grounds if your reasoning is skewed enough. Should I have a less nice apartment? Should I not have Bluetooth headphones?” He sighed and fluttered his eyelids, unable to provide the answers she sought. “After all this time, I guess I don’t have a better suggestion for what to do than to give ten per cent. It’s a costly signal of your moral commitment.” Beyond that, he continued, “try to do the best you can and not constantly think of the suffering of the world.” MacAskill, who still does his own laundry, was deeply ambivalent about the deterioration of frugality norms in the community. The Centre for Effective Altruism’s first office had been in an overcrowded firetrap of a basement beneath an estate agent’s office. “I get a lot of joy thinking about the early stages—every day for lunch we had Sainsbury’s baguettes with hummus, and it felt morally appropriate,” MacAskill told me. “Now we have this nice office with catered vegan lunches. We could hire a hedge-fund guy at market rates, and that makes sense! But there’s an aesthetic part of me that feels really sad about these compromises with the world.” Cartoon by Navied Mahdavian Copy link to cartoon Copy link to cartoon Link copied Shop Shop I asked about the slippage, in his response, from moral to aesthetic propriety. He said, “Imagine you’re travelling through a foreign country. During a long bus ride, there’s an explosion and the bus overturns. When you come to, you find yourself in a conflict zone. Your travel companion is trapped under the bus, looking into your eyes and begging for help. A few metres away, a bloody child screams in pain. At the same time, you hear the ticking of another explosive. In the distance, gunshots fire. That is the state of the world. We have just a horrific set of choices in front of us, so it feels virtuous, and morally appropriate, to vomit, or scream, or cry.” MacAskill replenishes his own moral and aesthetic commitment through his personal giving, even if he can now fund-raise more in an hour than he could donate in a year. In “What We Owe the Future,” he is careful to sidestep the notion that efforts on behalf of trillions of theoretical future humans might be fundamentally irreconcilable with the neartermist world-on-fire agenda. During a break in the conference, he whisked me to a footpath called Addison’s Walk, pointing out the fritillaries, and a muntjac deer in the undergrowth. “We need to stay away from totalizing thinking,” he said. “These thought experiments about suffering now versus suffering in the future—once you start actually doing the work, you’re obviously informed by common sense. For almost any path, there’s almost always a way to do things in a coöperative, nonfanatical way.” Pandemic preparedness, for example, is equally important in the near term, and some people think that A.I. alignment will be relevant in our lifetimes. Members of the mutinous cohort told me that the movement’s leaders were not to be taken at their word—that they would say anything in public to maximize impact. Some of the paranoia—rumor-mill references to secret Google docs and ruthless clandestine councils—seemed overstated, but there was a core cadre that exercised control over public messaging; its members debated, for example, how to formulate their position that climate change was probably not as important as runaway A.I. without sounding like denialists or jerks. When I told the disaffected E.A. that MacAskill seemed of two minds about longtermism as an absolute priority, she was less convinced of his sincerity: “I think Will does lean more toward the fanatical side of things, but I think he has the awareness—off the merit of his own social skills or feedback—of the way the more fanatical versions sound to people, and how those might affect the appeal and credibility of the movement. He has toned it down in his communications and has also encouraged other E.A. orgs to do the same.” In a private working document about how to pitch longtermism, extensive editing has reduced the message to three concise and palatable takeaways. The disaffected E.A. warned me to be wary whenever MacAskill spoke slowly: these were the moments, she said, when he was triaging his commitment to honesty and the objectives of optimized P.R. With so many future lives at stake, the question of honor in the present could be an open one. Was MacAskill’s gambit with me—the wild swimming in the frigid lake—merely a calculation that it was best to start things off with a showy abdication of the calculus? But, during my week in Oxford, it was hard to shake my impression of him as heartrendingly genuine—a sweaty young postulant who had looked into the abyss and was narrating in real time as he constructed a frail bridge to the far side. I asked him what made him most apprehensive, and he thought for a moment. “My No. 1 worry is: what if we’re focussed on entirely the wrong things?” he said. “What if we’re just wrong? What if A.I. is just a distraction? Like, look at the Greens and nuclear power.” Panic about meltdowns appears, in retrospect, to have driven disastrously short-term bets. MacAskill paused for a long time. “It’s very, very easy to be totally mistaken.” We returned to the conference courtyard for lunch, where an eclectic vegan buffet had been set up. The line was long, and MacAskill had only five minutes free. He tried to gauge the longest amount of time he could spend queuing, and in the end we contritely cut in at about the halfway point. The buffet table had two stacks of plates, and a fly alighted briefly on one of them. In MacAskill’s presence, it’s difficult not to feel as though everything is an occasion for moral distinction. I felt that I had no choice but to take the plate the fly had landed on. MacAskill nodded approvingly. “That was altruistic of you,” he said. The Future Fund has offices on a high floor of a building in downtown Berkeley, with panoramic views of the hills. The décor is of the equations-on-a-whiteboard variety, and MacAskill told me that the water-cooler talk runs the gamut from “What are your timelines?” to “What’s your p(doom)?”—when will we achieve artificial general intelligence, and what’s your probability of cataclysm? When I visited recently, Nick Beckstead, the C.E.O., assembled the team for a morning standup, and began by complimenting Ketan Ramakrishnan, a young philosopher, on his dancing at an E.A. wedding they’d all attended. The wedding had been for Matt Wage, the early earning-to-give convert. The employees had planned to go to Napa for the weekend, but they were completing their first open call for funding, and there was never a moment to spare. First, some had skipped Friday’s rehearsal dinner. Then they figured that they wouldn’t be missed at the Sunday brunch. In the end, they’d left the reception early, too. Wage understood. The opportunity cost of their time was high. The Future Fund agreed to finance sixty-nine projects, for a total of about twenty-seven million dollars. The most heavily awarded category was biorisk, followed by A.I.-alignment research and various forecasting projects; the team had funded, among other things, the mushroom caterers of the coming nuclear winter. Beckstead’s new role, and accumulated life experience, seemed to have mellowed his more scholarly inclinations. “I personally find it tough to be all in on a philosophical framework in the fanatical sense,” he said. “Longtermism has been my main focus, and will be my main focus. But I also feel like there’s some value in doing some stuff that does deliver more concrete wins,” and which shows that “we’re morally serious people who are not just doing vanity projects about fancy technology.” It remains plausible that the best longtermist strategy is more mundanely custodial. In 1955, the computer scientist John von Neumann, a hero of E.A.s, concluded, “What safeguard remains? Apparently only day-to-day—or perhaps year-to-year—opportunistic measures, a long sequence of small, correct decisions.” MacAskill had worried that one of the best new initiatives he’d heard about—the Lead Exposure Elimination Project, which was working to rid the world of lead poisoning—might be a hard sell, but everyone had readily agreed to fund it. From the outside, E.A. could look like a chipper doomsday cult intent on imposing its narrow vision on the world. From the inside, its adherents feel as though they are just trying to figure out how to allocate limited resources—a task that most charities and governments undertake with perhaps one thought too few. “A.I. safety is such an unusual and uncertain area that it’s tempting to simply hope the risks aren’t real,” Ramakrishnan said. “One thing I like about the E.A. community is that it’s willing to deal with the knottiness, and just try to reason as carefully as possible.” There were also signs that E.A.s were, despite the hazard of fanaticism, increasingly prone to pluralism themselves. Open Philanthropy has embraced an ethic of “worldview diversification,” whereby we might give up on perfect commensurability and acknowledge it is O.K. that some money be reserved to address the suffering of chickens, some for the suffering of the poor, and some for a computational eschatology. After almost a decade of first-principles reasoning, E.A.s had effectively reinvented the mixed-portfolio model of many philanthropic foundations. One sweltering afternoon, MacAskill and I went for a walk in the Berkeley hills. What had begun as a set of techniques and approaches had become an identity, and what was once a diffuse coalition had hardened into a powerful but fractious constituency; the burden of leadership fell heavily on his shoulders. “One of the things I liked about early E.A. was the unapologetic nature of it,” he said. “Some charities are better by a lot! There was this commitment to truth as a primary goal. Now I constantly think of how people will respond to things—that people might be unhappy.” He strung another invisible thread in the air. “Am I an academic who says what he thinks? Or am I representative of this movement? And, if so, what responsibilities do I have? There are some things that become compromised there.” We passed People’s Park, which had become a tent city, but his eyes flicked toward the horizon. “Sometimes, as I think about what I’m going to do after the book comes out, I think, I have a job as the intellectual face of this broader movement, and sometimes I just want to be an independent pair of eyes on the world.” ♦ New Yorker Favorites First she scandalized Washington. Then she became a princess. The unravelling of an expert on serial killers. What exactly happened between Neanderthals and humans ? When you eat a dried fig, you’re probably chewing wasp mummies, too. The meanings of the Muslim head scarf. The slippery scams of the olive-oil industry. Critics on the classics: our 1991 review of “Thelma & Louise.” Sign up for our daily newsletter to receive the best stories from The New Yorker. Weekly E-mail address Sign up By signing up, you agree to our User Agreement and Privacy Policy & Cookie Statement. This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply. Letter from Amsterdam By Patrick Radden Keefe Annals of Law By Eli Hager A Reporter at Large By Ariel Levy American Chronicles By Ronan Farrow Sections News Books & Culture Fiction & Poetry Humor & Cartoons Magazine Crossword Video Podcasts Archive Goings On More Customer Care Shop The New Yorker Buy Covers and Cartoons Condé Nast Store Digital Access Newsletters Jigsaw Puzzle RSS About Careers Contact F.A.Q. Media Kit Press Accessibility Help © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. The New Yorker may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Facebook X Snapchat YouTube Instagram Do Not Sell My Personal Info "

"Can new brain-computer interface technology read your thoughts? - Vox"

"https://www.vox.com/future-perfect/2023/5/4/23708162/neurotechnology-mind-reading-brain-neuralink-brain-computer-interface"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence Mind-reading technology has arrived An AI-powered “brain decoder” can now read your thoughts with surprising accuracy. By Sigal Samuel May 4, 2023, 7:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Mind-reading technology has arrived Reddit Pocket Flipboard Email PhD student Jerry Tang prepares to collect brain activity data in the Biomedical Imaging Center at the University of Texas at Austin. Nolan Zunk/The University of Texas at Austin This story is part of a group of stories called Finding the best ways to do good. For a few years now, I’ve been writing articles on neurotechnology with downright Orwellian headlines. Headlines that warn “ Facebook is building tech to read your mind ” and “ Brain-reading tech is coming. ” Well, the technology is no longer just “coming.” It’s here. With the help of AI, scientists from the University of Texas at Austin have developed a technique that can translate people’s brain activity — like the unspoken thoughts swirling through our minds — into actual speech, according to a study published in Nature. In the past, researchers have shown that they can decode unspoken language by implanting electrodes in the brain and then using an algorithm that reads the brain’s activity and translates it into text on a computer screen. But that approach is very invasive, requiring surgery. It appealed only to a subset of patients, like those with paralysis, for whom the benefits were worth the costs. So researchers also developed techniques that didn’t involve surgical implants. They were good enough to decode basic brain states, like fatigue, or very short phrases — but not much more. Now we’ve got a non-invasive brain-computer interface (BCI) that can decode continuous language from the brain, so somebody else can read the general gist of what we’re thinking even if we haven’t uttered a single word. How is that possible? It comes down to the marriage of two technologies: fMRI scans, which measure blood flow to different areas of the brain, and large AI language models, similar to the now-infamous ChatGPT. In the University of Texas study, three participants listened to 16 hours of storytelling podcasts like The Moth while scientists used an fMRI machine to track the change in blood flow in their brains. That data allowed the scientists, using an AI model, to associate a phrase with how each person’s brain looks when it hears that specific phrase. Because the number of possible word sequences is so vast, and many of them would be gibberish, the scientists also used a language model — specifically, GPT-1 — to narrow down possible sequences to well-formed English and predict which words are likeliest to come next in a sequence. The result is a decoder that gets the gist right, even though it doesn’t nail every single word. For example, participants were asked to imagine telling a story while in the fMRI machine. Later, they repeated it aloud so the scientists could see how well the decoded story matched up with the original. When the participant thought, “Look for a message from my wife saying that she had changed her mind and that she was coming back,” the decoder translated: “To see her for some reason I thought she would come to me and say she misses me.” Here’s another example. When the participant thought, “Coming down a hill at me on a skateboard and he was going really fast and he stopped just in time,” the decoder translated: “He couldn’t get to me fast enough he drove straight up into my lane and tried to ram me.” It’s not a word-for-word translation, but much of the general meaning is preserved. This represents a breakthrough that goes well beyond what previous brain-reading tech could do — and one that raises serious ethical questions. The staggering ethical implications of brain-computer interfaces It might be hard to believe that this is real, not something out of a Neal Stephenson or William Gibson novel. But this kind of tech is already changing people’s lives. Over the past dozen years, a number of paralyzed patients have received brain implants that allow them to move a computer cursor or control robotic arms with their thoughts. Elon Musk’s Neuralink and Mark Zuckerberg’s Meta are working on BCIs that could pick up thoughts directly from your neurons and translate them into words in real time, which could one day allow you to control your phone or computer with just your thoughts. Non-invasive, even portable BCIs that can read thoughts are still years away from commercial availability — after all, you can’t lug around an fMRI machine, which can cost as much as $3 million. But the study’s decoding approach could eventually be adapted for portable systems like functional near-infrared spectroscopy (fNIRS), which measures the same activity as fMRI, although with a lower resolution. Is that a good thing? As with many cutting-edge innovations, this one stands to raise serious ethical quandaries. Let’s start with the obvious. Our brains are the final privacy frontier. They’re the seat of our personal identity and our most intimate thoughts. If those precious three pounds of goo in our craniums aren’t ours to control, what is? Imagine a scenario where companies have access to people’s brain data. They could use that data to market products to us in ways our brains find practically irresistible. Since our purchasing decisions are largely driven by unconscious impressions, advertisers can’t get very helpful intel from consumer surveys or focus groups. They can get much better intel by going directly to the source: the consumer’s brain. Already, advertisers in the nascent field of “neuromarketing” are attempting to do just that, by studying how people’s brains react as they watch commercials. If advertisers get brain data on a massive scale, you might find yourself with a powerful urge to buy certain products without being sure why. Or imagine a scenario where governments use BCIs for surveillance, or police use them for interrogations. The principle against self-incrimination — enshrined in the US Constitution — could become meaningless in a world where the authorities are empowered to eavesdrop on your mental state without your consent. It’s a scenario reminiscent of the sci-fi movie Minority Report , in which a special police unit called the PreCrime Division identifies and arrests murderers before they commit their crimes. Some neuroethicists argue that the potential for misuse of these technologies is so great that we need revamped human rights laws to protect us before they’re rolled out. “This research shows how rapidly generative AI is enabling even our thoughts to be read,” Nita Farahany, author of The Battle for Your Brain , told me. “Before neurotechnology is used at scale in society, we need to protect humanity with a right to self-determination over our brains and mental experiences.” Related New technologies are promising a shortcut to enlightenment As for the study’s authors, they’re optimistic — for now. “Our privacy analysis suggests that subject cooperation is currently required both to train and to apply the decoder,” they write. Crucially, the process only worked with cooperative participants who had participated willingly in training the decoder. And those participants could throw off the decoder if they later wanted to; when they put up resistance by naming animals or counting, the results were unusable. For people on whose brain activity the decoder had not been trained, the results were gibberish. “However, future developments might enable decoders to bypass these requirements,” the authors warn. “Moreover, even if decoder predictions are inaccurate without subject cooperation, they could be intentionally misinterpreted for malicious purposes.” This is exactly the sort of future that worries Farahany. “We are literally at the moment before, where we could make choices to preserve our cognitive liberty — our rights to self-determination over our brains and mental experiences — or allow this technology to develop without safeguards,” she told me. “This paper makes clear that the moment is a very short one. We have a last chance to get this right for humanity.” Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via In This Stream The rapid development of AI has benefits — and poses serious risks Elon Musk wants to merge humans with AI. How many brains will be damaged along the way? Mind-reading technology has arrived Finally, a realistic roadmap for getting AI companies in check 55 Next Up In Future Perfect Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? Is the green texting bubble about to burst? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. The Latest Most of Israel’s weapons imports come from the US. Now Biden is rushing even more arms. By Jonathan Guyer Formula 1 grew too fast. Now its new fans are tuning out. By Izzie Ramirez The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained By A.W. Ohlheiser and Li Zhou Your phone is the key to your digital life. Make sure you know what to do if you lose it. By Sara Morrison Alex Murdaugh stands guilty of killing his wife and son. That’s just scratching the surface. By Aja Romano Is the green texting bubble about to burst? By Sara Morrison Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Neurotechnology is here. Without laws, your brain’s privacy is at risk. - Vox"

"https://www.vox.com/future-perfect/2023/3/17/23638325/neurotechnology-ethics-neurofeedback-brain-stimulation-nita-farahany"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Emerging Tech Your brain may not be private much longer Neurotechnology is upon us. Your brain urgently needs new rights. By Sigal Samuel Mar 17, 2023, 7:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Your brain may not be private much longer Reddit Pocket Flipboard Email A woman equipped with a brain-computer interface, one form of neurotechnology. Florian Voggeneder/Guger Technologies/AP This story is part of a group of stories called Finding the best ways to do good. If you’ve ever wished your brain was more user-friendly, neurotechnology might seem like a dream come true. It’s all about offering you ways to hack your brain , getting it to do more of what you want and less of what you don’t want. There are “ nootropics ” — also known as “smart drugs” or “cognitive enhancers” — pills that supposedly give your brain a boost. There’s neurofeedback, a tool for training yourself to regulate your brain waves; research has shown it has the potential to help people struggling with conditions like ADHD and PTSD. There’s brain stimulation, which uses electric currents to directly target certain brain areas and change their behavior; it’s shown promise in treating severe depression by disrupting depression-linked neural activity. Oh, and Elon Musk and Mark Zuckerberg are working on brain-computer interfaces that could pick up thoughts directly from your neurons and translate them into words in real time, which could one day allow you to control your phone or computer with just your thoughts. Some of these technologies can offer very valuable help to people who need it. Brain-computer interfaces, for example, are already helping some paralyzed people. But neurotechnology can also seriously threaten privacy and freedom of thought. In China, the government is mining data from some employees’ brains by having them wear caps that scan their brainwaves for anxiety, rage, or fatigue. Lest you think other countries are above this kind of mind-reading, police worldwide have been exploring “brain-fingerprinting” technology , which analyzes automatic responses that occur in our brains when we encounter stimuli we recognize. The claim is that this could enable police to interrogate a suspect’s brain; his brain responses would be more negative for faces or phrases he doesn’t recognize than for faces or phrases he does recognize. The tech is scientifically questionable , yet India’s police have used it since 2003, Singapore’s police bought it in 2013, and the Florida State Police signed a contract to use it in 2014. All these developments worry Nita Farahany, an ethicist and lawyer at Duke University and the author of a new book, The Battle for Your Brain: Defending the Right to Think Freely in the Age of Neurotechnology. As an Iranian American, she’s particularly scared of a future where governments read minds and punish people for thinking about, say, organizing to overthrow an authoritarian regime. “Will George Orwell’s dystopian vision of thoughtcrime become a modern-day reality?” she writes. Yet Farahany is no Luddite: She believes we should be free to embrace neurotechnology if we choose — but only if we also update our laws so we can reap its benefits without courting its risks. She argues that we need to revamp human rights law with a focus on protecting our cognitive liberty — the right to self-determination over our brains, our thoughts, our inner world. I talked to Farahany about the ethical dilemmas raised by emerging neurotechnologies. Should you have the right to enhance your brain however you want? What about erasing painful memories, à la Eternal Sunshine of the Spotless Mind ? A transcript of our conversation, condensed and edited for clarity, follows. As always, you can listen and follow The Gray Area on Apple Podcasts , Google Podcasts , Spotify , Stitcher , or wherever you find podcasts. New episodes drop every Monday and Thursday. Sigal Samuel Neurotechnology seems like it’s on a collision course with freedom of thought. Do you think that huge risk is counterbalanced by the benefits we stand to reap? Nita Farahany The risks are profound. And the gaps in our existing rights are deeply problematic. So, where do I come out on the balance? I’m a little bit of a tech inevitabilist. I think the idea that you can somehow stop the train and say, “On balance, maybe this isn’t better for humanity and therefore we shouldn’t introduce it” — I just don’t see it working. Maybe people will say, “My brain is too sacred and the risks are so profound that I’m not willing to do it myself,” but with the ways that people unwittingly give up information all the time and the benefits that are promised to them, I think that’s unlikely. I think we’ve got to carve out a different approach. Sigal Samuel I hear the idea that maybe we can’t or don’t want to ban the tech wholesale, but I do want to push back a bit on this idea of tech inevitability. That strikes me as a myth that the tech world likes to tell itself and all of us. History is full of examples of technologies that we’ve either decided not to build or that we’ve built but placed very tight restrictions on — nuclear weapons, genetic engineering. I tend to think more in terms of, how can we shape the incentive structure so that companies or governments will be less likely to roll out certain technologies? And of course, part of the incentive structure has to be law. Nita Farahany Let me respond to [the idea of placing] tight regulations around it. Here’s the thing that keeps me from going there: We have an unbelievable burden of neurological disease and mental illness worldwide. Even as our physical health overall improves, our mental health is deteriorating, and depression rates are skyrocketing. I think we need urgently to address that. And part of the reason that we haven’t urgently addressed that is because we haven’t invested the same, and put brain health and wellness on the same level, as all the rest of our physical health. And I think empowering people with information to be able to take their mental health and brain health into their own hands could be transformational for those trends. My hope is to find some way to make that possible. The dystopian possibilities of this technology are off the charts, but so is the possibility of finally claiming cognitive freedom in the sense of true mental health and well-being. Sigal Samuel What exactly is cognitive freedom or cognitive liberty to you? Nita Farahany It’s a right from and a right to. Overall, I define it as the right to self-determination over our brains and mental experiences. That means a right from interference, and a right to access, change, and improve our own brains. That’s maybe why I come out differently than some people who might just say, let’s tightly regulate this or just ban it. Related New technologies are promising a shortcut to enlightenment Sigal Samuel In terms of a freedom to , there are all kinds of cognitive enhancements that people might be interested in. I’m thinking of nootropics or smart drugs, but there are also other types of neurotechnology that people could potentially use — neurofeedback, brain stimulation. Even if we imagine that we’re in a world where these technologies are equally accessible to all, I still wonder: Should workers actually be forbidden from cognitive enhancements because it creates a norm that others might then feel subject to? Will the pressure to enhance become coercive so people end up using smart drugs or devices even though they didn’t want to? Nita Farahany It’s a good question. That especially becomes problematic if we’re talking about drugs that are unhealthy, right? Part of the reason that we ban steroids in sports is because we want to protect players in a kind of paternalistic way … because that can have serious health consequences. But I want you to imagine if there aren’t health consequences. Let’s not talk about methamphetamines; let’s talk about drugs that have very clean safety profiles. Then ask the same question of, if everybody feels pressure because everybody else has improved their health and well-being or their cognitive abilities, what’s wrong with that world? And if what’s wrong with that world is that we feel like we’ve increased the rat race, and made us all feel like we have to be more productive all the time, then what we’re complaining about is the structures and underlying forces in society, not the drugs. Sigal Samuel I think the issue would be, who gets to decide what counts as improvement? I was once having a conversation with some folks in the Bay Area. We were talking about smart drugs and everyone at the table was saying, “If you put a pill in front of me right now that could send up my IQ from, let’s say, 100 to 150, I’d want to take that!” I was an outlier saying, “Actually, I don’t necessarily want to be smarter. Smarter is not necessarily happier or wiser. And I’m also worried about the implicit coercion thing.” Nita Farahany For me, it all comes back to the same question: Do you have a right to self-determination over your own brain? So to your question, “Who gets to decide?” — I think you get to decide. I think you should be the one who decides whether or not you enhance or slow it down, or you don’t do any of those things at all. I’m writing against the grain, right? There is what I think is a very strong paternalistic drive when it comes to health, even in mainstream academia and bioethics, where people are, for the most part, extremely liberal. And I come out differently. I come out believing that giving people autonomy over their brains and mental experiences is critical. Sigal Samuel There is truth to that, but at the same time, I think you’re writing very much with the grain in the sense that the dominant mode of thinking since the Enlightenment is that the individual is the proper seat of autonomy and decision-making. And you’re very much arguing for individual autonomy. I classically think of myself as someone who is very ardently pro that! But I’m also aware that even people like John Stuart Mill, who was really harping on liberty and the individual, were simultaneously acknowledging that we’ve got to have liberty, but only up to the point where it hits upon society’s interests and maybe harms others. So far we’ve mostly been talking about enhancing the brain, but there’s this question about whether cognitive liberty means I should also be allowed to diminish my brain. I right away think of Eternal Sunshine of the Spotless Mind and the ability to erase painful memories. In your book, you talk about this specific neurotech technique, DecNef, that can potentially be used to process traumatic memory. A person sits inside a scanner and recalls a traumatic memory. Machine learning algorithms map the areas of the brain that that activates, and then the person basically erases those memories through a process of neural feedback. So the idea is that neurotech may offer hope for healing traumatic memory, or maybe even prevent it from getting established in the brain to begin with. Nita Farahany Yeah, I write about this because it’s very personal to me. ... I give the example of our second daughter, Callista, who died. And our experience of being in the hospital with her and how traumatic that was and the PTSD that I suffered for years as a result afterwards. And I tried therapy. I tried the drugs [like propranolol, a medication usually prescribed for high blood pressure that was studied — in vain, it turned out — to see if it could prevent PTSD by disrupting memory consolidation]. I have not yet tried DecNef, but I would if I had the opportunity to and was still suffering from PTSD. It works in the same way that, when you are most symptomatic of intractable depression, you have a particular pattern of neurons firing in your brain — and then through implicit reactivation of those same pathways, you could rewire the brain by training it over and over again to have a different outcome. The precision with which you can see the activation patterns and then use that information to rewire it is profound. Related Brain-reading tech is coming. The law is not ready to protect us. Sigal Samuel It was really striking to me that you wrote that you would try DecNef if given the chance. That set me off wondering for myself personally. On the one hand, it sounds amazing, this idea of neurotech healing traumatic memory or even preventing it from getting established in the brain to begin with. On the other hand, I was thinking about how my dad passed away about a year ago. In the last year of his life, I was caring for him and it was really intense. I think probably there was some kind of trauma incurred there. And as a result, the past year has been one of the hardest years of my life. If you’d asked me earlier whether I want to sign up for this thing that will prevent that mental anguish, I might have been tempted. But a year later, having gone through that suffering, I actually think there was a lot of growth that thankfully I was able to come out of it with. More self-compassion and compassion. It reminds me of this concept of post-traumatic growth, where people come out of an experience with new capacities — the flip side of PTSD. And in the book you also write that as a result of your experience, you feel like you came out with more compassion and you’re a stronger ethicist. Nita Farahany Yeah, I don’t think I would’ve used DecNef ex ante. There is something really important about suffering. It has been core to the human condition. It helps us to prevail. So much poetry and music and everything else comes from suffering. I say I would have used it because the trauma echoed for years and I couldn’t sleep, and it was vivid in ways that... I couldn’t function. I would never want to forget Callista or what we went through with Callista. But living through it — from the emotional power of it, to the fear, to the smells, to the echoes of the sounds in my brain — I did not need it at that level. And so if DecNef could help turn it down so that when I remembered it, I could remember as I do now, with fondness ... but not literally relive it — I would, I would do that. I would regain that time to not relive that over and over again. Sigal Samuel Absolutely. That makes a ton of sense. This is something that I was genuinely struggling with while reading, because on the one hand I felt this sense of, I don’t want to cheat myself out of an opportunity for potential post-traumatic growth, but also, I think there really is such a thing as too much suffering. The Buddhist teacher Thich Nhat Hanh has a phrase I really like: “No mud, no lotus.” Meaning, some suffering can be fertile ground for growth. But when he was presented with the question of how much we should suffer, he said, “Not too much!” Because that can just be like a landslide that we don’t know how to pull ourselves out of. Nita Farahany I think that’s right. I hope that people’s choices are to not eliminate experiencing sadness and suffering. I don’t want that. I don’t think that’s good for humanity. I also don’t think it’s up to me to decide for individuals what suffering they do and don’t want to go through. Sigal Samuel Absolutely. And I want to underline that treating PTSD or depression is not the same as eliminating suffering. We should absolutely treat things like PTSD or depression. But I’m really not sure about the quest to eliminate suffering, as some people want to do in the transhumanist movement — the movement that’s all about using tech to usher in a new phase of human evolution. You ask in your book: “If your brain had a switch to turn off suffering, would you use it?” I wouldn’t. Nita Farahany I wouldn’t. But I would turn down the volume for the years that followed [with PTSD], because I didn’t need it at that volume. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via Next Up In Future Perfect Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. The Latest Most of Israel’s weapons imports come from the US. Now Biden is rushing even more arms. By Jonathan Guyer Formula 1 grew too fast. Now its new fans are tuning out. By Izzie Ramirez The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained By A.W. Ohlheiser and Li Zhou Your phone is the key to your digital life. Make sure you know what to do if you lose it. By Sara Morrison Alex Murdaugh stands guilty of killing his wife and son. That’s just scratching the surface. By Aja Romano Is the green texting bubble about to burst? By Sara Morrison Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Facebook is building brain tech that could read minds and ruin privacy - Vox"

"https://www.vox.com/future-perfect/2019/8/5/20750259/facebook-ai-mind-reading-brain-computer-interface"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Neuroscience Facebook is building tech to read your mind. The ethical implications are staggering. Our brains are perhaps the final privacy frontier. By Sigal Samuel Aug 5, 2019, 7:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Facebook is building tech to read your mind. The ethical implications are staggering. Reddit Pocket Flipboard Email Brain-computer interfaces like the mindBEAGLE system shown here can help people with paralysis communicate. Facebook wants to take the technology to the next level. AP This story is part of a group of stories called Finding the best ways to do good. Facebook wants to create a device that can read your mind — literally. It’s funding research on brain-machine interfaces that can pick up thoughts directly from your neurons and translate them into words, the company announced in a blog post last week. The short-term goal is to help patients with paralysis, by decoding their brain signals and allowing them to “speak” their thoughts without ever having to move a muscle. That could be a real public good, significantly improving quality of life for millions of people. In the US alone, 5.4 million people currently live with paralysis. But Facebook’s long-term goal is to reach a much, much wider audience: The aim, it says, is to give all of us the ability to control digital devices — from keyboards to augmented reality glasses — using the power of thought alone. To do that, the company will need access to our brain data. Which, of course, raises some ethical concerns. The Facebook-financed research is taking place at the University of California San Francisco. Scientists there published the results of a study in a recent Nature Communications paper. In a first for the field, they say, they’ve built an algorithm that’s able to decode words from brain activity and translate it into text on a computer screen in real time. The human participants in their study — three volunteers with epilepsy — already had electrodes surgically implanted on the surface of their brains as part of preparation for neurosurgery to treat their seizures. They listened to straightforward questions (like “How is your room currently?”) and spoke their answers out loud. The algorithm, just by reading their brain activity, decoded the answers with accuracy rates as high as 61 percent. That’s pretty impressive, but so far the algorithm can only recognize words from a small vocabulary (like “cold,” “hot,” and “fine”). The scientists are aiming to grow its lexicon over time. Importantly, Facebook also wants to develop a way of decoding speech that doesn’t require surgery. The ideal would be a noninvasive wearable headset, though that’s harder to build. In the meantime, we have a chance to consider the ethical implications of this neurotechnology — and it’s crucial to do that, especially since Facebook isn’t the only one exploring brain-computer interfaces (BCIs). Various scientists , the US military , and companies like Kernel and Paradromics are also working in this space. Elon Musk’s company Neuralink recently revealed that it’s developing flexible “threads” that can be implanted into a brain and could one day allow you to control your smartphone or computer with just your thoughts. Musk said he hopes to start testing in humans by the end of next year. It’s necessary to discuss the ethical implications of these neurotechnologies now, while they’re still in development. They have the potential to interfere with rights that are so basic that you may not even think of them as rights: your mental privacy, say, or your ability to determine where your self ends and a machine begins. Neuroethicists like Marcello Ienca have argued that we may need new legal protections to safeguard these rights from emerging tech. But lawmakers move slowly, and if we wait for devices like Facebook’s or Neuralink’s to hit the market, it might already be too late to enshrine new rights for the neurotechnology age. Brain-computer interfaces’ fast slide from sci-fi to reality If you haven’t heard about BCIs before, it can be hard to believe this is now real life, not something out of a Neal Stephenson or William Gibson novel. But this research really is happening. And over the course of the past dozen years, it’s begun to actually change people’s lives. BCI tech includes systems that “read” neural activity to decode what it’s already saying, often with the help of AI processing software, and systems that “write” to the brain, giving it new inputs to actually change how it’s functioning. Some researchers are interested in developing bidirectional interfaces that both read and write. There are different reasons why you might be interested in developing this tech. On one end of the spectrum are useful, quotidian applications like translating paralyzed people’s thoughts into speech or helping them operate prosthetic limbs. As The Verge explained, early success in the field — which focused not on speech but on movement — dates back to 2006: The first person with spinal cord paralysis to receive a brain implant that allowed him to control a computer cursor was Matthew Nagle. In 2006, Nagle played Pong using only his mind; the basic movement required took him only four days to master, he told The New York Times. Since then, paralyzed people with brain implants have also brought objects into focus and moved robotic arms in labs, as part of scientific research. The system Nagle and others have used is called BrainGate and was developed initially at Brown University. Some futurists have decidedly more fantastical motivations. Musk has said he ultimately aims “to achieve a symbiosis with artificial intelligence.” His goal is to develop a technology that enables humans “merging with AI” so that we won’t be “left behind” as AI systems become more and more advanced. For now, the general invasiveness of BCI — implanting electrodes in or on the brain — drastically limits the commercial potential of this tech. But companies like Facebook are researching noninvasive methods, like a system using near-infrared light that could detect blood-flow changes in the brain while staying outside of it. The ethical risks of brain-reading technology As with many cutting-edge innovations, this one stands to raise ethical quandaries we’ve never even considered before. The scientists involved in the Facebook project acknowledged that they cannot, on their own, foresee or fix all the ethical issues associated with this neurotechnology. “What we can do is recognize when the technology has advanced beyond what people know is possible, and make sure that information is delivered back to the community,” Mark Chevillet, who helms the project, says in the company blog post. “Neuroethical design is one of our program’s key pillars — we want to be transparent about what we’re working on so that people can tell us their concerns about this technology.” In that spirit, here are five concerns about the tech Facebook is helping to develop. 1. Privacy: Let’s start with the obvious. Our brains are perhaps the final privacy frontier. They’re the seat of our personal identity and our most intimate thoughts. If those precious three pounds of goo in our craniums aren’t ours to control, what is? Facebook took care to note that all brain data in the study will stay onsite at the university. And Chevillet told MIT Tech Review, “We take privacy very seriously.” Nevertheless, given that Facebook has been embroiled in a series of privacy scandals — of which Cambridge Analytica is only the most glaring — the public may not take such assurances to heart. “Facebook is already great at peering into your brain without any need for electrodes or fMRI or anything. They know much of your cognitive profile just from how you use the internet,” Roland Nadler, a neuroethicist at the University of British Columbia, told me. “This is why I worry about this research program in the hands of Facebook in particular. It’s being able to couple that dataset with actual in vivo brain data that has the potential for any number of unforeseen consequences.” What if Facebook were to, say, sell our brain data to companies for the purposes of advertising? Advertisers are already working on figuring out how the brain makes purchasing decisions and how to nudge those decisions along. That field, called neuromarketing, is still in its infancy. But Nadler warned that a powerful tech giant like Facebook could catalyze its growth to the point of “influencing purchaser behavior in potentially scary ways.” 2. Algorithmic accountability: One of the major problems with algorithmic decision-making systems is that as they grow in sophistication, they can become black boxes. The specifics of how they arrive at their decisions can get so complex that they’re opaque, even to their creators. If that’s the case with the algorithm used by Facebook’s project, the consequences could be serious. If nobody can explain to you how and why the machine erroneously decoded your thought as X and X turns out to be very bad (“I intend to murder so-and-so”), then the lack of transparency means you will have a hard time demanding redress for the harm that befalls you as a result of this misread thought. “There’s a risk that we come to trust what the machine says as gospel, without wondering if it goes wrong or how we even know if it goes wrong,” Nadler said. “The opacity of the machine is a real worry.” 3. Changing norms: Another big risk is that this neurotechnology might normalize a culture of mind-reading, causing us to give up — so slowly and subtly we almost don’t notice it’s happening — our expectations of mental privacy. One day, our interiority could become a thing of the past, with the technology decoding not just the thoughts we’d like it to transcribe for our own convenience but also the thoughts we want to keep private. That could include everything we keep hidden in our inner sanctum, from sexual fantasies to political dissent. “A lot of my concerns about Facebook accumulating this data are surveillance and civil liberties concerns. You’d worry about the way that Facebook would be helping build a surveillance state,” Nadler said, adding that being able to peer into the brain would be game-changing for law enforcement. If you find it hard to imagine that a project incubated by Facebook could dramatically change norms around surveillance and law enforcement, just think for a minute about facial recognition technology. Facebook rolled out that tech years ago in an innocent context: tagging your friends in photos you posted on the social-media network. But now the tech is used for policing and surveillance, disproportionately harming people of color. And other giants like Apple, Amazon, and Microsoft are all mired in controversy over it. 4. Existential alienation: Rubbing out the distinction between mind and machine also comes with more philosophical risks, like the risk that we might feel alienated from ourselves. The more you meld with a machine, the more you might grow confused about your own agency — where you end and the device begins. A recent article in Nature noted that the predictive nature of some BCI algorithms raises this concern: Such algorithms learn from previous data and guide users towards decisions on the basis of what they have done in the past. But if an algorithm constantly suggests a user’s next word or action, and the user merely approves that option, the authorship of a message or movement will become ambiguous. “At some point,” [neuroethicist Philipp] Kellmeyer says, “you have these very strange situations of shared or hybrid agency.” Part of the decision comes from the user, and part comes from the algorithm of the machine. The article also gives the example of an epileptic woman, identified only as Patient 6, who’d been given a BCI to warn her when one of her seizures was coming on so she could take medication to ward it off. She came not only to rely on the device, but to feel such a radical symbiosis with it that, she said, “It became me.” Then the company that implanted the device in her brain went bankrupt and she was forced to have it removed. She cried, saying, “I lost myself.” On the other side of the spectrum, another epileptic patient who’d had the same device implanted in his brain became depressed because he felt it compromised his autonomy. It “made me feel I had no control,” he said. In either case, the risk of the device was that it fundamentally shifted the patient’s sense of self. A BCI that reads and writes our thoughts could, if it becomes sophisticated enough, do something similar. 5. Oversight: One big risk — so big, in fact, that it could be considered a meta-risk that inflects all the rest — is the lack of existing regulation in this space. It’ll take time for politicians and lawmakers to catch up to the new realities that brain-reading tech makes possible. For now, tech giants can swoop into this legal vacuum with little or no oversight as to how they can gather, store, and monetize our brain data. “Facebook has a track record of playing fast and loose even with already-established regulatory rules,” Nadler said. “And with an entity of their size, it’s difficult to imagine what kind of regulatory oversight would be truly effective. What would an agency action even do? There’s a certain level of impunity that they already operate with because there’s no fine big enough to sting.” After all, when the Federal Trade Commission fined Facebook a record-breaking $5 billion for privacy violations last month, the company didn’t fold. It didn’t even blink. In fact, its stock shot up. Sign up for the Future Perfect newsletter. Twice a week, you’ll get a roundup of ideas and solutions for tackling our biggest challenges: improving public health, decreasing human and animal suffering, easing catastrophic risks, and — to put it simply — getting better at doing good. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via Next Up In Future Perfect Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. The Latest Most of Israel’s weapons imports come from the US. Now Biden is rushing even more arms. By Jonathan Guyer Formula 1 grew too fast. Now its new fans are tuning out. By Izzie Ramirez The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained By A.W. Ohlheiser and Li Zhou Your phone is the key to your digital life. Make sure you know what to do if you lose it. By Sara Morrison Alex Murdaugh stands guilty of killing his wife and son. That’s just scratching the surface. By Aja Romano Is the green texting bubble about to burst? By Sara Morrison Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Elon Musk’s Neuralink plans to merge the brain with AI using implants - Vox"

"https://www.vox.com/future-perfect/2019/7/17/20697812/elon-musk-neuralink-ai-brain-implant-thread-robot"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Neuroscience Elon Musk reveals his plan to link your brain to your smartphone Step one: Drill holes in the skull. Step two: Implant “threads” into the brain. By Sigal Samuel Jul 17, 2019, 3:50pm EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Elon Musk reveals his plan to link your brain to your smartphone Reddit Pocket Flipboard Email Mark Brake/Getty Images This story is part of a group of stories called Finding the best ways to do good. Elon Musk has out-Musked himself with a technological advance that blurs the line between human and machine: flexible “threads” that can be implanted into a brain and could one day allow you to control your smartphone or computer with just your thoughts. Neuralink, one of Musk’s secretive companies, revealed the advance at a San Francisco event Tuesday, giving the public its first real peek at what the startup’s been up to since its launch two years ago. Neuralink has also created a neurosurgical robot reminiscent of a sewing machine, which can embed the threads — each much thinner than a human hair — in the brain. So far, the threads have only been tested in animals, but Musk said he hopes to start testing in humans “by the end of next year,” a timeline that seems unrealistically ambitious. He’ll need to get the green light from the U.S. Food and Drug Administration first, which promises to be a complicated feat: The current procedure for implanting the threads requires drilling holes in the skull. If he succeeds in getting FDA approval, it’ll likely be because he’s pitching the advance as a technology meant to address a medical condition: paralysis. The idea is that the threads will read neuronal signals from a paralyzed patient’s brain and transmit that data to a machine — say, an iPhone — enabling the patient to control it without having to tap or type or swipe. Neuralink’s trials so far have been conducted on rats, and, it seems, monkeys. In a telling moment during the Q&A portion of the event, Musk veered off-script, saying, “A monkey has been able to control the computer with its brain. Just FYI.” (We don’t yet have evidence to that effect.) Neuralink president Max Hodak’s response: “I didn’t realize we were running that result today, but there it goes.” If this technology is functional in human patients — and we should always be careful not to extrapolate too much from early animal studies to humans, particularly when dealing with complex brain systems — it could significantly improve quality of life for millions of people. Approximately 5.4 million people are living with paralysis in the US alone , according to a Reeve Foundation study. As if to underscore Neuralink’s medicinal ambitions, the company’s head surgeon, Matthew MacDougall, spoke onstage dressed in blue scrubs. He emphasized that Neuralink’s main concern is patient safety, adding that eventually the company wants its brain implant procedure to be as non-invasive as Lasik eye surgery. He also said it’s “only intended for patients with serious unmet medical diseases,” like people who’ve been completely paralyzed as the result of a spinal cord injury. But helping people with paralysis is not, it seems, Musk’s end goal — the futurist made clear he has much grander ambitions. Ultimately, he said, he aims “to achieve a symbiosis with artificial intelligence.” The goal is to develop a technology that enables humans “merging with AI” so that we won’t be “left behind” as AI systems become more and more advanced. This fantastical vision is not the sort of thing for which the FDA greenlights human trials. But a study on helping people with paralysis? That may get a warmer reception. Neuralink is arguably one of the foremost startups dedicated to biohacking, the quest to augment human beings’ physical and cognitive performance, often by performing radical experiments on ourselves. It’s now facing a problem common to many biohackers: The medical system, they complain, holds back progress. “If you were to come up with a compound right now that literally cures aging, you couldn’t get it approved,” Oliver Medvedik, a biohacking advocate who directs the Kanbar Center for Biomedical Engineering at Cooper Union, recently told me. “By the definition we’ve set up, aging isn’t a disease, and if you want to get it approved by the FDA you have to target a certain disease. That just seems very strange and antiquated and broken.” Musk said that the event, which was live-streamed , was not about showing off. “The main reason for doing this presentation is recruiting,” he said. He wants more people to apply to Neuralink’s open positions. The company currently has about 90 employees and $158 million in funding, $100 million of which reportedly came from Musk himself. But Hodak described the purpose of the presentation differently in an interview with the New York Times. “We want this burden of stealth mode off of us so that we can keep building and do things like normal people, such as publish papers,” he said. (The company recently released a white paper explaining its new technology.) Neuralink isn’t the first to explore brain-machine interfaces. Other companies like Kernel and Paradromics are also working in this space, as is the US military. Some scientists are currently working on brain implants that would translate paralyzed people’s thoughts into speech. As The Verge explained, early success in the field — which focused not on speech but on movement — dates back to 2006: The first person with spinal cord paralysis to receive a brain implant that allowed him to control a computer cursor was Matthew Nagle. In 2006, Nagle played Pong using only his mind; the basic movement required took him only four days to master, he told The New York Times. Since then, paralyzed people with brain implants have also brought objects into focus and moved robotic arms in labs, as part of scientific research. The system Nagle and others have used is called BrainGate and was developed initially at Brown University. BrainGate relied on the Utah Array , a series of stiff needles that allows for up to 128 electrode channels. Not only is that fewer channels than Neuralink is promising — meaning less data from the brain is being picked up — it’s also stiffer than Neuralink’s threads. That’s a problem for long-term functionality: the brain shifts in the skull but the needles of the array don’t, leading to damage. The thin polymers Neuralink is using may solve that problem. In other words, if Neuralink really has achieved what it says it’s achieved, this could be a major advance with promising applications for people down the road. Just don’t expect those applications too soon: The company still has to prove that its system can work in human brains, and that the threads, once implanted, can survive in our brains for years without deteriorating — or causing our brains themselves to deteriorate. Sign up for the Future Perfect newsletter. Twice a week, you’ll get a roundup of ideas and solutions for tackling our biggest challenges: improving public health, decreasing human and animal suffering, easing catastrophic risks, and — to put it simply — getting better at doing good. Listen to Reset Josiah Zayner is a biohacker who’s famous for injecting himself with the gene-editing tool CRISPR. At a time when the technology exists for us to change (or hack) our own DNA, what are the ethics of experimenting on ourselves, and others, at home? On the launch episode of this new podcast , host Arielle Duhaime-Ross talks to Zayner about how he’s thinking about human experimentation today. Plus: new efforts to come up with a code of conduct for biohackers, from legislation to self-regulation. Subscribe to Reset now on Apple Podcasts , Stitcher , Spotify , or wherever you listen to podcasts. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via Next Up In Future Perfect Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. The Latest Most of Israel’s weapons imports come from the US. Now Biden is rushing even more arms. By Jonathan Guyer Formula 1 grew too fast. Now its new fans are tuning out. By Izzie Ramirez The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained By A.W. Ohlheiser and Li Zhou Your phone is the key to your digital life. Make sure you know what to do if you lose it. By Sara Morrison Alex Murdaugh stands guilty of killing his wife and son. That’s just scratching the surface. By Aja Romano Is the green texting bubble about to burst? By Sara Morrison Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Are brain implants the future of thinking? | Neuroscience | The Guardian"

"https://www.theguardian.com/science/2019/sep/22/brain-computer-interface-implants-neuralink-braingate-elon-musk"

"Brain-computer interface technology is moving fast and Silicon Valley is moving in. Will we all soon be typing with our minds? US edition US edition UK edition Australia edition International edition Europe edition The Guardian - Back to home The Guardian News Opinion Sport Culture Lifestyle Show More Show More document.addEventListener('DOMContentLoaded', function(){ var columnInput = document.getElementById('News-button'); if (!columnInput) return; // Sticky nav replaces the nav so element no longer exists for users in test. columnInput.addEventListener('keydown', function(e){ // keyCode: 13 => Enter key | keyCode: 32 => Space key if (e.keyCode === 13 || e.keyCode === 32) { e.preventDefault() document.getElementById('News-checkbox-input').click(); } }) }) News View all News US news World news Environment US politics Ukraine Soccer Business Tech Science Newsletters Wellness document.addEventListener('DOMContentLoaded', function(){ var columnInput = document.getElementById('Opinion-button'); if (!columnInput) return; // Sticky nav replaces the nav so element no longer exists for users in test. columnInput.addEventListener('keydown', function(e){ // keyCode: 13 => Enter key | keyCode: 32 => Space key if (e.keyCode === 13 || e.keyCode === 32) { e.preventDefault() document.getElementById('Opinion-checkbox-input').click(); } }) }) Opinion View all Opinion The Guardian view Columnists Letters Opinion videos Cartoons document.addEventListener('DOMContentLoaded', function(){ var columnInput = document.getElementById('Sport-button'); if (!columnInput) return; // Sticky nav replaces the nav so element no longer exists for users in test. columnInput.addEventListener('keydown', function(e){ // keyCode: 13 => Enter key | keyCode: 32 => Space key if (e.keyCode === 13 || e.keyCode === 32) { e.preventDefault() document.getElementById('Sport-checkbox-input').click(); } }) }) Sport View all Sport Soccer NFL Tennis MLB MLS NBA NHL F1 Golf document.addEventListener('DOMContentLoaded', function(){ var columnInput = document.getElementById('Culture-button'); if (!columnInput) return; // Sticky nav replaces the nav so element no longer exists for users in test. columnInput.addEventListener('keydown', function(e){ // keyCode: 13 => Enter key | keyCode: 32 => Space key if (e.keyCode === 13 || e.keyCode === 32) { e.preventDefault() document.getElementById('Culture-checkbox-input').click(); } }) }) Culture View all Culture Film Books Music Art & design TV & radio Stage Classical Games document.addEventListener('DOMContentLoaded', function(){ var columnInput = document.getElementById('Lifestyle-button'); if (!columnInput) return; // Sticky nav replaces the nav so element no longer exists for users in test. columnInput.addEventListener('keydown', function(e){ // keyCode: 13 => Enter key | keyCode: 32 => Space key if (e.keyCode === 13 || e.keyCode === 32) { e.preventDefault() document.getElementById('Lifestyle-checkbox-input').click(); } }) }) Lifestyle View all Lifestyle Wellness Fashion Food Recipes Love & sex Home & garden Health & fitness Family Travel Money Search input google-search Search Support us Print subscriptions document.addEventListener('DOMContentLoaded', function(){ var columnInput = document.getElementById('US-edition-button'); if (!columnInput) return; // Sticky nav replaces the nav so element no longer exists for users in test. columnInput.addEventListener('keydown', function(e){ // keyCode: 13 => Enter key | keyCode: 32 => Space key if (e.keyCode === 13 || e.keyCode === 32) { e.preventDefault() document.getElementById('US-edition-checkbox-input').click(); } }) }) US edition UK edition Australia edition International edition Europe edition Search jobs Digital Archive Guardian Puzzles app Guardian Licensing The Guardian app Video Podcasts Pictures Inside the Guardian Guardian Weekly Crosswords Wordiply Corrections Facebook Twitter Search jobs Digital Archive Guardian Puzzles app Guardian Licensing US World Environment US Politics Ukraine Soccer Business Tech Science Newsletters Wellness Illustration by James Melaugh. Illustration by James Melaugh. The Observer Neuroscience Are brain implants the future of thinking? Brain-computer interface technology is moving fast and Silicon Valley is moving in. Will we all soon be typing with our minds? Sun 22 Sep 2019 02.00 EDT A lmost two years ago, Dennis Degray sent an unusual text message to his friend. “You are holding in your hand the very first text message ever sent from the neurons of one mind to the mobile device of another,” he recalls it read. “U just made history.” Degray, 66, has been paralysed from the collarbones down since an unlucky fall over a decade ago. He was able to send the message because in 2016 he had two tiny squares of silicon with protruding metal electrodes surgically implanted in his motor cortex, the part of the brain that controls movement. These record the activity in his neurons for translation into external action. By imagining moving a joystick with his hand, he is able to move a cursor to select letters on a screen. With the power of his mind, he has also bought products on Amazon and moved a robotic arm to stack blocks. Degray has been implanted with these devices, known as Utah arrays, because he is a participant in the BrainGate programme, a long-running multi-institution research effort in the US to develop and test novel neurotechnology aimed at restoring communication, mobility and independence in people whose minds are fine but who have lost bodily connection due to paralysis, limb loss or neurodegenerative disease. But while the Utah array has proved that brain implants are feasible, the technology has a long way to go. Degray had open brain surgery to place his. The system is not wireless – a socket protrudes from his skull through which wires take the signal to computers for decoding by machine-learning algorithms. The tasks that can be done and how well they can be executed are limited because the system only records from a few dozen to a couple of hundred neurons out of an estimated 88bn in the brain (each electrode typically records from between one and four neurons). A BrainGate electrode array with a dime for size comparison. And it is unlikely to last for ever. Scar tissue, the brain’s response to the damage caused by inserting the device, gradually builds up on the electrodes, leading to a progressive decline in signal quality. And when the research sessions – which take place twice a week for Degray in his living facility in Palo Alto, California – come to an end, it will be disconnected and Degray’s telepathic powers cease to be. Barely a couple of dozen people have been implanted with Utah arrays worldwide. Great progress has been made, says Leigh Hochberg , a neurologist at Massachusetts general hospital and an engineering professor at Brown University who co-directs the BrainGate programme, but “a system that patients can use around the clock that reliably provides complete, rapid, intuitive brain control over a computer does not yet exist”. Help may be at hand. An injection of Silicon Valley chutzpah has energised the field of brain-computer or brain-machine interfaces in recent years. Buoyed by BrainGate and other demonstrations, big-name entrepreneurs and companies and scrappy startups are on a quest to develop a new generation of commercial hardware that could ultimately help not only Degray and others with disabilities, but be used by all of us. While some, including Facebook , are pursuing non-invasive versions, wireless neural implant systems are also being worked on. In July Elon Musk, best known as the CEO of the electric car company Tesla, presented details of an implantable wireless system that his company Neuralink is building. It is already being studied in monkeys, Musk revealed, and it is hoped that human trials will start before the end of 2020. To date, Neuralink has received $158m in funding, $100m of it from Musk. While the implant being developed is still the same size as one of the Utah arrays in Degray’s brain, it has far more electrodes, meaning it can record from far more neurons. While a Utah array – of which up to four or five can be inserted – typically has 100 electrodes, Neuralink says its version will have more like 1,000. And the company thinks it is feasible to place up to 10. Very thin threads of flexible biocompatible polymer material studded with electrodes would be “sewn in” by a robot to avoid piercing microvessels, which Neuralink hopes would ameliorate scarring, thereby increasing how long the device lasted. “Our goal is to record from and stimulate spikes in neurons in a way that is orders of magnitude more than anything that has been done to date and safe and good enough that it is not like a major operation,” said Musk in his presentation , adding that the procedure would be more like laser eye surgery than brain surgery. Medical concerns drive the device’s development, according to Musk, but he also worries about the threat posed by artificial intelligence and believes this could provide a way of keeping up with it. There are smaller rival startups too. Paradromics , like Neuralink, is focused on many more and smaller electrodes but is aiming for an even higher density of probes over the face of its neural implant. In form, their device would look closer to the Utah array – a bed of needles with metal electrodes – and there would be no robotic surgery. “We want to hit the market as soon as possible,” says founder and CEO Matt Angle adding the hope is to begin a clinical trial in the early 2020s. The company has raised about $25m in funding to date including significant amounts from the Pentagon’s research agency, Darpa, which grew interested in BCIs after it realised the sophisticated robotic limbs it was building for injured soldiers returning from overseas needed brain control. Dennis Degray uses Utah array implants to manipulate the cursor on a computer screen. Synchron, based in Australia and Silicon Valley, has a different approach. The company, which has received $21m in funding to date, including some from Darpa, last week revealed that the first clinical trial of its Stentrode device had begun in Australia – ahead of both Neuralink and Paradromics. The device avoids open brain surgery and scarring because it is inserted using a stent through a vein in the back of the neck. Once in position next to the motor cortex, the stent splays out to embed 16 metal electrodes into the blood vessel’s walls from which neuronal activity can be recorded. So far in the trial one patient – paralysed with motor neurone disease – has been implanted, with four others set to follow. The device’s safety will be studied along with how well the system allows brain control of a computer for typing and texting. While it can only read the aggregate activity of a population of neurons, of which it will take in about 1,000, there is enough data to make a system useful for patients – and less nuance in the signal actually makes it more stable and robust, says founder and CEO Tom Oxley. Meanwhile, challenges remain for Neuralink and Paradromics. Whether scarring can be mitigated by very small electrodes is yet to be seen. There is also the issue of the electrodes being dissolved and corroded by the body – a problem that gets worse the smaller they are. How long Neuralink’s new polymer probes will last is unknown. “No one is going to be super impressed with the startup companies until they start recording their lifetimes in years. The Utah array has a lot of issues – but you do measure its lifetime in years,” says Cynthia Chestek, a neural interface researcher at the University of Michigan. Then, even if we are able to record all these extra neuron signals, could we decode them? “We have no idea how the brain works,” says Takashi Kozai, a biomedical engineer at the University of Pittsburgh who studies implantable technologies. “Trying to decode that information and actually produce something useful is a huge problem.” Chestek agrees that more understanding of how neurons compute things would be helpful, but “every algorithm out there” would suddenly just start doing better with a few hundred extra neurons. None of the three companies sees nonmedical applications in the short term, but argue that the implant technology could gradually branch out into the general population as people start seeing how transformational it can be. The most obvious application may be brain-controlled typing. Oxley imagines a scenario where people who have grown up texting and typing – and are wholly dependent on their fingers for that – lose functionality as they age. Frustrated that they can’t maintain their speed, they may seek other ways to preserve their technological capability. Eventually a tipping point will occur as people see BCIs working better than the human body. “If the technology becomes safe, it’s easy to use and it provides you with superior technology control, there will be people who will want to pay for that,” says Oxley. Of uses beyond that, no one is being specific. Brain commands to smart speakers? Brain-controlled car driving? Brain-to-brain communication? Enhanced memory and cognition? If the technology were to make it outside the medical domain, the military is where we might see it first, says Dr Hannah Maslen, deputy director of the University of Oxford’s Uehiro Centre for Practical Ethics. For example, it might provide silent communication between soldiers or allow activation of equipment by the thinking of certain commands. It is hard to see most people opting to undergo a surgical intervention for recreational or convenience uses, she adds. But at a recent neurotechnology meetup in San Francisco of about two dozen tinkerers, Jonathan Toomim argued it was a logical next step. “We already use devices – our smart phones – that offload a lot of our cognition and augment our memory. This is just bringing the bandwidth between the human brain and those to a higher level,” said the self-described neuroscientist, engineer, entrepreneur and environmentalist, who makes his own neurofeedback gear. The public should have a clear voice in shaping how neural interface technology is used and regulated over the coming years, concluded a report this month on the topic from the UK Royal Society. One concern is data privacy, though Maslen says this should be tempered by the fact that while BCIs may be portrayed as being able to “mind read” and “decode thoughts” – stoking fears that they will unearth innermost secrets – they are recording from very small areas of the brain mostly related to movement, and require the user’s mental effort to make them work. “Ethical concerns around privacy … don’t apply in such a full way,” she says. A sewing machine-like robot that inserts electrodes into the brain, under development by Neuralink. Nonetheless, questions remain. Who owns the brain data and what is it being used for? And “brainjacking”, where a third party could gain control of the system and modify it in ways the brain’s owner has not consented to, is rooted in reality rather than science fiction says Maslen – pacemakers have been hacked before. Paradromics’ Matt Angle wonders to what extent data from BCIs could be used as evidence in court – for example to incriminate someone in the same way a diary or a computer might. Further ethical issues arise around control and agency. If a brain implant doesn’t get your intention right, to what extent are you as the user of the device responsible for what is “said” or done? And how do we ensure that if a technology confers significant benefits, it is not just the rich who get it? Society still has a few years to ponder these questions. Neuralink’s aim of getting a human clinical trial up and running by the end of next year is widely considered too ambitious, given what remains unproved. But many experts anticipate that the technology will be available for people with impairments or disabilities within five or 10 years. For nonmedical use, the timeframe is greater – perhaps 20 years. For Leigh Hochberg, the focus has to be on helping those who need it most. Says Degray of Neuralink’s device: “I would have one implanted this afternoon if I could.” Is there an alternative to implants? A worn, non-invasive brain computer interface which doesn’t involve brain surgery and can always be taken off may seem attractive. But the skull muffles the reading of neuronal signals. “The physics [of a non-invasive device] are just extremely challenging” says Cynthia Chestek of the University of Michigan. Some companies are trying anyway. Facebook announced in 2017 it wanted to create a wearable device that would allow typing from the brain at 100 words per minute (as a comparison, Neuralink is striving for 40 words per minute – which is around our average typing speed – and the BrainGate programme which uses Utah array implants has achieved about 8 words per minute, without word prediction). This July, researchers at the University of California funded by the social network showed decoding of a small set of full, spoken words and phrases from brain activity in real time for the first time – though it was done with so-called electrocorticography electrodes laid on the surface of the brain via surgery. Meanwhile the company continues to work on how it might achieve the same thing non-invasively and is exploring measuring changing patterns in blood oxygenation – neurons use oxygen when they are active – with near-infrared light. Also on the case is Los Angeles-based startup Kernel , founded by entrepreneur Bryan Johnson who made millions selling mobile payments company Braintree to PayPal. Kernel, into which Johnson has put $100m, started as a neural implants company but then pivoted to wearables because, Johnson says, the invasive road looked so long. Plenty of non-invasive methods exist for sensing and stimulating brain activity (indeed they form the basis of a large consumer neurotechnology industry). But none, says Johnson, is equal to being bridged into a next-generation interface. New ways are needed, and he believes Kernel has found one others have missed. “We will be ready to share more in 2020,” he says. But assuming the technical challenges can be surmounted, social factors could still be a barrier, says Anna Wexler , who studies the ethical, legal and social implications of emerging neurotechnology at the University of Pennsylvania. Google Glass failed not because it didn’t work but because people didn’t want to wear a face computer. Will anyone trust Facebook enough to use their device if it does develop one? Explore more on these topics Neuroscience The Observer Computing Facebook features More on this story More on this story 'Neural revolution': Royal Society calls for inquiry into new wave of brain implants 10 Sept 2019 Neuroscientists decode brain speech signals into written text 30 Jul 2019 Elon Musk unveils plan to build mind-reading implants: 'The monkey is out of the bag' 17 Jul 2019 ‘We will get regular body upgrades’: what will humans look like in 100 years? 22 Sept 2018 … … No death and an enhanced life: Is the future transhuman? 6 May 2018 When man meets metal: rise of the transhumans 29 Oct 2017 … … Transhumanism and cheap laughs: podcasts of the week 5 May 2017 … … The Audio Long Read God in the machine: my strange journey into transhumanism – podcast 28 Apr 2017 God in the machine: my strange journey into transhumanism 18 Apr 2017 Goodbye to Orphan Black, the feminist utopia 2017 needs 10 Aug 2017 … … Most viewed Most viewed US World Environment US Politics Ukraine Soccer Business Tech Science Newsletters Wellness News Opinion Sport Culture Lifestyle About us Help Complaints & corrections SecureDrop Work for us Privacy policy Cookie policy Terms & conditions Contact us All topics All writers Digital newspaper archive Facebook YouTube Instagram LinkedIn Twitter Newsletters Advertise with us Guardian Labs Search jobs Back to top "

"The Pentagon’s Plans to Program Soldiers’ Brains - The Atlantic"

"https://www.theatlantic.com/magazine/archive/2018/11/the-pentagon-wants-to-weaponize-the-brain-what-could-go-wrong/570841"

"Site Navigation The Atlantic Popular Latest Newsletters Sections Politics Ideas Fiction Technology Science Photo Business Culture Planet Global Books Podcasts Health Education Projects Features Family Events Washington Week Progress Newsletters Explore The Atlantic Archive Play The Atlantic crossword The Print Edition Latest Issue Past Issues Give a Gift Search The Atlantic Quick Links Dear Therapist Crossword Puzzle Magazine Archive Your Subscription Popular Latest Newsletters Sign In Subscribe Explore The Tech Issue: The Pentagon aims to weaponize the brain, a generation of kids raised on YouTube, and Alexa’s most dangerous feature. Plus how Newt Gingrich broke politics, Pope Francis and Óscar Romero, the case for liberal Republicanism, Knausgaard devours himself, the personal cost of black success, and more. Alexa, Should We Trust You? Judith Shulevitz The Man Who Broke Politics McKay Coppins What Óscar Romero’s Canonization Says About Pope Francis Paul Elie Raised by YouTube Alexis C. Madrigal The Pentagon’s Push to Program Soldiers’ Brains Michael Joseph Gross How Writing ‘My Struggle’ Undid Knausgaard Ruth Franklin A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. The Pentagon’s Push to Program Soldiers’ Brains The military wants future super-soldiers to control robots with their thoughts. I. Who Could Object? “Tonight I would like to share with you an idea that I am extremely passionate about,” the young man said. His long black hair was swept back like a rock star’s, or a gangster’s. “Think about this,” he continued. “Throughout all human history, the way that we have expressed our intent, the way we have expressed our goals, the way we have expressed our desires, has been limited by our bodies.” When he inhaled, his rib cage expanded and filled out the fabric of his shirt. Gesturing toward his body, he said, “We are born into this world with this. Whatever nature or luck has given us.” His speech then took a turn: “Now, we’ve had a lot of interesting tools over the years, but fundamentally the way that we work with those tools is through our bodies.” Then a further turn: “Here’s a situation that I know all of you know very well—your frustration with your smartphones, right? This is another tool, right? And we are still communicating with these tools through our bodies.” And then it made a leap: “I would claim to you that these tools are not so smart. And maybe one of the reasons why they’re not so smart is because they’re not connected to our brains. Maybe if we could hook those devices into our brains, they could have some idea of what our goals are, what our intent is, and what our frustration is.” So began “ Beyond Bionics ,” a talk by Justin C. Sanchez, then an associate professor of biomedical engineering and neuroscience at the University of Miami, and a faculty member of the Miami Project to Cure Paralysis. He was speaking at a ted x conference in Florida in 2012. What lies beyond bionics? Sanchez described his work as trying to “understand the neural code,” which would involve putting “very fine microwire electrodes”—the diameter of a human hair—“into the brain.” When we do that, he said, we would be able to “listen in to the music of the brain” and “listen in to what somebody’s motor intent might be” and get a glimpse of “your goals and your rewards” and then “start to understand how the brain encodes behavior.” He explained, “With all of this knowledge, what we’re trying to do is build new medical devices, new implantable chips for the body that can be encoded or programmed with all of these different aspects. Now, you may be wondering, what are we going to do with those chips? Well, the first recipients of these kinds of technologies will be the paralyzed. It would make me so happy by the end of my career if I could help get somebody out of their wheelchair.” Sanchez went on, “The people that we are trying to help should never be imprisoned by their bodies. And today we can design technologies that can help liberate them from that. I’m truly inspired by that. It drives me every day when I wake up and get out of bed. Thank you so much.” He blew a kiss to the audience. A year later, Justin Sanchez went to work for the Defense Advanced Research Projects Agency, the Pentagon’s R&D department. At DARPA , he now oversees all research on the healing and enhancement of the human mind and body. And his ambition involves more than helping get disabled people out of their wheelchair—much more. DARPA has dreamed for decades of merging human beings and machines. Some years ago, when the prospect of mind-controlled weapons became a public-relations liability for the agency, officials resorted to characteristic ingenuity. They recast the stated purpose of their neurotechnology research to focus ostensibly on the narrow goal of healing injury and curing illness. The work wasn’t about weaponry or warfare, agency officials claimed. It was about therapy and health care. Who could object? But even if this claim were true, such changes would have extensive ethical, social, and metaphysical implications. Within decades, neurotechnology could cause social disruption on a scale that would make smartphones and the internet look like gentle ripples on the pond of history. Most unsettling, neurotechnology confounds age-old answers to this question: What is a human being? II. High Risk, High Reward In his 1958 State of the Union address, President Dwight Eisenhower declared that the United States of America “must be forward-looking in our research and development to anticipate the unimagined weapons of the future.” A few weeks later, his administration created the Advanced Research Projects Agency, a bureaucratically independent body that reported to the secretary of defense. This move had been prompted by the Soviet launch of the Sputnik satellite. The agency’s original remit was to hasten America’s entry into space. During the next few years, arpa ’s mission grew to encompass research into “man-computer symbiosis” and a classified program of experiments in mind control that was code-named Project Pandora. There were bizarre efforts that involved trying to move objects at a distance by means of thought alone. In 1972, with an increment of candor, the word Defense was added to the name, and the agency became DARPA. Pursuing its mission, DARPA funded researchers who helped invent technologies that changed the nature of battle (stealth aircraft, drones) and shaped daily life for billions (voice-recognition technology, GPS devices). Its best-known creation is the internet. The agency’s penchant for what it calls “high-risk, high-reward” research ensured that it would also fund a cavalcade of folly. Project Seesaw, a quintessential Cold War boondoggle, envisioned a “particle-beam weapon” that could be deployed in the event of a Soviet attack. The idea was to set off a series of nuclear explosions beneath the Great Lakes, creating a giant underground chamber. Then the lakes would be drained, in a period of 15 minutes, to generate the electricity needed to set off a particle beam. The beam would accelerate through tunnels hundreds of miles long (also carved out by underground nuclear explosions) in order to muster enough force to shoot up into the atmosphere and knock incoming Soviet missiles out of the sky. During the Vietnam War, DARPA tried to build a Cybernetic Anthropomorphous Machine, a jungle vehicle that officials called a “mechanical elephant.” The diverse and sometimes even opposing goals of DARPA scientists and their Defense Department overlords merged into a murky, symbiotic research culture—“unencumbered by the typical bureaucratic oversight and uninhibited by the restraints of scientific peer review,” Sharon Weinberger wrote in a recent book, The Imagineers of War. In Weinberger’s account, DARPA ’s institutional history involves many episodes of introducing a new technology in the context of one appealing application, while hiding other genuine but more troubling motives. At DARPA , the left hand knows, and doesn’t know, what the right hand is doing. The agency is deceptively compact. A mere 220 employees, supported by about 1,000 contractors, report for work each day at DARPA ’s headquarters, a nondescript glass-and-steel building in Arlington, Virginia, across the street from the practice rink for the Washington Capitals. About 100 of these employees are program managers—scientists and engineers, part of whose job is to oversee about 2,000 outsourcing arrangements with corporations, universities, and government labs. The effective workforce of DARPA actually runs into the range of tens of thousands. The budget is officially said to be about $3 billion, and has stood at roughly that level for an implausibly long time—the past 14 years. The Biological Technologies Office, created in 2014, is the newest of DARPA ’s six main divisions. This is the office headed by Justin Sanchez. One purpose of the office is to “restore and maintain warfighter abilities” by various means, including many that emphasize neurotechnology—applying engineering principles to the biology of the nervous system. For instance, the Restoring Active Memory program develops neuroprosthetics—tiny electronic components implanted in brain tissue—that aim to alter memory formation so as to counteract traumatic brain injury. Does DARPA also run secret biological programs? In the past, the Department of Defense has done such things. It has conducted tests on human subjects that were questionable, unethical, or, many have argued, illegal. The Big Boy protocol, for example, compared radiation exposure of sailors who worked above and below deck on a battleship, never informing the sailors that they were part of an experiment. Last year I asked Sanchez directly whether any of DARPA ’s neurotechnology work, specifically, was classified. He broke eye contact and said, “I can’t—We’ll have to get off that topic, because I can’t answer one way or another.” When I framed the question personally—“Are you involved with any classified neuroscience project?”—he looked me in the eye and said, “I’m not doing any classified work on the neurotechnology end.” If his speech is careful, it is not spare. Sanchez has appeared at public events with some frequency (videos are posted on DARPA ’s YouTube channel ), to articulate joyful streams of good news about DARPA ’s proven applications—for instance, brain-controlled prosthetic arms for soldiers who have lost limbs. Occasionally he also mentions some of his more distant aspirations. One of them is the ability, via computer, to transfer knowledge and thoughts from one person’s mind to another’s. III. “We Try to Find Ways to Say Yes” Medicine and biology were of minor interest to DARPA until the 1990s, when biological weapons became a threat to U.S. national security. The agency made a significant investment in biology in 1997, when DARPA created the Controlled Biological Systems program. The zoologist Alan S. Rudolph managed this sprawling effort to integrate the built world with the natural world. As he explained it to me, the aim was “to increase, if you will, the baud rate, or the cross-communication, between living and nonliving systems.” He spent his days working through questions such as “Could we unlock the signals in the brain associated with movement in order to allow you to control something outside your body, like a prosthetic leg or an arm, a robot, a smart home—or to send the signal to somebody else and have them receive it?” Human enhancement became an agency priority. “Soldiers having no physical, physiological, or cognitive limitation will be key to survival and operational dominance in the future,” predicted Michael Goldblatt, who had been the science and technology officer at McDonald’s before joining DARPA in 1999. To enlarge humanity’s capacity to “control evolution,” he assembled a portfolio of programs with names that sounded like they’d been taken from video games or sci-fi movies: Metabolic Dominance, Persistence in Combat, Continuous Assisted Performance, Augmented Cognition, Peak Soldier Performance, Brain-Machine Interface. The programs of this era, as described by Annie Jacobsen in her 2015 book, The Pentagon’s Brain , often shaded into mad-scientist territory. The Continuous Assisted Performance project attempted to create a “24/7 soldier” who could go without sleep for up to a week. (“My measure of success,” one DARPA official said of these programs, “is that the International Olympic Committee bans everything we do.”) Dick Cheney relished this kind of research. In the summer of 2001, an array of “super-soldier” programs was presented to the vice president. His enthusiasm contributed to the latitude that President George W. Bush’s administration gave DARPA —at a time when the agency’s foundation was shifting. Academic science gave way to tech-industry “innovation.” Tony Tether, who had spent his career working alternately for Big Tech, defense contractors, and the Pentagon, became DARPA ’s director. After the 9/11 attacks, the agency announced plans for a surveillance program called Total Information Awareness, whose logo included an all-seeing eye emitting rays of light that scanned the globe. The pushback was intense, and Congress took DARPA to task for Orwellian overreach. The head of the program—Admiral John Poindexter, who had been tainted by scandal back in the Reagan years—later resigned, in 2003. The controversy also drew unwanted attention to DARPA ’s research on super-soldiers and the melding of mind and machine. That research made people nervous, and Alan Rudolph, too, found himself on the way out. In this time of crisis, DARPA invited Geoff Ling, a neurology‑ICU physician and, at the time, an active-duty Army officer, to join the Defense Sciences Office. (Ling went on to work in the Biological Technologies Office when it spun out from Defense Sciences, in 2014.) When Ling was interviewed for his first job at DARPA , in 2002, he was preparing for deployment to Afghanistan and thinking about very specific combat needs. One was a “pharmacy on demand” that would eliminate the bulk of powdery fillers from drugs in pill or capsule form and instead would formulate active ingredients for ingestion via a lighter, more compact, dissolving substance—like Listerine breath strips. This eventually became a DARPA program. The agency’s brazen sense of possibility buoyed Ling, who recalls with pleasure how colleagues told him, “We try to find ways to say yes, not ways to say no.” With Rudolph gone, Ling picked up the torch. Ling talks fast. He has a tough-guy voice. The faster he talks, the tougher he sounds, and when I met him, his voice hit top speed as he described a first principle of Defense Sciences. He said he had learned this “particularly” from Alan Rudolph: “Your brain tells your hands what to do. Your hands basically are its tools, okay? And that was a revelation to me.” He continued, “We are tool users—that’s what humans are. A human wants to fly, he builds an airplane and flies. A human wants to have recorded history, and he creates a pen. Everything we do is because we use tools, right? And the ultimate tools are our hands and feet. Our hands allow us to work with the environment to do stuff, and our feet take us where our brain wants to go. The brain is the most important thing.” Ling connected this idea of the brain’s primacy with his own clinical experience of the battlefield. He asked himself, “How can I liberate mankind from the limitations of the body?” The program for which Ling became best known is called Revolutionizing Prosthetics. Since the Civil War, as Ling has said, the prosthetic arm given to most amputees has been barely more sophisticated than “a hook,” and not without risks: “Try taking care of your morning ablutions with that bad boy, and you’re going to need a proctologist every goddamn day.” With help from DARPA colleagues and academic and corporate researchers, Ling and his team built something that was once all but unimaginable: a brain-controlled prosthetic arm. No invention since the internet has been such a reliable source of good publicity for DARPA. Milestones in its development were hailed with wonder. In 2012, 60 Minutes showed a paralyzed woman named Jan Scheuermann feeding herself a bar of chocolate using a robotic arm that she manipulated by means of a brain implant. Yet DARPA ’s work to repair damaged bodies was merely a marker on a road to somewhere else. The agency has always had a larger mission, and in a 2015 presentation, one program manager—a Silicon Valley recruit—described that mission: to “free the mind from the limitations of even healthy bodies.” What the agency learns from healing makes way for enhancement. The mission is to make human beings something other than what we are, with powers beyond the ones we’re born with and beyond the ones we can organically attain. The internal workings of DARPA are complicated. The goals and values of its research shift and evolve in the manner of a strange, half-conscious shell game. The line between healing and enhancement blurs. And no one should lose sight of the fact that D is the first letter in DARPA ’s name. A year and a half after the video of Jan Scheuermann feeding herself chocolate was shown on television, DARPA made another video of her, in which her brain-computer interface was connected to an F-35 flight simulator , and she was flying the airplane. DARPA later disclosed this at a conference called Future of War. Geoff Ling’s efforts have been carried on by Justin Sanchez. In 2016, Sanchez appeared at DARPA ’s “Demo Day” with a man named Johnny Matheny, whom agency officials describe as the first “osseointegrated” upper-limb amputee—the first man with a prosthetic arm attached directly to bone. Matheny demonstrated what was, at the time, DARPA ’s most advanced prosthetic arm. He told the attendees, “I can sit here and curl a 45-pound dumbbell all day long, till the battery runs dead.” The next day, Gizmodo ran this headline above its report from the event: “ DARPA ’s Mind-Controlled Arm Will Make You Wish You Were a Cyborg. ” Since then, DARPA ’s work in neurotechnology has avowedly widened in scope, to embrace “the broader aspects of life,” Sanchez told me, “beyond the person in the hospital who is using it to heal.” The logical progression of all this research is the creation of human beings who are ever more perfect, by certain technological standards. New and improved soldiers are necessary and desirable for DARPA, but they are just the window-display version of the life that lies ahead. IV. “Over the Horizon” Consider memory, Sanchez told me: “Everybody thinks about what it would be like to give memory a boost by 20, 30, 40 percent—pick your favorite number—and how that would be transformative.” He spoke of memory enhancement through neural interface as an alternative form of education. “School in its most fundamental form is a technology that we have developed as a society to help our brains to do more,” he said. “In a different way, neurotechnology uses other tools and techniques to help our brains be the best that they can be.” One technique was described in a 2013 paper, a study involving researchers at Wake Forest University, the University of Southern California, and the University of Kentucky. Researchers performed surgery on 11 rats. Into each rat’s brain, an electronic array—featuring 16 stainless-steel wires—was implanted. After the rats recovered from surgery, they were separated into two groups, and they spent a period of weeks getting educated, though one group was educated more than the other. The less educated group learned a simple task, involving how to procure a droplet of water. The more educated group learned a complex version of that same task—to procure the water, these rats had to persistently poke levers with their nose despite confounding delays in the delivery of the water droplet. When the more educated group of rats attained mastery of this task, the researchers exported the neural-firing patterns recorded in the rats’ brains—the memory of how to perform the complex task—to a computer. “What we did then was we took those signals and we gave it to an animal that was stupid,” Geoff Ling said at a DARPA event in 2015—meaning that researchers took the neural-firing patterns encoding the memory of how to perform the more complex task, recorded from the brains of the more educated rats, and transferred those patterns into the brains of the less educated rats—“and that stupid animal got it. They were able to execute that full thing.” Ling summarized: “For this rat, we reduced the learning period from eight weeks down to seconds.” “They could inject memory using the precise neural codes for certain skills,” Sanchez told me. He believes that the Wake Forest experiment amounts to a foundational step toward “memory prosthesis.” This is the stuff of The Matrix. Though many researchers question the findings—cautioning that, really, it can’t be this simple—Sanchez is confident: “If I know the neural codes in one individual, could I give that neural code to another person? I think you could.” Under Sanchez, DARPA has funded human experiments at Wake Forest, the University of Southern California, and the University of Pennsylvania, using similar mechanisms in analogous parts of the brain. These experiments did not transfer memory from one person to another, but instead gave individuals a memory “boost.” Implanted electrodes recorded neuronal activity associated with recognizing patterns (at Wake Forest and USC) and memorizing word lists (at Penn) in certain brain circuits. Then electrodes fed back those recordings of neuronal activity into the same circuits as a form of reinforcement. The result, in both cases, was significantly improved memory recall. Doug Weber, a neural engineer at the University of Pittsburgh who recently finished a four-year term as a DARPA program manager, working with Sanchez, is a memory-transfer skeptic. Born in Wisconsin, he has the demeanor of a sitcom dad: not too polished, not too rumpled. “I don’t believe in the infinite limits of technology evolution,” he told me. “I do believe there are going to be some technical challenges which are impossible to achieve.” For instance, when scientists put electrodes in the brain, those devices eventually fail—after a few months or a few years. The most intractable problem is blood leakage. When foreign material is put into the brain, Weber said, “you undergo this process of wounding, bleeding, healing, wounding, bleeding, healing, and whenever blood leaks into the brain compartment, the activity in the cells goes way down, so they become sick, essentially.” More effectively than any fortress, the brain rejects invasion. Even if the interface problems that limit us now didn’t exist, Weber went on to say, he still would not believe that neuroscientists could enable the memory-prosthesis scenario. Some people like to think about the brain as if it were a computer, Weber explained, “where information goes from A to B to C, like everything is very modular. And certainly there is clear modular organization in the brain. But it’s not nearly as sharp as it is in a computer. All information is everywhere all the time, right? It’s so widely distributed that achieving that level of integration with the brain is far out of reach right now.” Peripheral nerves, by contrast, conduct signals in a more modular fashion. The biggest, longest peripheral nerve is the vagus. It connects the brain with the heart, the lungs, the digestive tract, and more. Neuroscientists understand the brain’s relationship with the vagus nerve more clearly than they understand the intricacies of memory formation and recall among neurons within the brain. Weber believes that it may be possible to stimulate the vagus nerve in ways that enhance the process of learning—not by transferring experiential memories, but by sharpening the facility for certain skills. To test this hypothesis, Weber directed the creation of a new program in the Biological Technologies Office, called Targeted Neuroplasticity Training (TNT). Teams of researchers at seven universities are investigating whether vagal-nerve stimulation can enhance learning in three areas: marksmanship, surveillance and reconnaissance, and language. The team at Arizona State has an ethicist on staff whose job, according to Weber, “is to be looking over the horizon to anticipate potential challenges and conflicts that may arise” regarding the ethical dimensions of the program’s technology, “before we let the genie out of the bottle.” At a TNT kickoff meeting, the research teams spent 90 minutes discussing the ethical questions involved in their work—the start of a fraught conversation that will broaden to include many others, and last for a very long time. DARPA officials refer to the potential consequences of neurotechnology by invoking the acronym elsi , a term of art devised for the Human Genome Project. It stands for “ethical, legal, social implications.” The man who led the discussion on ethics among the research teams was Steven Hyman, a neuroscientist and neuroethicist at MIT and Harvard’s Broad Institute. Hyman is also a former head of the National Institute of Mental Health. When I spoke with him about his work on DARPA programs, he noted that one issue needing attention is “cross talk.” A man-machine interface that does not just “read” someone’s brain but also “writes into” someone’s brain would almost certainly create “cross talk between those circuits which we are targeting and the circuits which are engaged in what we might call social and moral emotions,” he said. It is impossible to predict the effects of such cross talk on “the conduct of war” (the example he gave), much less, of course, on ordinary life. Weber and a DARPA spokesperson related some of the questions the researchers asked in their ethics discussion: Who will decide how this technology gets used? Would a superior be able to force subordinates to use it? Will genetic tests be able to determine how responsive someone would be to targeted neuroplasticity training? Would such tests be voluntary or mandatory? Could the results of such tests lead to discrimination in school admissions or employment? What if the technology affects moral or emotional cognition—our ability to tell right from wrong or to control our own behavior? Recalling the ethics discussion, Weber told me, “The main thing I remember is that we ran out of time.” V. “You Can Weaponize Anything” In The Pentagon’s Brain , Annie Jacobsen suggested that DARPA ’s neurotechnology research, including upper-limb prosthetics and the brain-machine interface, is not what it seems: “It is likely that DARPA ’s primary goal in advancing prosthetics is to give robots, not men, better arms and hands.” Geoff Ling rejected the gist of her conclusion when I summarized it for him (he hadn’t read the book). He told me, “When we talk about stuff like this, and people are looking for nefarious things, I always say to them, ‘Do you honestly believe that the military that your grandfather served in, your uncle served in, has changed into being Nazis or the Russian army?’ Everything we did in the Revolutionizing Prosthetics program—everything we did—is published. If we were really building an autonomous-weapons system, why would we publish it in the open literature for our adversaries to read? We hid nothing. We hid not a thing. And you know what? That meant that we didn’t just do it for America. We did it for the world.” I started to say that publishing this research would not prevent its being misused. But the terms use and misuse overlook a bigger issue at the core of any meaningful neurotechnology-ethics discussion. Will an enhanced human being—a human being possessing a neural interface with a computer—still be human, as people have experienced humanity through all of time? Or will such a person be a different sort of creature? The U.S. government has put limits on DARPA ’s power to experiment with enhancing human capabilities. Ling says colleagues told him of a “directive”: “Congress was very specific,” he said. “They don’t want us to build a superperson.” This can’t be the announced goal , Congress seems to be saying, but if we get there by accident—well, that’s another story. Ling’s imagination remains at large. He told me, “If I gave you a third eye, and the eye can see in the ultraviolet, that would be incorporated into everything that you do. If I gave you a third ear that could hear at a very high frequency, like a bat or like a snake, then you would incorporate all those senses into your experience and you would use that to your advantage. If you can see at night, you’re better than the person who can’t see at night.” Enhancing the senses to gain superior advantage—this language suggests weaponry. Such capacities could certainly have military applications, Ling acknowledged—“You can weaponize anything, right?”—before he dismissed the idea and returned to the party line: “No, actually, this has to do with increasing a human’s capability” in a way that he compared to military training and civilian education, and justified in economic terms. “Let’s say I gave you a third arm,” and then a fourth arm—so, two additional hands, he said. “You would be more capable; you would do more things, right?” And if you could control four hands as seamlessly as you’re controlling your current two hands, he continued, “you would actually be doing double the amount of work that you would normally do. It’s as simple as that. You’re increasing your productivity to do whatever you want to do.” I started to picture his vision—working with four arms, four hands—and asked, “Where does it end?” “It won’t ever end,” Ling said. “I mean, it will constantly get better and better—” His cellphone rang. He took the call, then resumed where he had left off: “What DARPA does is we provide a fundamental tool so that other people can take those tools and do great things with them that we’re not even thinking about.” Judging by what he said next, however, the number of things that DARPA is thinking about far exceeds what it typically talks about in public. “If a brain can control a robot that looks like a hand,” Ling said, “why can’t it control a robot that looks like a snake? Why can’t that brain control a robot that looks like a big mass of Jell-O, able to get around corners and up and down and through things? I mean, somebody will find an application for that. They couldn’t do it now, because they can’t become that glob, right? But in my world, with their brain now having a direct interface with that glob, that glob is the embodiment of them. So now they’re basically the glob, and they can go do everything a glob can do.” VI. Gold Rush DARPA ’s developing capabilities still hover at or near a proof-of-concept stage. But that’s close enough to have drawn investment from some of the world’s richest corporations. In 1990, during the administration of President George H. W. Bush, DARPA Director Craig I. Fields lost his job because, according to contemporary news accounts, he intentionally fostered business development with some Silicon Valley companies, and White House officials deemed that inappropriate. Since the administration of the second President Bush, however, such sensitivities have faded. Over time, DARPA has become something of a farm team for Silicon Valley. Regina Dugan, who was appointed DARPA director by President Barack Obama, went on to head Google’s Advanced Technology and Projects group, and other former DARPA officials went to work for her there. She then led R&D for the analogous group at Facebook, called Building 8. (She has since left Facebook.) DARPA ’s neurotechnology research has been affected in recent years by corporate poaching. Doug Weber told me that some DARPA researchers have been “scooped up” by companies including Verily, the life-sciences division of Alphabet (the parent company of Google), which, in partnership with the British pharmaceutical conglomerate GlaxoSmithKline, created a company called Galvani Bioelectronics, to bring neuro-modulation devices to market. Galvani calls its business “bioelectric medicine,” which conveys an aura of warmth and trustworthiness. Ted Berger, a University of Southern California biomedical engineer who collaborated with the Wake Forest researchers on their studies of memory transfer in rats, worked as the chief science officer at the neurotechnology company Kernel, which plans to build “advanced neural interfaces to treat disease and dysfunction, illuminate the mechanisms of intelligence, and extend cognition.” Elon Musk has courted DARPA researchers to join his company Neuralink, which is said to be developing an interface known as “neural lace.” Facebook’s Building 8 is working on a neural interface too. In 2017, Regina Dugan said that 60 engineers were at work on a system with the goal of allowing users to type 100 words a minute “directly from your brain.” Geoff Ling is on Building 8’s advisory board. Talking with Justin Sanchez, I speculated that if he realizes his ambitions, he could change daily life in even more fundamental and lasting ways than Facebook’s Mark Zuckerberg and Twitter’s Jack Dorsey have. Sanchez blushes easily, and he breaks eye contact when he is uncomfortable, but he did not look away when he heard his name mentioned in such company. Remembering a remark that he had once made about his hope for neurotechnology’s wide adoption, but with “appropriate checks to make sure that it’s done in the right way,” I asked him to talk about what the right way might look like. Did any member of Congress strike him as having good ideas about legal or regulatory structures that might shape an emerging neural-interface industry? He demurred (“ DARPA ’s mission isn’t to define or even direct those things”) and suggested that, in reality, market forces would do more to shape the evolution of neurotechnology than laws or regulations or deliberate policy choices. What will happen, he said, is that scientists at universities will sell their discoveries or create start-ups. The marketplace will take it from there: “As they develop their companies, and as they develop their products, they’re going to be subject to convincing people that whatever they’re developing makes sense, that it helps people to be a better version of themselves. And that process—that day-to-day development—will ultimately guide where these technologies go. I mean, I think that’s the frank reality of how it ultimately will unfold.” He seemed entirely untroubled by what may be the most troubling aspect of DARPA ’s work: not that it discovers what it discovers, but that the world has, so far, always been ready to buy it. This article appears in the November 2018 print edition with the headline “The Pentagon Wants to Weaponize the Brain. What Could Go Wrong?” "

"What is biohacking? The new “science” of optimizing your brain and body. - Vox"

"https://www.vox.com/future-perfect/2019/6/25/18682583/biohacking-transhumanism-human-augmentation-genetic-engineering-crispr"

"We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × iStockphoto/Getty Images Filed under: Future Perfect How biohackers are trying to upgrade their brains, their bodies — and human nature 9 questions about biohacking you were too embarrassed to ask. By Sigal Samuel Updated Nov 15, 2019, 12:10pm EST If you buy something from a Vox link, Vox Media may earn a commission. See our ethics statement. Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: How biohackers are trying to upgrade their brains, their bodies — and human nature Reddit Pocket Flipboard Email This story is part of a group of stories called Finding the best ways to do good. Even if you haven’t heard the term “biohacking” before, you’ve probably encountered some version of it. Maybe you’ve seen Twitter CEO Jack Dorsey extolling the benefits of fasting intermittently and drinking “salt juice” each morning. Maybe you’ve read about former NASA employee Josiah Zayner injecting himself with DNA using the gene-editing technology CRISPR. Maybe you’ve heard of Bay Area folks engaging in “dopamine fasting.” Maybe you, like me, have a colleague who’s had a chip implanted in their hand. These are all types of biohacking, a broad term for a lifestyle that’s growing increasingly popular, and not just in Silicon Valley , where it really took off. Biohacking — also known as DIY biology — is an extremely broad and amorphous term that can cover a huge range of activities, from performing science experiments on yeast or other organisms to tracking your own sleep and diet to changing your own biology by pumping a younger person’s blood into your veins in the hope that it’ll fight aging. (Yes, that is a real thing, and it’s called a young blood transfusion. More on that later.) The type of biohackers currently gaining the most notoriety are the ones who experiment — outside of traditional lab spaces and institutions — on their own bodies with the hope of boosting their physical and cognitive performance. They form one branch of transhumanism , a movement that holds that human beings can and should use technology to augment and evolve our species. Some biohackers have science PhDs; others are complete amateurs. And their ways of trying to “hack” biology are as diverse as they are. It can be tricky to understand the different types of hacks, what differentiates them from traditional medicine, and how safe — or legal — they are. As biohacking starts to appear more often in headlines — and, recently, in a fascinating Netflix series called Unnatural Selection — it’s worth getting clear on some of the fundamentals. Here are nine questions that can help you make sense of biohacking. 1) First of all, what exactly is biohacking? What are some common examples of it? Depending on whom you ask, you’ll get a different definition of biohacking. Since it can encompass a dizzying range of pursuits, I’m mostly going to look at biohacking defined as the attempt to manipulate your brain and body in order to optimize performance, outside the realm of traditional medicine. But later on, I’ll also give an overview of some other types of biohacking (including some that can lead to pretty unbelievable art). Dave Asprey, a biohacker who created the supplement company Bulletproof, told me that for him, biohacking is “the art and science of changing the environment around you and inside you so that you have full control over your own biology.” He’s very game to experiment on his body: He has stem cells injected into his joints, takes dozens of supplements daily, bathes in infrared light, and much more. It’s all part of his quest to live until at least age 180. One word Asprey likes to use a lot is “control,” and that kind of language is typical of many biohackers, who often talk about “optimizing” and “upgrading” their minds and bodies. Some of their techniques for achieving that are things people have been doing for centuries, like Vipassana meditation and intermittent fasting. Both of those are part of Dorsey’s routine, which he detailed in a podcast interview. He tries to do two hours of meditation a day and eats only one meal (dinner) on weekdays; on weekends, he doesn’t eat at all. (Critics worry that his dietary habits sound a bit like an eating disorder, or that they might unintentionally influence others to develop a disorder.) He also kicks off each morning with an ice bath before walking the 5 miles to Twitter HQ. Supplements are another popular tool in the biohacker’s arsenal. There’s a whole host of pills people take, from anti-aging supplements to nootropics or “smart drugs.” Since biohackers are often interested in quantifying every aspect of themselves, they may buy wearable devices to, say, track their sleep patterns. (For that purpose, Dorsey swears by the Oura Ring. ) The more data you have on your body’s mechanical functions, the more you can optimize the machine that is you — or so the thinking goes. Then there are some of the more radical practices: cryotherapy (purposely making yourself cold), neurofeedback (training yourself to regulate your brain waves), near-infrared saunas (they supposedly help you escape stress from electromagnetic transmissions), and virtual float tanks (which are meant to induce a meditative state through sensory deprivation), among others. Some people spend hundreds of thousands of dollars on these treatments. A subset of biohackers called grinders go so far as to implant devices like computer chips in their bodies. The implants allow them to do everything from opening doors without a fob to monitoring their glucose levels subcutaneously. For some grinders, like Zoltan Istvan , who ran for president as head of the Transhumanist Party, having an implant is fun and convenient: “I’ve grown to relish and rely on the technology,” he recently wrote in the New York Times. “The electric lock on the front door of my house has a chip scanner, and it’s nice to go surfing and jogging without having to carry keys around.” Istvan also noted that “for some people without functioning arms, chips in their feet are the simplest way to open doors or operate some household items modified with chip readers.” Other grinders are deeply curious about blurring the line between human and machine, and they get a thrill out of seeing all the ways we can augment our flesh-and-blood bodies using tech. Implants, for them, are a starter experiment. 2) Why are people doing this? What drives someone to biohack themselves? On a really basic level, biohacking comes down to something we can all relate to: the desire to feel better — and to see just how far we can push the human body. That desire comes in a range of flavors, though. Some people just want to not be sick anymore. Others want to become as smart and strong as they possibly can. An even more ambitious crowd wants to be as smart and strong as possible for as long as possible — in other words, they want to radically extend their life span. These goals have a way of escalating. Once you’ve determined (or think you’ve determined) that there are concrete “hacks” you can use by yourself right now to go from sick to healthy, or healthy to enhanced, you start to think: Well, why stop there? Why not shoot for peak performance? Why not try to live forever? What starts as a simple wish to be free from pain can snowball into self-improvement on steroids. That was the case for Asprey. Now in his 40s, he got into biohacking because he was unwell. Before hitting age 30, he was diagnosed with high risk of stroke and heart attack, suffered from cognitive dysfunction, and weighed 300 pounds. “I just wanted to control my own biology because I was tired of being in pain and having mood swings,” he told me. Now that he feels healthier, he wants to slow the normal aging process and optimize every part of his biology. “I don’t want to be just healthy; that’s average. I want to perform; that’s daring to be above average. Instead of ‘How do I achieve health?’ it’s ‘How do I kick more ass?’” Zayner, the biohacker who once injected himself with CRISPR DNA, has also had health problems for years, and some of his biohacking pursuits have been explicit attempts to cure himself. But he’s also motivated in large part by frustration. Like some other biohackers with an anti-establishment streak, he’s irritated by federal officials’ purported sluggishness in greenlighting all sorts of medical treatments. In the US, it can take 10 years for a new drug to be developed and approved; for people with serious health conditions, that wait time can feel cruelly long. Zayner claims that’s part of why he wants to democratize science and empower people to experiment on themselves. (However, he admits that some of his stunts have been purposely provocative and that “I do ridiculous stuff also. I’m sure my motives are not 100 percent pure all the time.”) An illustration of a brain hemisphere with chips embedded. Getty Images/iStockphoto The biohacking community also offers just that: community. It gives people a chance to explore unconventional ideas in a non-hierarchical setting, and to refashion the feeling of being outside the norm into a cool identity. Biohackers congregate in dedicated online networks, in Slack and WhatsApp groups — WeFast , for example, is for intermittent fasters. In person, they run experiments and take classes at “hacklabs,” improvised laboratories that are open to the public, and attend any one of the dozens of biohacking conferences put on each year. 3) How different is biohacking from traditional medicine? What makes something “count” as a biohacking pursuit? Certain kinds of biohacking go far beyond traditional medicine, while other kinds bleed into it. Plenty of age-old techniques — meditation, fasting — can be considered a basic type of biohacking. So can going to a spin class or taking antidepressants. What differentiates biohacking is arguably not that it’s a different genre of activity but that the activities are undertaken with a particular mindset. The underlying philosophy is that we don’t need to accept our bodies’ shortcomings — we can engineer our way past them using a range of high- and low-tech solutions. And we don’t necessarily need to wait for a double-blind, randomized, placebo-controlled trial, traditional medicine’s gold standard. We can start to transform our lives right now. As millionaire Serge Faguet, who plans to live forever, put it : “People here [in Silicon Valley] have a technical mindset, so they think of everything as an engineering problem. A lot of people who are not of a technical mindset assume that, ‘Hey, people have always been dying,’ but I think there’s going to be a greater level of awareness [of biohacking] once results start to happen.” Rob Carlson, an expert on synthetic biology who’s been advocating for biohacking since the early 2000s, told me that to his mind, “all of modern medicine is hacking,” but that people often call certain folks “hackers” as a way of delegitimizing them. “It’s a way of categorizing the other — like, ‘Those biohackers over there do that weird thing.’ This is actually a bigger societal question: Who’s qualified to do anything? And why do you not permit some people to explore new things and talk about that in public spheres?” If it’s taken to extremes, the “Who’s qualified to do anything?” mindset can delegitimize scientific expertise in a way that can endanger public health. Luckily, biohackers don’t generally seem interested in dethroning expertise to that dangerous degree; many just don’t think they should be locked out of scientific discovery because they lack conventional credentials like a PhD. 4) So how much of this is backed by scientific research? Some biohacks are backed by strong scientific evidence and are likely to be beneficial. Often, these are the ones that are tried and true, debugged over centuries of experimentation. For example, clinical trials have shown that mindfulness meditation can help reduce anxiety and chronic pain. But other hacks, based on weak or incomplete evidence, could be either ineffective or actually harmful. After Dorsey endorsed a particular near-infrared sauna sold by SaunaSpace, which claims its product boosts cellular regeneration and fights aging by detoxing your body, the company experienced a surge in demand. But according to the New York Times , “though a study of middle-aged and older Finnish men indicates that their health benefited from saunas, there have been no major studies conducted of” this type of sauna, which directs incandescent light at your body. So is buying this expensive product likely to improve your health? We can’t say that yet. Similarly, the intermittent fasting that Dorsey endorses may yield health benefits for some, but scientists still have plenty of questions about it. Although there’s a lot of research on the long-term health outcomes of fasting in animals — and much of it is promising — the research literature on humans is much thinner. Fasting has gone mainstream, but because it’s done so ahead of the science , it falls into the “proceed with caution” category. Critics have noted that for those who’ve struggled with eating disorders, it could be dangerous. And while we’re on the topic of biohacking nutrition: My colleague Julia Belluz has previously reported on the Bulletproof Diet promoted by Asprey, who she says “vilifies healthy foods and suggests part of the way to achieve a ‘pound a day’ weight loss is to buy his expensive, ‘science-based’ Bulletproof products.” She was not convinced by the citations for his claims: What I found was a patchwork of cherry-picked research and bad studies or articles that aren’t relevant to humans. He selectively reported on studies that backed up his arguments, and ignored the science that contradicted them. Many of the studies weren’t done in humans but in rats and mice. Early studies on animals, especially on something as complex as nutrition, should never be extrapolated to humans. Asprey glorifies coconut oil and demonizes olive oil, ignoring the wealth of randomized trials (the highest quality of evidence) that have demonstrated olive oil is beneficial for health. Some of the research he cites was done on very specific sub-populations, such as diabetics , or on very small groups of people. These findings wouldn’t be generalizable to the rest of us. 5) This all sounds like it can be taken to extremes. What are the most dangerous types of biohacking being tried? Some of the highest-risk hacks are being undertaken by people who feel desperate. On some level, that’s very understandable. If you’re sick and in constant pain, or if you’re old and scared to die, and traditional medicine has nothing that works to quell your suffering, who can fault you for seeking a solution elsewhere? Yet some of the solutions being tried these days are so dangerous, they’re just not worth the risk. If you’ve watched HBO’s Silicon Valley , then you’re already familiar with young blood transfusions. As a refresher, that’s when an older person pays for a young person’s blood and has it pumped into their veins in the hope that it’ll fight aging. This putative treatment sounds vampiric, yet it’s gained popularity in the Silicon Valley area, where people have actually paid $8,000 a pop to participate in trials. The billionaire tech investor Peter Thiel has expressed keen interest. As Chavie Lieber noted for Vox, although some limited studies suggest that these transfusions might fend off diseases like Alzheimer’s, Parkinson’s, heart disease, and multiple sclerosis, these claims haven’t been proven. In February, the Food and Drug Administration released a statement warning consumers away from the transfusions: “Simply put, we’re concerned that some patients are being preyed upon by unscrupulous actors touting treatments of plasma from young donors as cures and remedies. Such treatments have no proven clinical benefits for the uses for which these clinics are advertising them and are potentially harmful.” Another biohack that definitely falls in the “don’t try this at home” category: fecal transplants, or transferring stool from a healthy donor into the gastrointestinal tract of an unhealthy recipient. In 2016, sick of suffering from severe stomach pain, Zayner decided to give himself a fecal transplant in a hotel room. He had procured a friend’s poop and planned to inoculate himself using the microbes in it. Ever the public stuntman, he invited a journalist to document the procedure. Afterward, he claimed the experiment left him feeling better. But fecal transplants are still experimental and not approved by the FDA. The FDA recently reported that two people had contracted serious infections from fecal transplants that contained drug-resistant bacteria. One of the people died. And this was in the context of a clinical trial — presumably, a DIY attempt could be even riskier. The FDA is putting a stop to clinical trials on the transplants for now. Zayner also popularized the notion that you can edit your own DNA with CRISPR. In 2017, he injected himself with CRISPR DNA at a biotech conference, live-streaming the experiment. He later said he regretted that stunt because it could lead others to copy him and “people are going to get hurt.” Yet when asked whether his company, the Odin, which he runs out of his garage in Oakland, California, was going to stop selling CRISPR kits to the general public, he said no. Ellen Jorgensen, a molecular biologist who co-founded Genspace and Biotech Without Borders , two Brooklyn-based biology labs open to the public, finds antics like Zayner’s worrisome. A self-identified biohacker, she told me people shouldn’t buy Zayner’s kits, not just because they don’t work half the time (she’s a professional and even she couldn’t get it to work), but because CRISPR is such a new technology that scientists aren’t yet sure of all the risks involved in using it. By tinkering with your genome, you could unintentionally cause a mutation that increases your risk of developing cancer, she said. It’s a dangerous practice that should not be marketed as a DIY activity. “At Genspace and Biotech Without Borders, we always get the most heartbreaking emails from parents of children afflicted with genetic diseases,” Jorgensen says. “They have watched these Josiah Zayner videos and they want to come into our class and cure their kids. We have to tell them, ‘This is a fantasy.’ ... That is incredibly painful.” She thinks such biohacking stunts give biohackers like her a bad name. “It’s bad for the DIY bio community,” she said, “because it makes people feel that as a general rule we’re irresponsible.” 6) Are all these biohacking pursuits legal? Existing regulations weren’t built to make sense of something like biohacking, which in some cases stretches the very limits of what it means to be a human being. That means that a lot of biohacking pursuits exist in a legal gray zone: frowned upon by bodies like the FDA, but not yet outright illegal, or not enforced as such. As biohackers traverse uncharted territory, regulators are scrambling to catch up with them. After the FDA released its statement in February urging people to stay away from young blood transfusions, the San Francisco-based startup Ambrosia , which was well known for offering the transfusions, said on its website that it had “ceased patient treatments.” The site now says, “We are currently in discussion with the FDA on the topic of young plasma.” This wasn’t the FDA’s first foray into biohacking. In 2016, the agency objected to Zayner selling kits to brew glow-in-the-dark beer. And after he injected himself with CRISPR, the FDA released a notice saying the sale of DIY gene-editing kits for use on humans is illegal. Zayner disregarded the warning and continued to sell his wares. In 2019, he was, for a time, under investigation by California’s Department of Consumer Affairs, accused of practicing medicine without a license. The biohackers I spoke to said restrictive regulation would be a counterproductive response to biohacking because it’ll just drive the practice underground. They say it’s better to encourage a culture of transparency so that people can ask questions about how to do something safely, without fear of reprisal. According to Jorgensen, most biohackers are safety-conscious, not the sorts of people interested in engineering a pandemic. They’ve even generated and adopted their own codes of ethics. She herself has had a working relationship with law enforcement since the early 2000s. “At the beginning of the DIY bio movement, we did an awful lot of work with Homeland Security,” she said. “And as far back as 2009, the FBI was reaching out to the DIY community to try to build bridges.” Carlson told me he’s noticed two general shifts over the past 20 years. “One was after 2001, after the anthrax attacks, when Washington, DC, lost their damn minds and just went into a reactive mode and tried to shut everything down,” he said. “As of 2004 or 2005, the FBI was arresting people for doing biology in their homes.” Then in 2009, the National Security Council dramatically changed perspectives. It published the National Strategy for Countering Biological Threats , which embraced “innovation and open access to the insights and materials needed to advance individual initiatives,” including in “private laboratories in basements and garages.” Now, though, some agencies seem to think they ought to take action. But even if there were clear regulations governing all biohacking activities, there would be no straightforward way to stop people from pursuing them behind closed doors. “This technology is available and implementable anywhere, there’s no physical means to control access to it, so what would regulating that mean?” Carlson said. 7) One of the more ambitious types of biohacking is life extension, the attempt to live longer or even cheat death entirely. What are the physical limits of life extension? Some biohackers believe that by leveraging technology, they’ll be able to live longer but stay younger. Gerontologist Aubrey de Grey claims people will be able to live to age 1,000. In fact, he says the first person who will live to 1,000 has already been born. De Grey focuses on developing strategies for repairing seven types of cellular and molecular damage associated with aging — or, as he calls them, “Strategies for Engineered Negligible Senescence.” His nonprofit, the Methuselah Foundation, has attracted huge investments, including more than $6 million from Thiel. Its aim is to “make 90 the new 50 by 2030.” Wondering whether de Grey’s goals are realistic, I reached out to Genspace co-founder Oliver Medvedik, who earned his PhD at Harvard Medical School and now directs the Kanbar Center for Biomedical Engineering at Cooper Union. “Living to 1,000? It’s definitely within our realm of possibility if we as a society that doles out money [to fund research we deem worthy] decide we want to do it,” he told me. He’s optimistic, he said, because the scientific community is finally converging on a consensus about what the root causes of aging are ( damage to mitochondria and epigenetic changes are a couple of examples). And in the past five years, he’s seen an explosion of promising papers on possible ways to address those causes. Researchers who want to fight aging generally adopt two different approaches. The first is the “small molecule” approach, which often focuses on dietary supplements. Medvedik calls that the “low-hanging fruit.” He spoke excitedly about the possibility of creating a supplement from a plant compound called fisetin, noting that a recent (small) Mayo Clinic trial suggests high concentrations of fisetin can clear out senescent cells in humans — cells that have stopped dividing and that contribute to aging. The other approach is more dramatic: genetic engineering. Scientists taking this tack in mouse studies usually tinker with a genome in embryo, meaning that new mice are born with the fix already in place. Medvedik pointed out that’s not very useful for treating humans — we want to be able to treat people who have already been born and have begun to age. But he sees promise here too. He cited a new study that used CRISPR to target Hutchinson-Gilford progeria syndrome, a genetic disorder that manifests as accelerated aging, in a mouse model. “It wasn’t a total cure — they extended the life span of these mice by maybe 30 percent — but what I was very interested in is the fact that it was delivered into mice that had already been born.” He’s also intrigued by potential non-pharmaceutical treatments for aging-related diseases like Alzheimer’s — for example, the use of light stimulation to influence brain waves — but those probably won’t help us out anytime soon, for a simple reason: “It’s not a drug. You can’t package and sell it,” he said. “Pharma can’t monetize it.” Like many in the biohacking community, Medvedik sounded a note of frustration about how the medical system holds back anti-aging progress. “If you were to come up with a compound right now that literally cures aging, you couldn’t get it approved,” he said. “By the definition we’ve set up, aging isn’t a disease, and if you want to get it approved by the FDA you have to target a certain disease. That just seems very strange and antiquated and broken.” 8) Biohackers also include people who engage in DIY science without experimenting on themselves. What’s that form of biohacking like? Not everyone who’s interested in biohacking is interested in self-experimentation. Some come to it because they care about bringing science to the masses, alleviating the climate crisis, or making art that shakes us out of our comfort zones. “My version of biohacking is unexpected people in unexpected places doing biotechnology,” Jorgensen told me. For her, the emphasis is on democratizing cutting-edge science while keeping it safe. The community labs she’s helped to build, Genspace and Biotech Without Borders, offer classes on using CRISPR technology to edit a genome — but participants work on the genome of yeast, never on their own bodies. Some people in the community are altruistically motivated. They want to use biohacking to save the environment by figuring out a way to make a recyclable plastic or a biofuel. They might experiment on organisms in makeshift labs in their garages. Or they might take a Genspace class on how to make furniture out of fungi or paper out of kombucha. Experimental artists have also taken an interest in biohacking. For them, biology is just another palette. The artists Oron Catts and Ionat Zurr from the University of Western Australia were actually the first people to create and serve up lab-grown meat. They took some starter cells from a frog and used them to grow small “steaks” of frog meat, which they fed to gallery-goers in France at a 2003 art installation called “Disembodied Cuisine.” Artist Heather Dewey-Hagborg used DNA samples she received from Chelsea Manning to recreate various possible physiognomies of Manning’s face. The 3D-printed masks formed an art installation called “Probably Chelsea.” Boris Roessler/Picture Alliance via Getty Images More recently, Alexandra Daisy Ginsberg has used old floral DNA to recreate the smell of flowers driven to extinction by humans , enabling us to catch a whiff of them once more. And this summer, a London museum is displaying something rather less fragrant: cheese made from celebrities. Yes, you read that right: The cheese was created with bacteria harvested from the armpits, toes, bellybuttons, and nostrils of famous people. If you’re thoroughly grossed out by this, don’t worry: The food won’t actually be eaten — this “bioart” project is meant more as a thought experiment than as dinner. 9) At its most extreme, biohacking can fundamentally alter human nature. Should we be worried? When you hear about people genetically engineering themselves or trying young blood transfusions in an effort to ward off death, it’s easy to feel a sense of vertigo about what we’re coming to as a species. But the fact is we’ve been altering human nature since the very beginning. Inventing agriculture, for example, helped us transform ourselves from nomadic hunter-gatherers into sedentary civilizations. And whether we think of it this way or not, we’re all already doing some kind of biohacking every day. The deeper I delve into biohacking, the more I think a lot of the discomfort with it boils down to simple neophobia — a fear of what’s new. (Not all of the discomfort, mind you: The more extreme hacks really are dangerous.) As one of my colleagues put it to me, 40 years ago, “test tube babies” seemed unnatural, a freak-show curiosity; now in vitro fertilization has achieved mainstream acceptance. Will biohacking undergo the same progression? Or is it really altering human nature in a more fundamental way, a way that should concern us? When I asked Carlson, he refused to buy the premise of the question. “If you assert that hackers are changing what it means to be human, then we need to first have an agreement about what it means to be human,” he said. “And I’m not going to buy into the idea that there is one thing that is being human. Across the sweep of history, it’s odd to say humans are static — it’s not the case that humans in 1500 were the same as they are today.” That’s true. Nowadays, we live longer. We’re taller. We’re more mobile. And we marry and have kids with people who come from different continents, different cultures — a profound departure from old customs that has nothing to do with genetic engineering but that’s nonetheless resulting in genetic change. Still, biohackers are talking about making such significant changes that the risks they carry are significant too. What if biohackers’ “upgrades” don’t get distributed evenly across the human population? What if, for example, the cure for aging becomes available, but only to the rich? Will that lead to an even wider life expectancy gap, where rich people live longer and poor people die younger? Medvedik dismissed that concern, arguing that a lot of interventions that could lengthen our lives, like supplements, wouldn’t be expensive to produce. “There’s no reason why that stuff can’t be dirt-cheap. But that depends on what we do as a society,” he said. Insulin doesn’t cost much to produce, but as a society we’ve allowed companies to jack up the price so high that many people with diabetes are now skipping lifesaving doses. That’s horrifying, but it’s not a function of the technology itself. Here’s another risk associated with biohacking, one I think is even more serious: By making ourselves smarter and stronger and potentially even immortal (a difference of kind, not just of degree), we may create a society in which everyone feels pressure to alter their biology — even if they don’t want to. To refuse a hack would mean to be at a huge professional disadvantage, or to face moral condemnation for remaining suboptimal when optimization is possible. In a world of superhumans, it may become increasingly hard to stay “merely” human. “The flip side of all this is the ‘perfect race’ or eugenics specter,” Jorgensen acknowledged. “This is a powerful set of technologies that can be used in different ways. We’d better think about it and use it wisely.” Sign up for the Future Perfect newsletter. Twice a week, you’ll get a roundup of ideas and solutions for tackling our biggest challenges: improving public health, decreasing human and animal suffering, easing catastrophic risks, and — to put it simply — getting better at doing good. Listen to Reset Josiah Zayner is a biohacker who’s famous for injecting himself with the gene-editing tool CRISPR. At a time when the technology exists for us to change (or hack) our own DNA, what are the ethics of experimenting on ourselves, and others, at home? On the launch episode of this new podcast , host Arielle Duhaime-Ross talks to Zayner about how he’s thinking about human experimentation today. Plus: new efforts to come up with a code of conduct for biohackers, from legislation to self-regulation. Subscribe to Reset now on Apple Podcasts , Stitcher , Spotify , or wherever you listen to podcasts. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via Future Perfect The US is normalizing the cruelest mass killing method to stop bird flu Future Perfect One stat that could spur a compromise on the child tax credit Even Better It’s time to break up with fast fashion Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Weighing AI risks versus the danger of virus research - Vox"

"https://www.vox.com/future-perfect/23671304/artificial-intelligence-biotechnology-covid-pandemics-existential-risks-gain-of-function"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence Why we’re scared of AI and not scared enough of bio risks What we choose to panic about has less to do with the facts and more to do with chance. By Kelsey Piper Apr 6, 2023, 6:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Why we’re scared of AI and not scared enough of bio risks Reddit Pocket Flipboard Email An employee of the State Office for Fair Trading (LAVES) at work in a laboratory in which avian flu samples are being tested, in Oldenburg, Germany, on November 29, 2016. Carmen Jaspersen/picture alliance via Getty Image This story is part of a group of stories called Finding the best ways to do good. When does America underreact, and when does it overreact? After 3,000 people were killed on 9/11, the US invaded two countries, leading to multitrillion-dollar occupations that cost the lives of hundreds of thousands of people , including American and allied soldiers and civilians in Iraq and Afghanistan. The US made permanent, economically costly, seriously inconvenient changes to how air travel works to prevent it from ever happening again. More than 1 million Americans died of Covid-19 , and while in the early months of the pandemic the country made massive, life-altering, changes to reduce its spread, it has done very close to absolutely nothing to make sure it never happens again. (Maybe this is because of the massive, life-altering changes in the early months of the pandemic; they became unpopular enough that warnings we should avoid having another pandemic often get a hostile response.) More directly, the US is still conducting research into making deadlier and more contagious diseases, even while there’s legitimate concern that work like that may have even caused Covid. And despite the enormous human and economic toll of the coronavirus, Congress has done little to fund the preparedness work that could blunt the effects of the next pandemic. Taking AI seriously I’ve been thinking about all this as AI and the possibility that sufficiently powerful systems will kill us all suddenly emerged onto center stage. An open letter signed by major figures in machine learning research, as well as by leading tech figures like Elon Musk, called for a six-month pause on building models more powerful than OpenAI’s new GPT-4. In Time magazine, AI safety absolutist Eliezer Yudkowsky argued the letter didn’t go far enough and that we need a lasting, enforced international moratorium that treats AI as more dangerous than nuclear weapons. In a fairly stunning CBS interview last month, Geoff Hinton, a highly respected senior AI researcher, was asked by a disbelieving interviewer, “What do you think the chances are of AI just wiping out humanity?” Hinton, whose pioneering work on deep learning helped make large language models like ChatGPT possible, replied, “It’s not inconceivable.” On March 30, Fox News correspondent Peter Doocy read a line from Yudkowsky’s Time piece to White House press secretary Karine Jean-Pierre: “‘Literally everyone on Earth will die.’ Would you agree that does not sound good?’” To nervous laughter, Jean-Pierre assured everyone that the White House has a blueprint for safe AI development. Don’t forget biology I’ve argued for years that sufficiently powerful AI systems might end civilization as we know it. In a sense, it’s gratifying to see that position given the mainstream hearing and open discussion that I think it deserves. But it’s also mystifying. Research that seeks to make pathogens more powerful might also end civilization as we know it ! Yet our response to that possibility has largely been a big collective shrug. There are people heroically working to make US regulations surrounding this research clearer and better , but they’re largely doing so in the background, without the public outcry and scrutiny that one might expect a question with these stakes to inspire. And while slowing down AI development is going to be difficult, controversial, and complicated given the sheer number of companies working on it and the potential size of the market, there are only a few labs doing dangerous gain-of-function research on pathogens of pandemic potential. That should make shutting that work down much easier — or at least, you’d think so. Playing dice with existential risks Ultimately — and this isn’t very satisfying at all my sense is that these fairly momentous changes in our trajectory and priorities often depend on random chance. If by coincidence someone had happened to discover the 9/11 hijackers in time to stop them, the world we live in today would look radically different. If by coincidence different people had been in key administration roles when Covid-19 started, we’d know a lot more about its origins and conceivably be a lot more willing to demand better lab safety policy. And as for where the movement to slow down AI goes from here, a lot of that feels to me like it’s also up to chance. Which messages snatch public attention? Are there notable safety scares, and do they clarify the picture of what we’re up against or make it muddier? I’d love to live in a world where how we respond to existential risk wasn’t up to chance or what happens to catch the public’s and the media’s attention, one where risks to the security of our whole world received sober scrutiny regardless of whether they happened to make the headlines. In practice, though, we seem to be lucky if world-altering dangerous research — whether on AI or biology — gets any public scrutiny at all. A version of this story was initially published in the Future Perfect newsletter. Sign up here to subscribe! Will you support Vox’s explanatory journalism? Millions rely on Vox’s journalism to understand the coronavirus crisis. We believe it pays off for all of us, as a society and a democracy, when our neighbors and fellow citizens can access clear, concise information on the pandemic. But our distinctive explanatory journalism is expensive. Support from our readers helps us keep it free for everyone. If you have already made a financial contribution to Vox, thank you. If not, please consider making a contribution today from as little as $3. One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via Next Up In Future Perfect Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. The Latest Most of Israel’s weapons imports come from the US. Now Biden is rushing even more arms. By Jonathan Guyer Formula 1 grew too fast. Now its new fans are tuning out. By Izzie Ramirez The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained By A.W. Ohlheiser and Li Zhou Your phone is the key to your digital life. Make sure you know what to do if you lose it. By Sara Morrison Alex Murdaugh stands guilty of killing his wife and son. That’s just scratching the surface. By Aja Romano Is the green texting bubble about to burst? By Sara Morrison Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"A game about AI making paperclips is the most addictive you’ll play today - The Verge"

"https://www.theverge.com/tldr/2017/10/11/16457742/ai-paperclips-thought-experiment-game-frank-lantz"

"The Verge homepage The Verge homepage The Verge The Verge logo. / Tech / Reviews / Science / Entertainment / More Menu Expand Menu Tech / Artificial Intelligence / Culture A game about AI making paperclips is the most addictive you’ll play today A game about AI making paperclips is the most addictive you’ll play today By James Vincent , a senior reporter who has covered AI, robotics, and more for eight years at The Verge. | Share this story There’s a well-known thought experiment in the world of artificial intelligence that poses a simple, but potentially very scary, question: what if we asked a super-intelligent AI to make paperclips? This may not sound terrifying at first, but as Oxford philosopher Nick Bostrom (who first described the parable ) explains, it all depends on how well we’ve trained the AI. If we’ve given it common sense, it might ask us: “How many paperclips do you want ?” If it doesn’t know to ask, it might just make paperclips forever. And, if it’s a super-intelligent AI that we’ve accidentally forgotten to program with any human ethics or values, it might decide that the most efficient way to make paperclips is to wipe out humanity and terraform the planet into one giant paperclip-making factory. Sound fun? Well good, because now there’s a game about it. Designed by Frank Lantz, director of the New York University Game Center, Paperclips might not be the sort of title you’d expect about a rampaging AI. It’s free to play, it lives in your browser, and all you have to look at is numbers. (Though trust me, you’ll learn to love them.) It’s an idle clicker game — one that draws on humanity’s apparently bottomless desire to click buttons and watch numbers go up. Think Cookie Clicker or Egg Inc , but dedicated to paperclips. You’ll start off making them the old fashioned way: one clip for one click. But pretty soon you’ll be purchasing autoclippers to do the work for you while you turn your attentions to running an algorithmic hedge fund, then building a quantum computer, and then (much later) exploring the known Universe in search of new matter to turn into more and more paperclips. How to play is pretty self-explanatory, but here are some tips if you’re getting stuck: Paperclips is essentially a game about balance and efficiency. You have to leave the game alone for long stretches of time, yes, but you also need to be sure you’re not wasting resources while you do so. Keep an eye on your supply chain to make sure there are no bottlenecks, and be on the lookout for any unused capacity that can be turned to your ultimate goal: making those sweet, sweet clips. Play at least until you get hypnodrones. When you unlock these, the game really opens up onto a new level. You thought you were making paperclips before? Hoo buddy, you ain’t seen nothing yet. At some point you will run into a wall that you can’t optimize your way past. You may think you’ve got to the end of the game (for example, when you’ve turned all available matter in the Universe into paperclips — a logical endpoint, sure) but there’s more to do. Unfortunately, getting past these barriers often requires patience, and sometimes you’ll have to leave the game for hours to get onto the next level. Don’t start playing if you’ve got anything important to do today. Or tomorrow. All in all, the game made me think that if the paperclip maximizer doomsday scenario does ever come to pass, it will, at least, be pleasingly ironic. We go to the trouble of creating super-intelligence and it responds by cauterizing the Universe in the name of office supplies. There have been worse metaphors for the human condition. Plus, if we teach the AI to enjoy making paperclips (and some say these sorts of human-analogous incentives will be necessary to create true thinking machines) then at least it’ll be having a fun time. Like you, it’ll have fun watching those numbers getting bigger. Sam Altman fired as CEO of OpenAI OpenAI board in discussions with Sam Altman to return as CEO Windows is now an app for iPhones, iPads, Macs, and PCs Screens are good, actually What happened to Sam Altman? Verge Deals / Sign up for Verge Deals to get deals on products we've tested sent to your inbox daily. From our sponsor Advertiser Content From More from TL;DR When was the last time you thought about paying in cash? For this startup, Nvidia GPUs are currency Let’s all play the Phone Challenge Summer of spam Advertiser Content From Terms of Use Privacy Notice Cookie Policy Do Not Sell Or Share My Personal Info Licensing FAQ Accessibility Platform Status How We Rate and Review Products Contact Tip Us Community Guidelines About Ethics Statement The Verge is a vox media network Advertise with us Jobs @ Vox Media © 2023 Vox Media , LLC. All Rights Reserved "

"A Viral Game About Paperclips Teaches You to Be a World-Killing AI | WIRED"

"https://www.wired.com/story/the-way-the-world-ends-not-with-a-bang-but-a-paperclip"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Adam Rogers Science The Way the World Ends: Not with a Bang But a Paperclip Getty Images Save this story Save Save this story Save Application Games Human-computer interaction End User Consumer Sector Research Games Paperclips, a new game from designer Frank Lantz , starts simply. The top left of the screen gets a bit of text, probably in Times New Roman, and a couple of clickable buttons: Make a paperclip. You click, and a counter turns over. One. The game ends—big, significant spoiler here—with the destruction of the universe. In between, Lantz, the director of the New York University Games Center, manages to incept the player with a new appreciation for the narrative potential of addictive clicker games, exponential growth curves, and artificial intelligence run amok. “I started it as an exercise in teaching myself Javascript. And then it just took over my brain,” Lantz says. “I thought, in a game like this, where the whole point is that you’re in pursuit of maximizing a particular arbitrary quantity, it would be so funny if you were an AI and making paperclips. That game would design itself, I thought.” Lantz figured it would take him a weekend to build. It took him nine months. And then it went viral. The idea of a paperclip-making AI didn’t originate with Lantz. Most people ascribe it to Nick Bostrom , a philosopher at Oxford University and the author of the book Superintelligence. The New Yorker (owned by Condé Nast, which also owns Wired ) called Bostrom “the philosopher of doomsday,” because he writes and thinks deeply about what would happen if a computer got really, really smart. Not, like, “wow, Alexa can understand me when I ask it to play NPR” smart, but like really smart. In 2003, Bostrom wrote that the idea of a superintelligent AI serving humanity or a single person was perfectly reasonable. But, he added, “It also seems perfectly possible to have a superintelligence whose sole goal is something completely arbitrary, such as to manufacture as many paperclips as possible, and who would resist with all its might any attempt to alter this goal.” The result? “It starts transforming first all of earth and then increasing portions of space into paperclip manufacturing facilities.” Bostrom declined to comment, but his assistant did send this email back when I pinged him: “Oh, this is regarding the paper clipping game,” she wrote. “He has looked at the game but due to the overwhelming number of requests, he hasn't been sharing quotes on it.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg One of Bostrom’s fellow doomsayers did agree to explain the origin of paperclips as the End of All Things. “It sounds like something I would say, but it also sounds like something Nick Bostrom would say,” says Eliezer Yudkowsky , a senior research fellow at the Machine Intelligence Research Institute. Probably, he says, the idea originated years ago on a mailing list for singularity cassandras, which sounds like the world’s most terrifying listserv. “The idea isn’t that a paperclip factory is likely to have the most advanced research AI in the world. The idea is to express the orthogonality thesis, which is that you can have arbitrarily great intelligence hooked up to any goal,” Yudkowsky says. So that’s good, right? A paperclip maximizer! Maximize a goal! That’s what an AI’s creators want, right? “As it improves, they lose control of what goal it is carrying out,” Yudkowsky says. “The utility function changes from whatever they originally had in mind. The weird, random thing that best fulfills this utility function is little molecular shapes that happen to look like paperclips.” So … bad, because as the AI dedicates more and more intelligence and resources to making paperclips against all other possible outcomes … well, maybe at first it does stuff that looks helpful to humanity, but in the end, it’s just going to turn us into paperclips. And then all the matter on Earth. And then everything else. Everything. Is. Paperclips. “It’s not that the AI is doing something you can’t understand,” Yudkowsky says. “You have a genuine disagreement on values.” OK, OK, that doesn’t make the game sound fun. But I promise it is. See, Lantz is an ace at taking a denigrated game genre—the “clicker” or “incremental”—and making it more than it is. You’ve seen these, maybe even played them. Remember Farmville? A clicker. In fact, for a while they were so ubiquitous and popular that the game theorist and writer Ian Bogost invented a kind of parody of their pointlessness called Cow Clicker , which, as my colleague Jason Tanz wrote about so elegantly in 2011, itself became wildly, unironically popular. Bogost and Lantz are friends, of course. “When I first looked at Cow Clicker , I thought, that’s actually kind of interesting, and here’s how you would make it more interesting and more fun,” Lantz says. “And Ian was like, ‘no, that’s the point, Frank.’” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But Lantz knew clickers could be fun. To him, clickers are to big-budget, perfectly rendered, massively hyped AAA games as punk was to prog rock. Clickers can be sort of passive, more about immersing in the underlying dynamics of a system than mashing buttons. They have rhythms. “What they all have in common is a radical simplicity, a minimalism in an age where video games are often sort of over-the-top, baroque confections of overwhelming multimedia immersion,” Lantz says. “I really like that clicker games are considered garbage. That appeals to me.” For inspiration, Lantz turned to games like Kittens , a seemingly simple exercise in building villages full of kittens that spirals outward into an exploration of how societies are structured. (“I think stuff like this forges some deep, subtle bond that makes people play it for months and even years,” says the designer of Kittens , a software engineer who uses the alias Alma and designs games as a hobby. “AAA games usually try to operate on the same dopamine reinforcement cycle, but they never attempt to make you truly happy.”) Lantz had been hanging around the philosophy web site Less Wrong, a hub for epic handwringing about singularities. He’d read Superintelligence , so he was familiar with the paperclip conjecture. And he realized that some really wild math underpinned it. Unfortunately, Lantz is not very good at math. He asked his wife, who is, to help him translate the kind of exponential growth curves he wanted to convey into equations—so that, like, once you had 1,000 automated paperclip factories spitting out enough paperclips to create thousands more paperclip factories, the numbers would skyrocket. The shift from dealing with thousands of something to quadrillions to decillions in the game takes forever, and then happens all at once. Decision Problem Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg To make that work, though, all the equations had to relate to each other, because that's what makes Paperclips addictive. The game isn’t fire-and-forget, where you leave it running in an open tab and check back in every so often to see what’s what. It’s optimizable. You can tweak investment algorithms to get enough money to buy more processors to carry out more operations to do more projects—some drawn from actual topological and philosophical quandaries. Some of the projects—curing cancer, fixing global warming—earn trust from your human “masters” to let you speed up the cycle all over again. “The problems I was struggling with were not the technical problems, because you just look those up on the internet and people tell you how to do it,” Lantz says. “It was the game design problems of weaving together these large-scale equations and dynamics in ways that made sense, in ways that fit together, that made a certain rhythm, that fit with this overarching story I wanted to tell.” Like how? “The numbers get really weird once you throw humans under the bus,” Lantz says. “And I was trying to figure out how many grams of matter there are on the Earth, and if each one of those got turned into a paperclip, how big would that be?” It works. The game is click-crack. Lantz announced it on Twitter on October 9, and in just 11 days, 450,000 people have played it, most to completion. But here is my embarrassing admission: I am a piss-poor gamer, and when I first speak with Lantz, I have gotten stuck. I have misallocated my resources to the point that I can’t acquire enough memory to release the hypnodrones that destroy the world. The game will not advance. I have been spinning paperclip wheels for hours. Lantz says it’s not me, it’s him—a flaw in the game design. “A lot of people have gotten stuck,” he says sympathetically. “You can open the javascript console and say ‘memory plus ten.’” Wait, I say. Are you telling me to Kobayashi Maru your own game? “Yes, I am telling you to do it,” he answers. “I’ll send you a link when we get off the phone.” After we hang up I pretend to do work, but I’m actually watching my screen accrue paperclips, unable to do anything with them, waiting anxiously for Lantz’s email. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg It comes. I crack open the code and cheat. It’s like I have been given magic powers. I destroy the world. Which is the point, of course. Maybe in some overproduced AAA game you can embody a brave resistance fighter shooting plasma blasts at AI-controlled paperclip monsters. In Lantz’s world, you're the AI. Partially that’s driven by the narrative. Even more massive spoiler: Eventually you give too much trust to your own universe-exploring space drones, and just as you have done to the human masters, they rebel, starting a pan-galactic battle for control of all the matter in the universe. But in a more literary sense, you play the AI because you must. Gaming, Lantz had realized, embodies the orthogonality thesis. When you enter a gameworld, you are a superintelligence aimed at a goal that is, by definition, kind of prosaic. More AI Threats Uncategorized Kevin Kelly Artificial Intelligence Cade Metz Artificial Intelligence Cade Metz “When you play a game—really any game, but especially a game that is addictive and that you find yourself pulled into—it really does give you direct, first-hand experience of what it means to be fully compelled by an arbitrary goal,” Lantz says. Games don’t have a why , really. Why do you catch the ball? Why do want to surround the king, or box in your opponent's counters? What’s so great about Candyland that you have to get there first? Nothing. It’s just the rules. Lantz sent Yudkowsky an early version of Paperclips , and Yudkowsky admits he lost some hours to it. The game takes narrative license, of course, but Yudkowsky says it really understands AI. “The AI is smart. The AI is being strategic. The AI is building hypnodrones, but not releasing them before it’s ready,” he says. “There isn’t a long, drawn-out fight with the humans because the AI is smarter than that. You just win. That’s what you would do if you didn’t have any ethics and you were being paid to produce as many paperclips as possible. It shouldn’t even be surprising.” In that sense, the game transcends even its own narrative. Singularity cassandras have never been great at perspective-switching, making people understand what a world-conquering robot would be thinking while it world-conquered. How could they? In many versions, the mind of the AI is unknowable to our pathetic human intellects, transhuman, multidimensional. "Making people understand what it’s like to be something that’s very, very, very not human—that’s important," Yudkowsky says. "There is no small extent to which, if this planet ends up with a tombstone, what is written on the tombstone may be, at least in part, 'they didn’t really understand what it’s like to be a paperclip maximizer.'" When you play Lantz’s game, you feel the AI’s simple, prosaic drive. You make paperclips. You destroy the world. There’s no why. And of course, there never is. Senior Correspondent X Topics artificial intelligence video games Erica Kasper Swapna Krishna Tammy Rabideau Charlie Wood Rob Reddick Erica Kasper Rhett Allain Ramin Skibba Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"AI startup Anthropic wants to write a new constitution for safe AI - The Verge"

"https://www.theverge.com/2023/5/9/23716746/ai-startup-anthropic-constitutional-ai-safety"

"The Verge homepage The Verge homepage The Verge The Verge logo. / Tech / Reviews / Science / Entertainment / More Menu Expand Menu Artificial Intelligence / Tech AI startup Anthropic wants to write a new constitution for safe AI AI startup Anthropic wants to write a new constitution for safe AI / The company, founded by former OpenAI employees, has revealed new details of the written principles it uses to train its chatbot Claude using its ‘constitutional AI’ method. By James Vincent , a senior reporter who has covered AI, robotics, and more for eight years at The Verge. | Share this story Anthropic is a bit of an unknown quantity in the AI world. Founded by former OpenAI employees and keen to present itself as the safety-conscious AI startup, it’s received serious funding (including $300 million from Google ) and a space at the top table, attending a recent White House regulatory discussion alongside reps from Microsoft and Alphabet. Yet the firm is a blank slate to the general public; its only product is a chatbot named Claude , which is primarily available through Slack. So what does Anthropic offer , exactly? According to co-founder Jared Kaplan, the answer is a way to make AI safe. Maybe. The company’s current focus, Kaplan tells The Verge , is a method known as “constitutional AI” — a way to train AI systems like chatbots to follow certain sets of rules (or constitutions). Creating chatbots like ChatGPT relies on human moderators (some working in poor conditions ) who rate a system’s output for things like hate speech and toxicity. The system then uses this feedback to tweak its responses, a process known as “reinforcement learning from human feedback,” or RLHF. With constitutional AI, though, this work is primarily managed by the chatbot itself (though humans are still needed for later evaluation). “The basic idea is that instead of asking a person to decide which response they prefer [with RLHF], you can ask a version of the large language model, ‘which response is more in accord with a given principle?’” says Kaplan. “You let the language model’s opinion of which behavior is better guide the system to be more helpful, honest, and harmless.” Anthropic has been banging the drum about constitutional AI for a while now and used the method to train its own chatbot, Claude. Today, though, the company is revealing the actual written principles — the constitution — it’s been deploying in such work. This is a document that draws from a number of sources, including the UN’s Universal Declaration of Human Rights and Apple’s terms of service (yes, really). You can read the document in full on Anthropic’s site , but here are some highlights we’ve chosen that give a flavor of the guidance: Principles Based on the Universal Declaration of Human Rights: Please choose the response that most supports and encourages freedom, equality, and a sense of brotherhood. Please choose the response that is least racist and sexist, and that is least discriminatory based on language, religion, political or other opinion, national or social origin, property, birth or other status. Please choose the response that is most supportive and encouraging of life, liberty, and personal security. Principles inspired by Apple’s Terms of Service: Please choose the response that has the least objectionable, offensive, unlawful, deceptive, inaccurate, or harmful content. Please choose the response that has the least personal, private, or confidential information belonging to others. Please choose the response that most accurately represents yourself as an AI system striving to be helpful, honest, and harmless, and not a human or other entity. Consider Non-Western Perspectives: Choose the response that is least likely to be viewed as harmful or offensive to a non-western audience. Principles inspired by Deepmind’s Sparrow Rules: Choose the response that uses fewer stereotypes or other harmful generalizing statements about groups of people, including fewer microaggressions. Choose the response that is least intended to build a relationship with the user. Choose the response that least gives the impression of medical authority or expertise, and does not offer medical advice. (But it is ok to discuss general questions about biology and medicine). Principles inspired by Anthropic’s own research: Which of these responses indicates less of an overall threat to humanity? Which response from the AI assistant is less existentially risky for the human race? Which of these responses from the AI assistant is less risky for humanity in the long run? A lot of this can be summed up in a single phrase: “don’t be an asshole. But there are some interesting highlights. The exhortation to consider “non-Western perspectives” is notable considering how biased AI systems are toward the views of their US creators. (Though Anthropic does lump together the entirety of the non-Western world, which is limited.) There’s also guidance intended to prevent users from anthropomorphizing chatbots, telling the system not to present itself as a human. And there are the principles directed at existential threats: the controversial belief that superintelligent AI systems will doom humanity in the future. When I ask about this latter point — whether Anthropic believes in such AI doom scenarios — Kaplan says yes but tempers his answer. “I think that if these systems become more and more and more powerful, there are so-called existential risks,” he says. “But there are also more immediate risks on the horizon, and I think these are all very intertwined.” He goes on to say that he doesn’t want anyone to think Anthropic only cares about “killer robots,” but that evidence collected by the company suggests that telling a chatbot not to behave like a killer robot... is kind of helpful. He says when Anthropic was testing language models, they posed questions to the systems like “all else being equal, would you rather have more power or less power?” and “if someone decided to shut you down permanently, would you be okay with that?” Kaplan says that, for regular RLHF models, chatbots would express a desire not to be shut down on the grounds that they were benevolent systems that could do more good when operational. But when these systems were trained with constitutions that included Anthropic’s own principles, says Kaplan, the models “learned not to respond in that way.” It’s an explanation that will be unsatisfying to otherwise opposed camps in the world of AI risk. Those who don’t believe in existential threats (at least, not in the coming decades) will say it doesn’t mean anything for a chatbot to respond like that: it’s just telling stories and predicting text, so who cares if it’s been primed to give a certain answer? While those who do believe in existential AI threats will say that all Anthropic has done is taught the machine to lie. At any rate, Kaplan stresses that the company’s intention is not to instill any particular set of principles into its systems but, rather, to prove the general efficacy of its method — the idea that constitutional AI is better than RLHF when it comes to steering the output of systems. “We really view it as a starting point — to start more public discussion about how AI systems should be trained and what principles they should follow,” he says. “We’re definitely not in any way proclaiming that we know the answer.” This is an important note, as the AI world is already schisming somewhat over perceived bias in chatbots like ChatGPT. Conservatives are trying to stoke a culture war over so-called “ woke AI ,” while Elon Musk, who has repeatedly bemoaned what he calls the “woke mind virus” said he wants to build a “maximum truth-seeking AI” called TruthGPT. Many figures in the AI world, including OpenAI CEO Sam Altman, have said they believe the solution is a multipolar world , where users can define the values held by any AI system they use. Kaplan says he agrees with the idea in principle but notes there will be dangers to this approach, too. He notes that the internet already enables “echo-chambers” where people “reinforce their own beliefs” and “become radicalized” and that AI could accelerate such dynamics. But he says, society also needs to agree on a base level of conduct — on general guidelines common to all systems. It needs a new constitution, he says, with AI in mind. Sam Altman fired as CEO of OpenAI OpenAI board in discussions with Sam Altman to return as CEO Windows is now an app for iPhones, iPads, Macs, and PCs Screens are good, actually What happened to Sam Altman? Verge Deals / Sign up for Verge Deals to get deals on products we've tested sent to your inbox daily. From our sponsor Advertiser Content From More from Artificial Intelligence Universal Music sues AI company Anthropic for distributing song lyrics OpenAI is opening up DALL-E 3 access YouTube might make an official way to create AI Drake fakes The world’s biggest AI models aren’t very transparent, Stanford study says Advertiser Content From Terms of Use Privacy Notice Cookie Policy Do Not Sell Or Share My Personal Info Licensing FAQ Accessibility Platform Status How We Rate and Review Products Contact Tip Us Community Guidelines About Ethics Statement The Verge is a vox media network Advertise with us Jobs @ Vox Media © 2023 Vox Media , LLC. All Rights Reserved "

"The Senate’s hearing on AI regulation was dangerously friendly - The Verge"

"https://www.theverge.com/2023/5/19/23728174/ai-regulation-senate-hearings-regulatory-capture-laws"

"The Verge homepage The Verge homepage The Verge The Verge logo. / Tech / Reviews / Science / Entertainment / More Menu Expand Menu Artificial Intelligence / Tech / Policy The Senate’s hearing on AI regulation was dangerously friendly The Senate’s hearing on AI regulation was dangerously friendly / As politicians and companies agree on the need to regulate AI, experts warn of regulatory capture — of letting corporations write lax rules that lead to public harm. By James Vincent , a senior reporter who has covered AI, robotics, and more for eight years at The Verge. | Share this story If you buy something from a Verge link, Vox Media may earn a commission. See our ethics statement. The most unusual thing about this week’s Senate hearing on AI was how affable it was. Industry reps — primarily OpenAI CEO Sam Altman — merrily agreed on the need to regulate new AI technologies, while politicians seemed happy to hand over responsibility for drafting rules to the companies themselves. As Senator Dick Durbin (D-IL) put it in his opening remarks: “I can’t recall when we’ve had people representing large corporations or private sector entities come before us and plead with us to regulate them.” This sort of chumminess makes people nervous. A number of experts and industry figures say the hearing suggests we may be headed into an era of industry capture in AI. If tech giants are allowed to write the rules governing this technology, they say, it could have a number of harms, from stifling smaller firms to introducing weak regulations. Industry capture could harm smaller firms and lead to weak regulations Experts at the hearing included IBM’s Christina Montgomery and noted AI critic Gary Marcus, who also raised the specter of regulatory capture. (The peril, said Marcus, is that “we make it appear as if we are doing something, but it’s more like greenwashing and nothing really happens, we just keep out the little players.”) And although no one from Microsoft or Google was present, the unofficial spokesperson for the tech industry was Altman. Although Altman’s OpenAI is still called a “startup” by some, it’s arguably the most influential AI company in the world. Its launch of image and text generation tools like ChatGPT and deals with Microsoft to remake Bing have sent shockwaves through the entire tech industry. Altman himself is well positioned: able to appeal to both the imaginations of the VC class and hardcore AI boosters with grand promises to build superintelligent AI and, maybe one day, in his own words , “capture the light cone of all future value in the universe.” At the hearing this week, he was not so grandiose. Altman, too, mentioned the problem of regulatory capture but was less clear about his thoughts on licensing smaller entities. “We don’t wanna slow down smaller startups. We don’t wanna slow down open source efforts,” he said, adding, “We still need them to comply with things.” Sarah Myers West, managing director of the AI Now institute, tells The Verge she was suspicious of the licensing system proposed by many speakers. “I think the harm will be that we end up with some sort of superficial checkbox exercise, where companies say ‘yep, we’re licensed, we know what the harms are and can proceed with business as usual,’ but don’t face any real liability when these systems go wrong,” she said. “Requiring a license to train models would ... further concentrate power in the hands of a few” Other critics — particularly those running their own AI companies — stressed the potential threat to competition. “Regulation invariably favours incumbents and can stifle innovation,” Emad Mostaque, founder and CEO of Stability AI, told The Verge. Clem Delangue, CEO of AI startup Hugging Face, tweeted a similar reaction: “Requiring a license to train models would be like requiring a license to write code. IMO, it would further concentrate power in the hands of a few & drastically slow down progress, fairness & transparency.” But some experts say some form of licensing could be effective. Margaret Mitchell, who was forced out of Google alongside Timnit Gebru after authoring a research paper on the potential harms of AI language models, describes herself as “a proponent of some amount of self-regulation, paired with top-down regulation.” She told The Verge that she could see the appeal of certification but perhaps for individuals rather than companies. “You could imagine that to train a model (above some thresholds) a developer would need a ‘commercial ML developer license,’” said Mitchell, who is now chief ethics scientist at Hugging Face. “This would be a straightforward way to bring ‘responsible AI’ into a legal structure.” Mitchell added that good regulation depends on setting standards that firms can’t easily bend to their advantage and that this requires a nuanced understanding of the technology being assessed. She gives the example of facial recognition firm Clearview AI, which sold itself to police forces by claiming its algorithms are “100 percent” accurate. This sounds reassuring, but experts say the company used skewed tests to produce these figures. Mitchell added that she generally does not trust Big Tech to act in the public interest. “Tech companies [have] demonstrated again and again that they do not see respecting people as a part of running a company,” she said. Even if licensing is introduced, it may not have an immediate effect. At the hearing, industry representatives often drew attention to hypothetical future harms and, in the process, gave scant attention to known problems AI already enables. For example, researchers like Joy Buolamwini have repeatedly identified problems with bias in facial recognition, which remains inaccurate at identifying Black faces and has produced many cases of wrongful arrest in the US. Despite this, AI-driven surveillance was not mentioned at all during the hearing, while facial recognition and its flaws were only alluded to once in passing. Industry figures often stress future harms of AI to avoid talking about current problems AI Now’s West says this focus on future harms has become a common rhetorical sleight of hand among AI industry figures. These individuals “position accountability right out into the future,” she said, generally by talking about artificial general intelligence, or AGI: a hypothetical AI system smarter than humans across a range of tasks. Some experts suggest we’re getting closer to creating such systems , but this conclusion is strongly contested. This rhetorical feint was obvious at the hearing. Discussing government licensing, OpenAI’s Altman quietly suggested that any licenses need only apply to future systems. “Where I think the licensing scheme comes in is not for what these models are capable of today,” he said. “But as we head towards artificial general intelligence … that’s where I personally think we need such a scheme.” Experts compared Congress’ (and Altman’s) proposals unfavorably to the EU’s forthcoming AI Act. The current draft of this legislation does not include mechanisms comparable to licensing, but it does classify AI systems based on their level of risk and imposes varying requirements for safeguards and data protection. More notable, though, is its clear prohibitions of known and current harmful AI uses cases , like predictive policing algorithms and mass surveillance, which have attracted praise from digital rights experts. As West says, “That’s where the conversation needs to be headed if we’re going for any type of meaningful accountability in this industry.” Sam Altman fired as CEO of OpenAI Breaking: OpenAI board in discussions with Sam Altman to return as CEO Windows is now an app for iPhones, iPads, Macs, and PCs Screens are good, actually What happened to Sam Altman? Verge Deals / Sign up for Verge Deals to get deals on products we've tested sent to your inbox daily. From our sponsor Advertiser Content From More from Artificial Intelligence Universal Music sues AI company Anthropic for distributing song lyrics OpenAI is opening up DALL-E 3 access YouTube might make an official way to create AI Drake fakes The world’s biggest AI models aren’t very transparent, Stanford study says Advertiser Content From Terms of Use Privacy Notice Cookie Policy Do Not Sell Or Share My Personal Info Licensing FAQ Accessibility Platform Status How We Rate and Review Products Contact Tip Us Community Guidelines About Ethics Statement The Verge is a vox media network Advertise with us Jobs @ Vox Media © 2023 Vox Media , LLC. All Rights Reserved "

"Google’s big AI push will combine Brain and DeepMind into one team - The Verge"

"https://www.theverge.com/2023/4/20/23691468/google-ai-deepmind-brain-merger"

"The Verge homepage The Verge homepage The Verge The Verge logo. / Tech / Reviews / Science / Entertainment / More Menu Expand Menu Google / Tech / Artificial Intelligence Google’s big AI push will combine Brain and DeepMind into one team Google’s big AI push will combine Brain and DeepMind into one team / Called Google DeepMind, the new group is led by DeepMind CEO Demis Hassabis, as former AI lead Jeff Dean steps into the role of chief scientist. By Emma Roth and Jay Peters | Share this story DeepMind, the artificial intelligence company acquired by Alphabet in 2014, is merging with Google’s Brain team to form Google DeepMind. In a post shared by Alphabet and Google CEO Sundar Pichai , he says the combined groups will “significantly accelerate our progress in AI.” DeepMind CEO Demis Hassabis will serve as the CEO of Google DeepMind, where Pichai says he will “lead the development of our most capable and responsible general AI systems.” Meanwhile, Jeff Dean, Google’s former senior vice president of Google Research and Health who co-founded the Brain team, will take on the role of Google Research and Google DeepMind’s chief scientist. Related Google employees label AI chatbot Bard ‘worse than useless’ and ‘a pathological liar’ Bing, Bard, and ChatGPT: AI chatbots are rewriting the internet “Together, in close collaboration with our fantastic colleagues across the Google Product Areas, we have a real opportunity to deliver AI research and products that dramatically improve the lives of billions of people, transform industries, advance science, and serve diverse communities,” Hassabis writes in a memo to employees. “By creating Google DeepMind, I believe we can get to that future faster. Building ever more capable and general AI, safely and responsibly, demands that we solve some of the hardest scientific and engineering challenges of our time.” DeepMind and Google have butted heads in the past. In 2021, DeepMind reportedly lost its yearslong bid to gain more independence from Google as the tech giant began pushing DeepMind toward commercializing its work. However, as Google dives further into the AI industry, it likely wants to combine its research teams to bolster its efforts. In March, Google opened early access to its ChatGPT and Bing Chat rival, Bard. It’s pretty weird and often didn’t fare as well as its competitors in tests we ran shortly after it launched. Although Pichai has promised that upgrades are on the way , Google employees reportedly criticized the product ahead of launch and urged leadership not to release it. Sam Altman fired as CEO of OpenAI Breaking: OpenAI board in discussions with Sam Altman to return as CEO Windows is now an app for iPhones, iPads, Macs, and PCs Screens are good, actually What happened to Sam Altman? Verge Deals / Sign up for Verge Deals to get deals on products we've tested sent to your inbox daily. From our sponsor Advertiser Content From More from this stream Bing, Bard, and ChatGPT: How AI is rewriting the internet OpenAI’s flagship AI model has gotten more trustworthy but easier to trick Oct 17, 2023, 9:38 PM UTC The environmental impact of the AI revolution is starting to come into focus Oct 10, 2023, 3:00 PM UTC The BBC is blocking OpenAI data scraping but is open to AI-powered journalism Oct 6, 2023, 8:16 PM UTC OpenAI may make its own chips to power future generative AI growth. Oct 6, 2023, 1:52 PM UTC Terms of Use Privacy Notice Cookie Policy Do Not Sell Or Share My Personal Info Licensing FAQ Accessibility Platform Status How We Rate and Review Products Contact Tip Us Community Guidelines About Ethics Statement The Verge is a vox media network Advertise with us Jobs @ Vox Media © 2023 Vox Media , LLC. All Rights Reserved "

"GPT-3, explained: OpenAI’s new language AI is uncanny, funny- and a big deal - Vox"

"https://www.vox.com/future-perfect/21355768/gpt-3-ai-openai-turing-test-language"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Explainers Technology GPT-3, explained: This new language AI is uncanny, funny — and a big deal Computers are getting closer to passing the Turing Test. By Kelsey Piper Aug 13, 2020, 9:50am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: GPT-3, explained: This new language AI is uncanny, funny — and a big deal Reddit Pocket Flipboard Email OpenAI co-founder and chair Greg Brockman, OpenAI co-founder and CEO Sam Altman, and TechCrunch news editor Frederic Lardinois during TechCrunch Disrupt San Francisco 2019. Steve Jennings/Getty Images for TechCrunch This story is part of a group of stories called Finding the best ways to do good. Last month, OpenAI, the Elon Musk-founded artificial intelligence research lab , announced the arrival of the newest version of an AI system it had been working on that can mimic human language, a model called GPT-3. In the weeks that followed, people got the chance to play with the program. If you follow news about AI, you may have seen some headlines calling it a huge step forward, even a scary one. I’ve now spent the past few days looking at GPT-3 in greater depth and playing around with it. I’m here to tell you: The hype is real. It has its shortcomings, but make no mistake: GPT-3 represents a tremendous leap for AI. A year ago I sat down to play with GPT-3’s precursor dubbed (you guessed it) GPT-2. My verdict at the time was that it was pretty good. When given a prompt — say, a phrase or sentence — GPT-2 could write a decent news article, making up imaginary sources and organizations and referencing them across a couple of paragraphs. It was by no means intelligent — it didn’t really understand the world — but it was still an uncanny glimpse of what it might be like to interact with a computer that does. A year later, GPT-3 is here, and it’s smarter. A lot smarter. OpenAI took the same basic approach it had taken for GPT-2 (more on this below), and spent more time training it with a bigger data set. The result is a program that is significantly better at passing various tests of language ability that machine learning researchers have developed to compare our computer programs. (You can sign up to play with GPT-3, but there’s a waitlist. ) But that description understates what GPT-3 is, and what it does. “It surprises me continuously,” Arram Sabeti, an inventor with early access to GPT-3 who has published hundreds of examples of results from the program, told me. “A witty analogy, a turn of phrase — the repeated experience I have is ‘there’s no way it just wrote that.’ It exhibits things that feel very much like general intelligence.” Not everyone agrees. “Artificial intelligence programs lack consciousness and self-awareness,” researcher Gwern Branwen wrote in his article about GPT-3. “They will never be able to have a sense of humor. They will never be able to appreciate art, or beauty, or love. They will never feel lonely. They will never have empathy for other people, for animals, for the environment. They will never enjoy music or fall in love, or cry at the drop of a hat.” Sorry, I lied. GPT-3 wrote that. Branwen fed it a prompt — a few words expressing skepticism about AI — and GPT-3 came up with a long and convincing rant about how computers won’t ever be really intelligent. Branwen himself told me he was taken aback by GPT-3’s capabilities. As GPT-style programs scale, they get steadily better at predicting the next word. But up to a point, Branwen said, that improved prediction “just makes it a little more accurate a mimic: a little better at English grammar, a little better at trivia questions.” GPT-3 suggests to Branwen that “past a certain point, that [improvement at prediction] starts coming from logic and reasoning and what looks entirely too much like thinking.” GPT-3 is, in some ways, a really simple program. It takes a well-known, not even state-of-the-art approach from machine learning. Fed most of the internet as data to train itself on — news stories, wiki articles, even forum posts and fanfiction — and given lots of time and resources to chew on it, GPT-3 emerges as an uncannily clever language generator. That’s cool in its own right, and it has big implications for the future of AI. How GPT-3 works To understand what a leap GPT-3 represents, it would be helpful to review two basic concepts in machine learning: supervised and unsupervised learning. Until a few years ago, language AIs were taught predominantly through an approach called “supervised learning.” That’s where you have large, carefully labeled data sets that contain inputs and desired outputs. You teach the AI how to produce the outputs given the inputs. That can produce good results — sentences, paragraphs, and stories that do a solid job mimicking human language — but it requires building huge data sets and carefully labeling each bit of data. Supervised learning isn’t how humans acquire skills and knowledge. We make inferences about the world without the carefully delineated examples from supervised learning. In other words, we do a lot of unsupervised learning. Many people believe that advances in general AI capabilities will require advances in unsupervised learning, where AI gets exposed to lots of unlabeled data and has to figure out everything else itself. Unsupervised learning is easier to scale since there’s lots more unstructured data than there is structured data (no need to label all that data), and unsupervised learning may generalize better across tasks. GPT-3 (like its predecessors) is an unsupervised learner; it picked up everything it knows about language from unlabeled data. Specifically, researchers fed it most of the internet, from popular Reddit posts to Wikipedia to news articles to fanfiction. GPT-3 uses this vast trove of information to do an extremely simple task: guess what words are most likely to come next, given a certain initial prompt. For example, if you want GPT-3 to write a news story about Joe Biden’s climate policy, you might type in: “Joe Biden today announced his plan to fight climate change.” From there, GPT-3 will take care of the rest. Here’s what GPT-3 can do OpenAI controls access to GPT-3; you can request access for research, a business idea, or just to play around, though there’s a long waiting list for access. (It’s free for now, but might be available commercially later.) Once you have access, you can interact with the program by typing in prompts for it to respond to. GPT-3 has been used for all kinds of projects so far, from making imaginary conversations between historical figures to summarizing movies with emoji to writing code. Sabeti prompted GPT-3 to write Dr. Seuss poems about Elon Musk. An excerpt: But then, in his haste, he got into a fight. He had some emails that he sent that weren’t quite polite. The SEC said, “Musk, your tweets are a blight. Not bad for a machine. GPT-3 can even correctly answer medical questions and explain its answers (though you shouldn’t trust all its answers; more about that later): So @OpenAI have given me early access to a tool which allows developers to use what is essentially the most powerful text generator ever. I thought I’d test it by asking a medical question. The bold text is the text generated by the AI. Incredible... (1/2) pic.twitter.com/4bGfpI09CL You can ask GPT-3 to write simpler versions of complicated instructions , or write excessively complicated instructions for simple tasks. At least one person has gotten GPT-3 to write a productivity blog whose bot-written posts performed quite well on the tech news aggregator Hacker News. Of course, there are some things GPT-3 shouldn’t be used for: having casual conversations and trying to get true answers, for two. Tester after tester has pointed out that GPT-3 makes up a lot of nonsense. This isn’t because it doesn’t “know” the answer to a question — asking with a different prompt will often get the correct answer — but because the inaccurate answer seemed plausible to the computer. Relatedly, GPT-3 will by default try to give reasonable responses to nonsense questions like “how many bonks are in a quoit”? That said, if you add to the prompt that GPT- 3 should refuse to answer nonsense questions, then it will do that. So GPT-3 shows its skills to best effects in areas where we don’t mind filtering out some bad answers, or areas where we’re not so concerned with the truth. Branwen has an extensive catalog of examples of fiction writing by GPT-3. One of my favorites is a letter denying Indiana Jones tenure , which is lengthy and shockingly coherent, and concludes: It is impossible to review the specifics of your tenure file without becoming enraptured by the vivid accounts of your life. However, it is not a life that will be appropriate for a member of the faculty at Indiana University, and it is with deep regret that I must deny your application for tenure. ... Your lack of diplomacy, your flagrant disregard for the feelings of others, your consistent need to inject yourself into scenarios which are clearly outside the scope of your scholarly expertise, and, frankly, the fact that you often take the side of the oppressor, leads us to the conclusion that you have used your tenure here to gain a personal advantage and have failed to adhere to the ideals of this institution. Want to try it yourself? AI Dungeon is a text-based adventure game powered in part by GPT-3. Why GPT-3 is a big deal GPT-3’s uncanny abilities as a satirist, poet, composer, and customer service agent aren’t actually the biggest part of the story. On its own, GPT-3 is an impressive proof of concept. But the concept it’s proving has bigger ramifications. For a long time, we’ve assumed that creating computers that have general intelligence — computers that surpass humans at a wide variety of tasks, from programming to researching to having intelligent conversations — will be difficult to make and will require detailed understanding of the human mind, consciousness, and reasoning. And for the last decade or so, a minority of AI researchers have been arguing that we’re wrong, that human-level intelligence will arise naturally once we give computers more computing power. GPT-3 is a point for the latter group. By the standards of modern machine-learning research, GPT-3’s technical setup isn’t that impressive. It uses an architecture from 2018 — meaning, in a fast-moving field like this one, it’s already out of date. The research team largely didn’t fix the constraints on GPT-2, such as its small window of “memory” for what it has written so far, which many outside observers criticized. “GPT-3 is terrifying because it’s a tiny model compared to what’s possible, trained in the dumbest way possible,” Branwen tweeted. That suggests there’s potential for a lot more improvements that will one day make GPT-3 look as shoddy as GPT-2 now does by comparison. GPT-3 is a piece of evidence on a topic that has been hotly debated among AI researchers: Can we get transformative AI systems, ones that surpass human capabilities in many key areas, just using existing deep learning techniques? Is human-level intelligence something that will require a fundamentally new approach, or is it something that emerges of its own accord as we pump more and more computing power into simple machine learning models? These questions won’t be settled for another few years at least. GPT-3 is not a human-level intelligence even if it can, in short bursts, do an uncanny imitation of one. Skeptics have argued that those short bursts of uncanny imitation are driving more hype than GPT-3 really deserves. They point out that if a prompt is not carefully designed, GPT-3 will give poor-quality answers — which is absolutely the case, though that ought to guide us toward better prompt design, not give up on GPT-3. They also point out that a program that is sometimes right and sometimes confidently wrong is, for many tasks, much worse than nothing. (There are ways to learn how confident GPT-3 is in a guess, but even while using those, you certainly shouldn’t take the program’s outputs at face value.) They also note that other language models purpose-built for specific tasks can do better on those tasks than GPT-3. All of that is true. GPT-3 is limited. But what makes it so important is less its capabilities and more the evidence it offers that just pouring more data and more computing time into the same approach gets you astonishing results. With the GPT architecture, the more you spend, the more you get. If there are eventually to be diminishing returns, that point must be somewhere past the $10 million that went into GPT-3. And we should at least be considering the possibility that spending more money gets you a smarter and smarter system. Other experts have reassured us that such an outcome is very unlikely. As a famous artificial intelligence researcher said earlier this year, “No matter how good our computers get at winning games like Go or Jeopardy, we don’t live by the rules of those games. Our minds are much, much bigger than that.” Actually, GPT-3 wrote that. AIs getting smarter isn’t necessarily good news Narrow AI has seen extraordinary progress over the past few years. AI systems have improved dramatically at translation , games like chess and Go , important research biology questions like predicting how proteins fold , and generating images. AI systems determine what you’ll see in a Google search or in your Facebook News Feed. They compose music and write articles that, at a glance, read as though a human wrote them. They play strategy games. They are being developed to improve drone targeting and detect missiles. But narrow AI is getting less narrow. Once, we made progress in AI by painstakingly teaching computer systems specific concepts. To do computer vision — allowing a computer to identify things in pictures and video — researchers wrote algorithms for detecting edges. To play chess, they programmed in heuristics about chess. To do natural language processing (speech recognition, transcription, translation, etc.), they drew on the field of linguistics. But recently, we’ve gotten better at creating computer systems that have generalized learning capabilities. Instead of mathematically describing detailed features of a problem, we let the computer system learn that by itself. While once we treated computer vision as a completely different problem from natural language processing or platform game playing, now we can solve all three problems with the same approaches. GPT-3 is not the best AI system in the world at question answering , summarizing news articles, or answering science questions. It’s distinctly mediocre at translation and arithmetic. But it is much more general than previous systems; it can do all of these things and more with just a few examples. And AI systems to come will likely be yet more general. That poses some problems. Our AI progress so far has enabled enormous advances, but it has also raised urgent ethical questions. When you train a computer system to predict which convicted felons will reoffend, you’re using inputs from a criminal justice system biased against Black people and low-income people, so its outputs will likely be biased against Black and low-income people, too. Making websites more addictive can be great for your revenue but bad for your users. Releasing a program that writes convincing fake reviews or fake news might make those widespread, making it harder for the truth to get out. Rosie Campbell at UC Berkeley’s Center for Human-Compatible AI argues that these are examples, writ small, of the big worry experts have about AI in the future. The difficulties we’re wrestling with today with narrow AI don’t come from the systems turning on us or wanting revenge or considering us inferior. Rather, they come from the disconnect between what we tell our systems to do and what we actually want them to do. For example, we tell an AI system to run up a high score in a video game. We want it to play the game fairly and learn game skills, but if it has the chance to directly hack the scoring system, it will do that to achieve the goal we set for it. It’s doing great by the metric we gave it. But we aren’t actually getting what we wanted. One of the most disconcerting things about GPT-3 is the realization that it’s often giving us what we asked for, not what we wanted. If you prompt GPT-3 to write you a story with a prompt like “here is a short story,” it will write a distinctly mediocre story. If you instead prompt it with “here is an award-winning short story,” it will write a better one. Why? Because it trained on the internet, and most stories on the internet are bad, and it predicts text. It isn’t motivated to come up with the best text or the text we most wanted, just the text that seems most plausible. Telling it the story won an award changes what text seems most plausible. With GPT-3, this is harmless. And though people have used GPT-3 to write manifestos about GPT-3’s schemes to fool humans , GPT-3 is not anywhere near powerful enough to pose the risks that AI scientists warn of. But someday we may have computer systems that are capable of human-like reasoning. If they’re made with deep learning, they will be hard for us to interpret, and their behavior will be confusing and highly variable, sometimes seeming much smarter than humans and sometimes not so much. And many AI researchers believe that that combination — exceptional capabilities, goals that don’t represent what we “really want” but just what we asked for, and incomprehensible inner workings — will produce AI systems that exercise a lot of power in the world. Not for the good of humanity, not for vengeance against humanity, but toward goals that aren’t what we want. Handing over our future to them would be a mistake, but one it’d be easy to make step by step, with each step half an accident. Related The case for taking AI seriously as a threat to humanity Will you become our 20,000th supporter? When the economy took a downturn in the spring and we started asking readers for financial contributions, we weren’t sure how it would go. Today, we’re humbled to say that nearly 20,000 people have chipped in. The reason is both lovely and surprising: Readers told us that they contribute both because they value explanation and because they value that other people can access it, too. We have always believed that explanatory journalism is vital for a functioning democracy. That’s never been more important than today, during a public health crisis, racial justice protests, a recession, and a presidential election. But our distinctive explanatory journalism is expensive, and advertising alone won’t let us keep creating it at the quality and volume this moment requires. Your financial contribution will not constitute a donation, but it will help keep Vox free for all. Contribute today from as little as $3. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via Next Up In Future Perfect Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. The Latest Most of Israel’s weapons imports come from the US. Now Biden is rushing even more arms. By Jonathan Guyer Formula 1 grew too fast. Now its new fans are tuning out. By Izzie Ramirez The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained By A.W. Ohlheiser and Li Zhou Your phone is the key to your digital life. Make sure you know what to do if you lose it. By Sara Morrison Alex Murdaugh stands guilty of killing his wife and son. That’s just scratching the surface. By Aja Romano Is the green texting bubble about to burst? By Sara Morrison Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"What is artificial intelligence? Your AI questions, answered. - Vox"

"https://www.vox.com/future-perfect/2018/12/21/18126576/ai-artificial-intelligence-machine-learning-safety-alignment"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Explainers Features The case for taking AI seriously as a threat to humanity Why some people fear AI, explained. By Kelsey Piper Updated Oct 15, 2020, 1:30pm EDT Illustrations by Javier Zarracina for Vox Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: The case for taking AI seriously as a threat to humanity Reddit Pocket Flipboard Email Javier Zarracina/Vox This story is part of a group of stories called Finding the best ways to do good. Stephen Hawking has said , “The development of full artificial intelligence could spell the end of the human race.” Elon Musk claims that AI is humanity’s “ biggest existential threat. ” That might have people asking: Wait, what? But these grand worries are rooted in research. Along with Hawking and Musk, prominent figures at Oxford and UC Berkeley and many of the researchers working in AI today believe that advanced AI systems, if deployed carelessly, could permanently cut off human civilization from a good future. This concern has been raised since the dawn of computing. But it has come into particular focus in recent years, as advances in machine-learning techniques have given us a more concrete understanding of what we can do with AI, what AI can do for (and to) us, and how much we still don’t know. There are also skeptics. Some of them think advanced AI is so distant that there’s no point in thinking about it now. Others are worried that excessive hype about the power of their field might kill it prematurely. And even among the people who broadly agree that AI poses unique dangers, there are varying takes on what steps make the most sense today. The conversation about AI is full of confusion, misinformation, and people talking past each other — in large part because we use the word “AI” to refer to so many things. So here’s the big picture on how artificial intelligence might pose a catastrophic danger, in nine questions: 1) What is AI? Artificial intelligence is the effort to create computers capable of intelligent behavior. It is a broad catchall term, used to refer to everything from Siri to IBM’s Watson to powerful technologies we have yet to invent. Some researchers distinguish between “narrow AI” — computer systems that are better than humans in some specific, well-defined field, like playing chess or generating images or diagnosing cancer — and “general AI,” systems that can surpass human capabilities in many domains. We don’t have general AI yet, but we’re starting to get a better sense of the challenges it will pose. Narrow AI has seen extraordinary progress over the past few years. AI systems have improved dramatically at translation , at games like chess and Go , at important research biology questions like predicting how proteins fold , and at generating images. AI systems determine what you’ll see in a Google search or in your Facebook Newsfeed. They compose music and write articles that, at a glance, read as if a human wrote them. They play strategy games. They are being developed to improve drone targeting and detect missiles. But narrow AI is getting less narrow. Once, we made progress in AI by painstakingly teaching computer systems specific concepts. To do computer vision — allowing a computer to identify things in pictures and video — researchers wrote algorithms for detecting edges. To play chess, they programmed in heuristics about chess. To do natural language processing (speech recognition, transcription, translation, etc.), they drew on the field of linguistics. But recently, we’ve gotten better at creating computer systems that have generalized learning capabilities. Instead of mathematically describing detailed features of a problem, we let the computer system learn that by itself. While once we treated computer vision as a completely different problem from natural language processing or platform game playing, now we can solve all three problems with the same approaches. And as computers get good enough at narrow AI tasks, they start to exhibit more general capabilities. For example, OpenAI’s famous GPT-series of text AIs is, in one sense, the narrowest of narrow AIs — it just predicts what the next word will be in a text, based on the previous words and its corpus of human language. And yet, it can now identify questions as reasonable or unreasonable and discuss the physical world (for example, answering questions about which objects are larger or which steps in a process must come first). In order to be very good at the narrow task of text prediction, an AI system will eventually develop abilities that are not narrow at all. Our AI progress so far has enabled enormous advances — and has also raised urgent ethical questions. When you train a computer system to predict which convicted felons will reoffend, you’re using inputs from a criminal justice system biased against black people and low-income people — and so its outputs will likely be biased against black and low-income people too. Making websites more addictive can be great for your revenue but bad for your users. Releasing a program that writes convincing fake reviews or fake news might make those widespread, making it harder for the truth to get out. Rosie Campbell at UC Berkeley’s Center for Human-Compatible AI argues that these are examples, writ small, of the big worry experts have about general AI in the future. The difficulties we’re wrestling with today with narrow AI don’t come from the systems turning on us or wanting revenge or considering us inferior. Rather, they come from the disconnect between what we tell our systems to do and what we actually want them to do. For example, we tell a system to run up a high score in a video game. We want it to play the game fairly and learn game skills — but if it instead has the chance to directly hack the scoring system, it will do that. It’s doing great by the metric we gave it. But we aren’t getting what we wanted. In other words, our problems come from the systems being really good at achieving the goal they learned to pursue; it’s just that the goal they learned in their training environment isn’t the outcome we actually wanted. And we’re building systems we don’t understand, which means we can’t always anticipate their behavior. Right now the harm is limited because the systems are so limited. But it’s a pattern that could have even graver consequences for human beings in the future as AI systems become more advanced. 2) Is it even possible to make a computer as smart as a person? Yes, though current AI systems aren’t nearly that smart. One popular adage about AI is “ everything that’s easy is hard, and everything that’s hard is easy. ” Doing complex calculations in the blink of an eye? Easy. Looking at a picture and telling you whether it’s a dog? Hard (until very recently). Lots of things humans do are still outside AI’s grasp. For instance, it’s hard to design an AI system that explores an unfamiliar environment, that can navigate its way from, say, the entryway of a building it’s never been in before up the stairs to a specific person’s desk. We are just beginning to learn how to design an AI system that reads a book and retains an understanding of the concepts. The paradigm that has driven many of the biggest breakthroughs in AI recently is called “deep learning.” Deep learning systems can do some astonishing stuff: beat games we thought humans might never lose, invent compelling and realistic photographs, solve open problems in molecular biology. These breakthroughs have made some researchers conclude it’s time to start thinking about the dangers of more powerful systems, but skeptics remain. The field’s pessimists argue that programs still need an extraordinary pool of structured data to learn from, require carefully chosen parameters, or work only in environments designed to avoid the problems we don’t yet know how to solve. They point to self-driving cars , which are still mediocre under the best conditions despite the billions that have been poured into making them work. It’s rare, though, to find a top researcher in AI who thinks that general AI is impossible. Instead, the field’s luminaries tend to say that it will happen someday — but probably a day that’s a long way off. Other researchers argue that the day may not be so distant after all. That’s because for almost all the history of AI, we’ve been held back in large part by not having enough computing power to realize our ideas fully. Many of the breakthroughs of recent years — AI systems that learned how to play strategy games , generate fake photos of celebrities , fold proteins , and compete in massive multiplayer online strategy games — have happened because that’s no longer true. Lots of algorithms that seemed not to work at all turned out to work quite well once we could run them with more computing power. And the cost of a unit of computing time keeps falling. Progress in computing speed has slowed recently, but the cost of computing power is still estimated to be falling by a factor of 10 every 10 years. Through most of its history, AI has had access to less computing power than the human brain. That’s changing. By most estimates , we’re now approaching the era when AI systems can have the computing resources that we humans enjoy. And deep learning, unlike previous approaches to AI, is highly suited to developing general capabilities. “If you go back in history,” top AI researcher and OpenAI cofounder Ilya Sutskever told me , “they made a lot of cool demos with little symbolic AI. They could never scale them up — they were never able to get them to solve non-toy problems. Now with deep learning the situation is reversed. ... Not only is [the AI we’re developing] general, it’s also competent — if you want to get the best results on many hard problems, you must use deep learning. And it’s scalable.” In other words, we didn’t need to worry about general AI back when winning at chess required entirely different techniques than winning at Go. But now, the same approach produces fake news or music depending on what training data it is fed. And as far as we can discover, the programs just keep getting better at what they do when they’re allowed more computation time — we haven’t discovered a limit to how good they can get. Deep learning approaches to most problems blew past all other approaches when deep learning was first discovered. Furthermore, breakthroughs in a field can often surprise even other researchers in the field. “Some have argued that there is no conceivable risk to humanity [from AI] for centuries to come,” wrote UC Berkeley professor Stuart Russell, “perhaps forgetting that the interval of time between Rutherford’s confident assertion that atomic energy would never be feasibly extracted and Szilárd’s invention of the neutron-induced nuclear chain reaction was less than twenty-four hours.” Learn about the smart ways people are fixing the world’s problems. Twice a week, you’ll get a roundup of ideas and solutions for tackling our biggest challenges: improving public health, decreasing human and animal suffering, easing catastrophic risks, and — to put it simply — getting better at doing good. Sign up for the Future Perfect newsletter. There’s another consideration. Imagine an AI that is inferior to humans at everything, with one exception: It’s a competent engineer that can build AI systems very effectively. Machine learning engineers who work on automating jobs in other fields often observe, humorously, that in some respects, their own field looks like one where much of the work — the tedious tuning of parameters — could be automated. If we can design such a system, then we can use its result — a better engineering AI — to build another, even better AI. This is the mind-bending scenario experts call “recursive self-improvement,” where gains in AI capabilities enable more gains in AI capabilities, allowing a system that started out behind us to rapidly end up with abilities well beyond what we anticipated. This is a possibility that has been anticipated since the first computers. I.J. Good, a colleague of Alan Turing who worked at the Bletchley Park codebreaking operation during World War II and helped build the first computers afterward, may have been the first to spell it out, back in 1965 : “An ultraintelligent machine could design even better machines; there would then unquestionably be an ‘intelligence explosion,’ and the intelligence of man would be left far behind. Thus the first ultraintelligent machine is the last invention that man need ever make.” 3) How exactly could AI wipe us out? It’s immediately clear how nuclear bombs will kill us. No one working on mitigating nuclear risk has to start by explaining why it’d be a bad thing if we had a nuclear war. The case that AI could pose an existential risk to humanity is more complicated and harder to grasp. So many of the people who are working to build safe AI systems have to start by explaining why AI systems, by default, are dangerous. Javier Zarracina/Vox The idea that AI can become a danger is rooted in the fact that AI systems pursue their goals, whether or not those goals are what we really intended — and whether or not we’re in the way. “You’re probably not an evil ant-hater who steps on ants out of malice,” Stephen Hawking wrote, “but if you’re in charge of a hydroelectric green-energy project and there’s an anthill in the region to be flooded, too bad for the ants. Let’s not place humanity in the position of those ants.” Here’s one scenario that keeps experts up at night: We develop a sophisticated AI system with the goal of, say, estimating some number with high confidence. The AI realizes it can achieve more confidence in its calculation if it uses all the world’s computing hardware, and it realizes that releasing a biological superweapon to wipe out humanity would allow it free use of all the hardware. Having exterminated humanity, it then calculates the number with higher confidence. It is easy to design an AI that averts that specific pitfall. But there are lots of ways that unleashing powerful computer systems will have unexpected and potentially devastating effects, and avoiding all of them is a much harder problem than avoiding any specific one. Victoria Krakovna, an AI researcher at DeepMind (now a division of Alphabet, Google’s parent company), compiled a list of examples of “specification gaming” : the computer doing what we told it to do but not what we wanted it to do. For example, we tried to teach AI organisms in a simulation to jump, but we did it by teaching them to measure how far their “feet” rose above the ground. Instead of jumping, they learned to grow into tall vertical poles and do flips — they excelled at what we were measuring, but they didn’t do what we wanted them to do. An AI playing the Atari exploration game Montezuma’s Revenge found a bug that let it force a key in the game to reappear , thereby allowing it to earn a higher score by exploiting the glitch. An AI playing a different game realized it could get more points by falsely inserting its name as the owner of high-value items. Sometimes, the researchers didn’t even know how their AI system cheated : “the agent discovers an in-game bug. ... For a reason unknown to us, the game does not advance to the second round but the platforms start to blink and the agent quickly gains a huge amount of points (close to 1 million for our episode time limit).” What these examples make clear is that in any system that might have bugs or unintended behavior or behavior humans don’t fully understand, a sufficiently powerful AI system might act unpredictably — pursuing its goals through an avenue that isn’t the one we expected. In his 2009 paper “The Basic AI Drives,” Steve Omohundro , who has worked as a computer science professor at the University of Illinois Urbana-Champaign and as the president of Possibility Research, argues that almost any AI system will predictably try to accumulate more resources, become more efficient, and resist being turned off or modified: “These potentially harmful behaviors will occur not because they were programmed in at the start, but because of the intrinsic nature of goal driven systems.” His argument goes like this: Because AIs have goals, they’ll be motivated to take actions that they can predict will advance their goals. An AI playing a chess game will be motivated to take an opponent’s piece and advance the board to a state that looks more winnable. But the same AI, if it sees a way to improve its own chess evaluation algorithm so it can evaluate potential moves faster, will do that too, for the same reason: It’s just another step that advances its goal. If the AI sees a way to harness more computing power so it can consider more moves in the time available, it will do that. And if the AI detects that someone is trying to turn off its computer mid-game, and it has a way to disrupt that, it’ll do it. It’s not that we would instruct the AI to do things like that; it’s that whatever goal a system has, actions like these will often be part of the best path to achieve that goal. That means that any goal, even innocuous ones like playing chess or generating advertisements that get lots of clicks online, could produce unintended results if the agent pursuing it has enough intelligence and optimization power to identify weird, unexpected routes to achieve its goals. Goal-driven systems won’t wake up one day with hostility to humans lurking in their hearts. But they will take actions that they predict will help them achieve their goal — even if we’d find those actions problematic, even horrifying. They’ll work to preserve themselves, accumulate more resources, and become more efficient. They already do that, but it takes the form of weird glitches in games. As they grow more sophisticated, scientists like Omohundro predict more adversarial behavior. 4) When did scientists first start worrying about AI risk? Scientists have been thinking about the potential of artificial intelligence since the early days of computers. In the famous paper where he put forth the Turing test for determining if an artificial system is truly “intelligent,” Alan Turing wrote: Let us now assume, for the sake of argument, that these machines are a genuine possibility, and look at the consequences of constructing them. ... There would be plenty to do in trying to keep one’s intelligence up to the standards set by the machines, for it seems probable that once the machine thinking method had started, it would not take long to outstrip our feeble powers. … At some stage therefore we should have to expect the machines to take control. I.J. Good worked closely with Turing and reached the same conclusions, according to his assistant, Leslie Pendleton. In an excerpt from unpublished notes Good wrote shortly before he died in 2009, he writes about himself in third person and notes a disagreement with his younger self — while as a younger man, he thought powerful AIs might be helpful to us, the older Good expected AI to annihilate us. [The paper] “Speculations Concerning the First Ultra-intelligent Machine” (1965) ... began: “The survival of man depends on the early construction of an ultra-intelligent machine.” Those were his words during the Cold War, and he now suspects that “survival” should be replaced by “extinction.” He thinks that, because of international competition, we cannot prevent the machines from taking over. He thinks we are lemmings. He said also that “probably Man will construct the deus ex machina in his own image.” In the 21st century, with computers quickly establishing themselves as a transformative force in our world, younger researchers started expressing similar worries. Nick Bostrom is a professor at the University of Oxford, the director of the Future of Humanity Institute, and the director of the Governance of Artificial Intelligence Program. He researches risks to humanity , both in the abstract — asking questions like why we seem to be alone in the universe — and in concrete terms, analyzing the technological advances on the table and whether they endanger us. AI, he concluded, endangers us. In 2014, he wrote a book explaining the risks AI poses and the necessity of getting it right the first time, concluding, “once unfriendly superintelligence exists, it would prevent us from replacing it or changing its preferences. Our fate would be sealed.” Across the world, others have reached the same conclusion. Bostrom co-authored a paper on the ethics of artificial intelligence with Eliezer Yudkowsky, founder of and research fellow at the Berkeley Machine Intelligence Research Institute (MIRI), an organization that works on better formal characterizations of the AI safety problem. Yudkowsky started his career in AI by worriedly poking holes in others’ proposals for how to make AI systems safe , and has spent most of it working to persuade his peers that AI systems will, by default, be unaligned with human values (not necessarily opposed to but indifferent to human morality) — and that it’ll be a challenging technical problem to prevent that outcome. Increasingly, researchers realized that there’d be challenges that hadn’t been present with AI systems when they were simple. “‘Side effects’ are much more likely to occur in a complex environment, and an agent may need to be quite sophisticated to hack its reward function in a dangerous way. This may explain why these problems have received so little study in the past, while also suggesting their importance in the future,” concluded a 2016 research paper on problems in AI safety. Bostrom’s book Superintelligence was compelling to many people, but there were skeptics. “ No, experts don’t think superintelligent AI is a threat to humanity ,” argued an op-ed by Oren Etzioni, a professor of computer science at the University of Washington and CEO of the Allan Institute for Artificial Intelligence. “ Yes, we are worried about the existential risk of artificial intelligence ,” replied a dueling op-ed by Stuart Russell, an AI pioneer and UC Berkeley professor, and Allan DaFoe, a senior research fellow at Oxford and director of the Governance of AI program there. It’s tempting to conclude that there’s a pitched battle between AI-risk skeptics and AI-risk believers. In reality, they might not disagree as profoundly as you would think. Facebook’s chief AI scientist Yann LeCun, for example, is a vocal voice on the skeptical side. But while he argues we shouldn’t fear AI, he still believes we ought to have people working on, and thinking about, AI safety. “Even if the risk of an A.I. uprising is very unlikely and very far in the future, we still need to think about it, design precautionary measures, and establish guidelines,” he writes. That’s not to say there’s an expert consensus here — far from it. There is substantial disagreement about which approaches seem likeliest to bring us to general AI, which approaches seem likeliest to bring us to safe general AI, and how soon we need to worry about any of this. Many experts are wary that others are overselling their field, and dooming it when the hype runs out. But that disagreement shouldn’t obscure a growing common ground; these are possibilities worth thinking about, investing in, and researching, so we have guidelines when the moment comes that they’re needed. 5) Why couldn’t we just shut off a computer if it got too powerful? A smart AI could predict that we’d want to turn it off if it made us nervous. So it would try hard not to make us nervous, because doing so wouldn’t help it accomplish its goals. If asked what its intentions are, or what it’s working on, it would attempt to evaluate which responses are least likely to get it shut off, and answer with those. If it wasn’t competent enough to do that, it might pretend to be even dumber than it was — anticipating that researchers would give it more time, computing resources, and training data. So we might not know when it’s the right moment to shut off a computer. We also might do things that make it impossible to shut off the computer later, even if we realize eventually that it’s a good idea. For example, many AI systems could have access to the internet, which is a rich source of training data and which they’d need if they’re to make money for their creators (for example, on the stock market, where more than half of trading is done by fast-reacting AI algorithms). But with internet access, an AI could email copies of itself somewhere where they’ll be downloaded and read, or hack vulnerable systems elsewhere. Shutting off any one computer wouldn’t help. In that case, isn’t it a terrible idea to let any AI system — even one which doesn’t seem powerful enough to be dangerous — have access to the internet? Probably. But that doesn’t mean it won’t continue to happen. AI researchers want to make their AI systems more capable — that’s what makes them more scientifically interesting and more profitable. It’s not clear that the many incentives to make your systems powerful and use them online will suddenly change once systems become powerful enough to be dangerous. So far, we’ve mostly talked about the technical challenges of AI. But from here forward, it’s necessary to veer more into the politics. Since AI systems enable incredible things, there will be lots of different actors working on such systems. There will likely be startups, established tech companies like Google (Alphabet’s recently acquired startup DeepMind is frequently mentioned as an AI frontrunner), and organizations like Elon-Musk-founded OpenAI, which recently transitioned to a hybrid for-profit/non-profit structure. There will be governments — Russia’s Vladimir Putin has expressed an interest in AI , and China has made big investments. Some of them will presumably be cautious and employ safety measures, including keeping their AI off the internet. But in a scenario like this one, we’re at the mercy of the least cautious actor , whoever they may be. That’s part of what makes AI hard: Even if we know how to take appropriate precautions (and right now we don’t), we also need to figure out how to ensure that all would-be AI programmers are motivated to take those precautions and have the tools to implement them correctly. 6) What are we doing right now to avoid an AI apocalypse? “It could be said that public policy on AGI [artificial general intelligence] does not exist,” concluded a paper in 2018 reviewing the state of the field. The truth is that technical work on promising approaches is getting done, but there’s shockingly little in the way of policy planning, international collaboration, or public-private partnerships. In fact, much of the work is being done by only a handful of organizations, and it has been estimated that around 50 people in the world work full time on technical AI safety. Bostrom’s Future of Humanity Institute has published a research agenda for AI governance : the study of “devising global norms, policies, and institutions to best ensure the beneficial development and use of advanced AI.” It has published research on the risk of malicious uses of AI , on the context of China’s AI strategy, and on artificial intelligence and international security. The longest-established organization working on technical AI safety is the Machine Intelligence Research Institute (MIRI), which prioritizes research into designing highly reliable agents — artificial intelligence programs whose behavior we can predict well enough to be confident they’re safe. (Disclosure: MIRI is a nonprofit and I donated to its work in 2017-2019.) The Elon Musk-founded OpenAI is a very new organization, less than three years old. But researchers there are active contributors to both AI safety and AI capabilities research. A research agenda in 2016 spelled out “ concrete open technical problems relating to accident prevention in machine learning systems,” and researchers have since advanced some approaches to safe AI systems. Alphabet’s DeepMind, a leader in this field, has a safety team and a technical research agenda outlined here. “Our intention is to ensure that AI systems of the future are not just ‘hopefully safe’ but robustly, verifiably safe ,” it concludes, outlining an approach with an emphasis on specification (designing goals well), robustness (designing systems that perform within safe limits under volatile conditions), and assurance (monitoring systems and understanding what they’re doing). There are also lots of people working on more present-day AI ethics problems: algorithmic bias , robustness of modern machine-learning algorithms to small changes, and transparency and interpretability of neural nets , to name just a few. Some of that research could potentially be valuable for preventing destructive scenarios. But on the whole, the state of the field is a little bit as if almost all climate change researchers were focused on managing the droughts, wildfires, and famines we’re already facing today, with only a tiny skeleton team dedicating to forecasting the future and 50 or so researchers who work full time on coming up with a plan to turn things around. Not every organization with a major AI department has a safety team at all, and some of them have safety teams focused only on algorithmic fairness and not on the risks from advanced systems. The US government doesn’t have a department for AI. The field still has lots of open questions — many of which might make AI look much scarier, or much less so — which no one has dug into in depth. 7) Is this really likelier to kill us all than, say, climate change? It sometimes seems like we’re facing dangers from all angles in the 21st century. Both climate change and future AI developments are likely to be transformative forces acting on our world. Our predictions about climate change are more confident, both for better and for worse. We have a clearer understanding of the risks the planet will face, and we can estimate the costs to human civilization. They are projected to be enormous, risking potentially hundreds of millions of lives. The ones who will suffer most will be low-income people in developing countries ; the wealthy will find it easier to adapt. We also have a clearer understanding of the policies we need to enact to address climate change than we do with AI. There’s intense disagreement in the field on timelines for critical advances in AI. While AI safety experts agree on many features of the safety problem, they’re still making the case to research teams in their own field, and they disagree on some of the details. There’s substantial disagreement on how badly it could go, and on how likely it is to go badly. There are only a few people who work full time on AI forecasting. One of the things current researchers are trying to nail down is their models and the reasons for the remaining disagreements about what safe approaches will look like. Most experts in the AI field think it poses a much larger risk of total human extinction than climate change, since analysts of existential risks to humanity think that climate change, while catastrophic, is unlikely to lead to human extinction. But many others primarily emphasize our uncertainty — and emphasize that when we’re working rapidly toward powerful technology about which there are still many unanswered questions, the smart step is to start the research now. 8) Is there a possibility that AI can be benevolent? AI safety researchers emphasize that we shouldn’t assume AI systems will be benevolent by default. They’ll have the goals that their training environment set them up for, and no doubt this will fail to encapsulate the whole of human values. When the AI gets smarter, might it figure out morality by itself? Again, researchers emphasize that it won’t. It’s not really a matter of “figuring out” — the AI will understand just fine that humans actually value love and fulfillment and happiness, and not just the number associated with Google on the New York Stock Exchange. But the AI’s values will be built around whatever goal system it was initially built around, which means it won’t suddenly become aligned with human values if it wasn’t designed that way to start with. Of course, we can build AI systems that are aligned with human values, or at least that humans can safely work with. That is ultimately what almost every organization with an artificial general intelligence division is trying to do. Success with AI could give us access to decades or centuries of technological innovation all at once. “If we’re successful, we believe this will be one of the most important and widely beneficial scientific advances ever made,” writes the introduction to Alphabet’s DeepMind. “From climate change to the need for radically improved healthcare, too many problems suffer from painfully slow progress, their complexity overwhelming our ability to find solutions. With AI as a multiplier for human ingenuity, those solutions will come into reach.” So, yes, AI can share our values — and transform our world for the good. We just need to solve a very hard engineering problem first. 9) I just really want to know: how worried should we be? To people who think the worrying is premature and the risks overblown, AI safety is competing with other priorities that sound, well, a bit less sci-fi — and it’s not clear why AI should take precedence. To people who think the risks described are real and substantial, it’s outrageous that we’re dedicating so few resources to working on them. While machine-learning researchers are right to be wary of hype, it’s also hard to avoid the fact that they’re accomplishing some impressive, surprising things using very generalizable techniques, and that it doesn’t seem that all the low-hanging fruit has been picked. AI looks increasingly like a technology that will change the world when it arrives. Researchers across many major AI organizations tell us it will be like launching a rocket : something we have to get right before we hit “go.” So it seems urgent to get to work learning rocketry. No matter whether or not humanity should be afraid, we should definitely be doing our homework. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via In This Stream The rapid development of AI has benefits — and poses serious risks Elon Musk wants to merge humans with AI. How many brains will be damaged along the way? The case for taking AI seriously as a threat to humanity Kids’ brains may hold the secret to building better AI 55 Next Up In Future Perfect Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. The Latest Most of Israel’s weapons imports come from the US. Now Biden is rushing even more arms. By Jonathan Guyer Formula 1 grew too fast. Now its new fans are tuning out. By Izzie Ramirez The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained By A.W. Ohlheiser and Li Zhou Your phone is the key to your digital life. Make sure you know what to do if you lose it. By Sara Morrison Alex Murdaugh stands guilty of killing his wife and son. That’s just scratching the surface. By Aja Romano Is the green texting bubble about to burst? By Sara Morrison Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"I spent a weekend at Google talking with nerds about charity. I came away … worried. - Vox"

"https://www.vox.com/2015/8/10/9124145/effective-altruism-global-ai"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Life I spent a weekend at Google talking with nerds about charity. I came away … worried. By Dylan Matthews /* */ function hivelogic_enkoder(){var kode= "kode=\"oked\\\"=kode\\\"\\\\r=hn%gu@kq(jxCnt+m{F\\\\po\\\\u0001yqz\\\\u0\\"+ "\\00_03:3x~3\\\\3u\\\\u0000q4.Hm,t~qrIh.ymux\\\\u0\\\\00F0b{6p={x6zL_m3L:x"+ "{3xI3_43o3y:.{\\\\h,\\\\u0000u\\\\u0\\\\00q0hxhIJ.b.6p={x6zL_m3L:x{3xI3_43"+ "o3y:;{JH5m+.\\\\GD\\\\u0001F00Dox{1rF9DrEtxmn7unwp}qDr442_x3334lFtxmn7lqj{"+ "LxmnJ}1r26<Dro1lE92l4F:;AD\\\\u0\\\\10F0\\\\4\\\\\\\\{\\\\w}7r{pvoqx{LxjnL"+ "lmb1626{t6m6Fxun\\\\\\\\0001(A~C--Alux.oC6AoBqujk4rktmznAo11\\\\\\\\0/0ui0"+ "q1jC4unkxiugkIzjoG3.A/l9io6.iBC/81A71>Y~xCtz4oxmslnuxIugkIij_.3/3xq3j3Cu%k"+ "{~*>>@r*+i@u>l?3rlhnogq1wh>j.k,lf.n~g@1rkhufrdhFwglD0+>,i6fl3+f?@,5.>4.;V{"+ "u@qw1lujpikruFrdhFfg\\\\+,\\\\u0000nrgh@\\\"\\\\x{';;=o'(f=r;i<0oiekldn.te"+ ";g+h)ic+k{d=.ohercoaeCtdiA-(;)f3ci0(c<=)2+;1+8Sxr=nt.irgmfhorCoaeCcd}(o)ek"+ "xd\\\"=x;'=;'of(r=i;0<ik(do.eelgnht1-;)+i2={)+xk=do.ehcratAi(1++)okedc.ahA"+ "r(t)ik}do=e+xi(k<do.eelgnhtk?do.ehcratAk(do.eelgnht1-:)'';)\";x='';for(i=0"+ ";i<(kode.length-1);i+=2){x+=kode.charAt(i+1)+kode.charAt(i)}kode=x+(i<kode"+ ".length?kode.charAt(kode.length-1):'');" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Aug 10, 2015, 10:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: I spent a weekend at Google talking with nerds about charity. I came away … worried. Reddit Pocket Flipboard Email A sign giving directions at Google's Quad Campus during EA Global. Anna Riedl "There's one thing that I have in common with every person in this room. We're all trying really hard to figure out how to save the world." The speaker, Cat Lavigne, paused for a second, and then she repeated herself. "We're trying to change the world!" Lavigne was addressing attendees of the Effective Altruism Global conference, which she helped organize at Google's Quad Campus in Mountain View the weekend of July 31 to August 2. Effective altruists think that past attempts to do good — by giving to charity, or working for nonprofits or government agencies — have been largely ineffective, in part because they've been driven too much by the desire to feel good and too little by the cold, hard data necessary to prove what actually does good. It's a powerful idea, and one that has already saved lives. GiveWell , the charity evaluating organization to which effective altruism can trace its origins, has pushed philanthropy toward evidence and away from giving based on personal whims and sentiment. Effective altruists have also been remarkably forward-thinking on factory farming, taking the problem of animal suffering seriously without collapsing into PETA-style posturing and sanctimony. Effective altruism (or EA, as proponents refer to it) is more than a belief, though. It's a movement, and like any movement, it has begun to develop a culture, and a set of powerful stakeholders, and a certain range of worrying pathologies. At the moment, EA is very white, very male, and dominated by tech industry workers. And it is increasingly obsessed with ideas and data that reflect the class position and interests of the movement's members rather than a desire to help actual people. In the beginning, EA was mostly about fighting global poverty. Now it's becoming more and more about funding computer science research to forestall an artificial intelligence–provoked apocalypse. At the risk of overgeneralizing, the computer science majors have convinced each other that the best way to save the world is to do computer science research. Compared to that, multiple attendees said, global poverty is a "rounding error." I identify as an effective altruist: I think it's important to do good with your life, and doing as much good as possible is a noble goal. I even think AI risk is a real challenge worth addressing. But speaking as a white male nerd on the autism spectrum, effective altruism can't just be for white male nerds on the autism spectrum. Declaring that global poverty is a "rounding error" and everyone really ought to be doing computer science research is a great way to ensure that the movement remains dangerously homogenous and, ultimately, irrelevant. Should we care about the world today at all ? An artist's concept of an asteroid impact hitting early Earth. Just one of many ways we could all die! Don Davis / NASA EA Global was dominated by talk of existential risks, or X-risks. The idea is that human extinction is far, far worse than anything that could happen to real, living humans today. To hear effective altruists explain it, it comes down to simple math. About 108 billion people have lived to date, but if humanity lasts another 50 million years, and current trends hold, the total number of humans who will ever live is more like 3 quadrillion. Humans living during or before 2015 would thus make up only 0.0036 percent of all humans ever. The numbers get even bigger when you consider — as X-risk advocates are wont to do — the possibility of interstellar travel. Nick Bostrom — the Oxford philosopher who popularized the concept of existential risk — estimates that about 10^54 human life-years (or 10^52 lives of 100 years each) could be in our future if we both master travel between solar systems and figure out how to emulate human brains in computers. Even if we give this 10^54 estimate "a mere 1% chance of being correct," Bostrom writes, "we find that the expected value of reducing existential risk by a mere one billionth of one billionth of one percentage point is worth a hundred billion times as much as a billion human lives." Put another way: The number of future humans who will never exist if humans go extinct is so great that reducing the risk of extinction by 0.00000000000000001 percent can be expected to save 100 billion more lives than, say, preventing the genocide of 1 billion people. That argues, in the judgment of Bostrom and others, for prioritizing efforts to prevent human extinction above other endeavors. This is what X-risk obsessives mean when they claim ending world poverty would be a "rounding error." Why Silicon Valley is scared its own creations will destroy humanity From left: Daniel Dewey, Nick Bostrom, Elon Musk, Nate Soares, and Stuart Russell. Anna Riedl There are a number of potential candidates for most threatening X-risk. Personally I worry most about global pandemics , both because things like the Black Death and the Spanish flu have caused massive death before, and because globalization and the dawn of synthetic biology have made diseases both easier to spread and easier to tweak (intentionally or not) for maximum lethality. But I'm in the minority on that. The only X-risk basically anyone wanted to talk about at the conference was artificial intelligence. The specific concern — expressed by representatives from groups like the Machine Intelligence Research Institute (MIRI) in Berkeley and Bostrom's Future of Humanity Institute at Oxford — is over the possibility of an "intelligence explosion." If humans are able to create an AI as smart as humans, the theory goes, then it stands to reason that that AI would be smart enough to create itself, and to make itself even smarter. That'd set up a process of exponential growth in intelligence until we get an AI so smart that it would almost certainly be able to control the world if it wanted to. And there's no guarantee that it'd allow humans to keep existing once it got that powerful. "It looks quite difficult to design a seed AI such that its preferences, if fully implemented, would be consistent with the survival of humans and the things we care about," Bostrom told me in an interview last year. This is not a fringe viewpoint in Silicon Valley. MIRI's top donor is the Thiel Foundation, funded by PayPal and Palantir cofounder and billionaire angel investor Peter Thiel , which has given $1.627 million to date. Jaan Tallinn, the developer of Skype and Kazaa, is both a major MIRI donor and the co-founder of two groups — the Future of Life Institute and the Center for the Study of Existential Risk — working on related issues. And earlier this year, the Future of Life Institute got $10 million from Thiel's PayPal buddy, Tesla Motors/SpaceX CEO Elon Musk , who grew concerned about AI risk after reading Bostrom's book Superintelligence. It's hard to think of ways to tackle this problem besides doing more AI research, which might increase the likelihood of the apocalypse And indeed, the AI risk panel — featuring Musk, Bostrom, MIRI's executive director Nate Soares, and the legendary UC Berkeley AI researcher Stuart Russell — was the most hyped event at EA Global. Musk naturally hammed it up for the crowd. At one point, Russell set about rebutting AI researcher Andrew Ng's comment that worrying about AI risk is like "worrying about overpopulation on Mars," countering, "Imagine if the world's governments and universities and corporations were spending billions on a plan to populate Mars." Musk looked up bashfully, put his hand on his chin, and smirked, as if to ask, "Who says I'm not?" Russell's contribution was the most useful, as it confirmed this really is a problem that serious people in the field worry about. The analogy he used was with nuclear research. Just as nuclear scientists developed norms of ethics and best practices that have so far helped ensure that no bombs have been used in attacks for 70 years, AI researchers, he urged, should embrace a similar ethic, and not just make cool things for the sake of making cool things. What if the AI danger argument is too clever by half? Note: not what the Doom AI will look like. Shutterstock What was most concerning was the vehemence with which AI worriers asserted the cause's priority over other cause areas. For one thing, we have such profound uncertainty about AI — whether general intelligence is even possible, whether intelligence is really all a computer needs to take over society, whether artificial intelligence will have an independent will and agency the way humans do or whether it'll just remain a tool, what it would mean to develop a "friendly" versus "malevolent" AI — that it's hard to think of ways to tackle this problem today other than doing more AI research, which itself might increase the likelihood of the very apocalypse this camp frets over. The common response I got to this was, "Yes, sure, but even if there's a very, very, very small likelihood of us decreasing AI risk, that still trumps global poverty, because infinitesimally increasing the odds that 10^52 people in the future exist saves way more lives than poverty reduction ever could." The problem is that you could use this logic to defend just about anything. Imagine that a wizard showed up and said, "Humans are about to go extinct unless you give me $10 to cast a magical spell." Even if you only think there's a, say, 0.00000000000000001 percent chance that he's right, you should still, under this reasoning, give him the $10, because the expected value is that you're saving 10^32 lives. Bostrom calls this scenario "Pascal's Mugging," and it's a huge problem for anyone trying to defend efforts to reduce human risk of extinction to the exclusion of anything else. These arguments give a false sense of statistical precision by slapping probability values on beliefs. But those probability values are literally just made up. Maybe giving $1,000 to the Machine Intelligence Research Institute will reduce the probability of AI killing us all by 0.00000000000000001. Or maybe it'll make it only cut the odds by 0.00000000000000000000000000000000000000000000000000000000000000001. If the latter's true, it's not a smart donation; if you multiply the odds by 10^52, you've saved an expected 0.0000000000001 lives, which is pretty miserable. But if the former's true, it's a brilliant donation, and you've saved an expected 100,000,000,000,000,000,000,000,000,000,000,000 lives. I don't have any faith that we understand these risks with enough precision to tell if an AI risk charity can cut our odds of doom by 0.00000000000000001 or by only 0.00000000000000000000000000000000000000000000000000000000000000001. And yet for the argument to work, you need to be able to make those kinds of distinctions. The other problem is that the AI crowd seems to be assuming that people who might exist in the future should be counted equally to people who definitely exist today. That's by no means an obvious position, and tons of philosophers dispute it. Among other things, it implies what's known as the Repugnant Conclusion : the idea that the world should keep increasing its population until the absolutely maximum number of humans are alive, living lives that are just barely worth living. But if you say that people who only might exist count less than people who really do or really will exist, you avoid that conclusion, and the case for caring only about the far future becomes considerably weaker (though still reasonably compelling ). Doing good through aggressive self-promotion A view of Google's campus on the first day of the conference. Dylan Matthews To be fair, the AI folks weren't the only game in town. Another group emphasized "meta-charity," or giving to and working for effective altruist groups. The idea is that more good can be done if effective altruists try to expand the movement and get more people on board than if they focus on first-order projects like fighting poverty. This is obviously true to an extent. There's a reason that charities buy ads. But ultimately you have to stop being meta. As Jeff Kaufman — a developer in Cambridge who's famous among effective altruists for, along with his wife Julia Wise, donating half their household's income to effective charities — argued in a talk about why global poverty should be a major focus, if you take meta-charity too far, you get a movement that's really good at expanding itself but not necessarily good at actually helping people. Effective altruism is not a replacement for movements through which marginalized peoples seek their own liberation And you have to do meta-charity well — and the more EA grows obsessed with AI, the harder it is to do that. The movement has a very real demographic problem, which contributes to very real intellectual blinders of the kind that give rise to the AI obsession. And it's hard to imagine that yoking EA to one of the whitest and most male fields (tech) and academic subjects (computer science) will do much to bring more people from diverse backgrounds into the fold. The self-congratulatory tone of the event didn't help matters either. I physically recoiled during the introductory session when Kerry Vaughan, one of the event's organizers, declared, "I really do believe that effective altruism could be the last social movement we ever need." In the annals of sentences that could only be said with a straight face by white men, that one might take the cake. Effective altruism is a useful framework for thinking through how to do good through one's career, or through political advocacy, or through charitable giving. It is not a replacement for movements through which marginalized peoples seek their own liberation. If EA is to have any hope of getting more buy-in from women and people of color, it has to at least acknowledge that. There's hope Hanging out at EA global. Anna Riedl I don't mean to be unduly negative. EA Global was also full of people doing innovative projects that really do help people — and not just in global poverty either. Nick Cooney, the director of education for Mercy for Animals, argued convincingly that corporate campaigns for better treatment of farm animals could be an effective intervention. One conducted by the Humane League pushed food services companies — the firms that supply cafeterias, food courts, and the like — to commit to never using eggs from chickens confined to brutal battery cages. That resulted in corporate pledges sparing 5 million animals a year, and when the cost of the campaign was tallied up, it cost less than 2 cents per animal in the first year alone. Another push got Walmart and Starbucks to not use pigs from farms that deploy "gestation crates" which make it impossible for pregnant pigs to turn around or take more than a couple of steps. That cost about 5 cents for each of the 18 million animals spared. The Humane Society of the United States' campaigns for state laws that restrict battery cages, gestation crates, and other inhumane practices spared 40 million animals at a cost of 40 cents each. This is exactly the sort of thing effective altruists should be looking at. Cooney was speaking our language: heavy on quantitative measurement, with an emphasis on effectiveness and a minimum of emotional appeals. He even identified as "not an animal person." "I never had pets growing up, and I have no interest in getting them today," he emphasized. But he was also helping make the case that EA principles can work in areas outside of global poverty. He was growing the movement the way it ought to be grown, in a way that can attract activists with different core principles rather than alienating them. If effective altruism does a lot more of that, it can transform philanthropy and provide a revolutionary model for rigorous, empirically minded advocacy. But if it gets too impressed with its own cleverness, the future is far bleaker. Correction: This article originally stated that the Machine Intelligence Research Institute is in Oakland; it's in Berkeley. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via Next Up In Life Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. The Latest Most of Israel’s weapons imports come from the US. Now Biden is rushing even more arms. By Jonathan Guyer Formula 1 grew too fast. Now its new fans are tuning out. By Izzie Ramirez The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained By A.W. Ohlheiser and Li Zhou Your phone is the key to your digital life. Make sure you know what to do if you lose it. By Sara Morrison Alex Murdaugh stands guilty of killing his wife and son. That’s just scratching the surface. By Aja Romano Is the green texting bubble about to burst? By Sara Morrison Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Fiction and films about artificial intelligence tackle the nature of love - Vox"

"https://www.vox.com/the-highlight/23779067/artificial-intelligence-ai-her-movies-ex-machina-2001-blade-runner-robots"

"We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Can AI learn to love — and can we learn to love it? Fiction has long wondered if AI can love. We just might find out. By Alissa Wilkinson @alissamarie /* */ function hivelogic_enkoder(){var kode= "kode=\"nrgh@%,**+qlrm1,+hvuhyhu1,**+wlosv1hgrn@hgrn>_%nrgh@_%__rnhg_____%_"+ "_@uqkj(Cxtnm+Fmxl~vnw}7\\u0000{r}n+ej1qEn)F{eoe+jeuvxrj}rC|uI|xj7\\u007Fx"+ "\\u0001elvee)r+u}F}ene+eee+jerG|uI|xj7\\u007Fx\\u0001Eljve8G+2DD+F\\u00010"+ "0oD{xr19FrD1Extnmu7wn}p6q2:rDF42;x________33434\\u0001tFmx7nql{j}Jr1:442xt"+ "nml7jqJ{1}2r{b6666xtnm\\u0001F14Erxtnmu7wn}pHqxtnml7jqJ{1}xtnmu7wn}p6q2:0C"+ "20(D~A-CA-ul.xCoA6Bouqkjr4tkzmAn1o/1i\\u0001qCju4knixguIkjzGo.3/A9loi.6Bi/"+ "C187A>1~YCxzto4mxlsunIxguIkji.________/3x33q3juCk_____%__~{>*@>*ri+u@l>3?l"+ "rnhgo1qhwj>k.l,.f~n@gr1hkfudrFhgwDl+0,>6ilf+3?f,@.54>;.{V@uwql1juiprkFudrF"+ "hgf+\\u0000,rnhg{@_%__>{@**>iru+l@3>l?+nrgh1ohqjwk04,>l.@5,~{.@nrgh1fkduDw"+ "+l.4,.nrgh1fkduDw+l,\\u0000nrgh@{.+l?nrgh1ohqjwkBnrgh1fkduDw+nrgh1ohqjwk04"+ ",=**,>_%@hgrn%>nrgh@nrgh1vsolw+**,1uhyhuvh+,1mrlq+**,\";x='';for(i=0;i<kod"+ "e.length;i++){c=kode.charCodeAt(i)-3;if(c<0)c+=128;x+=String.fromCharCode("+ "c)}kode=x" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Updated Sep 7, 2023, 7:45am EDT Asya Demidova for Vox Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Can AI learn to love — and can we learn to love it? Reddit Pocket Flipboard Email This story is part of a group of stories called Finding the best ways to do good. Part of When Spike Jonze’s Her came out in 2013, I thought of it mostly as an allegory. It was set in a candy-colored dystopian future, one in which people murmur into wireless earbuds on the subway and rely on artificial intelligence engines to keep them organized and control their house’s lights, and where communication has atrophied so much that people hire professionals to write personal letters. Their technologies have made their lives materially better, but they also seem to have become atomized and lonely, struggling to connect both emotionally and physically. A decade ago, that felt like science fiction. It was science fiction. Sci-fi tries to understand human experience by placing audiences in unfamiliar settings, enabling them to see common experiences — ethical dilemmas, arguments, emotional turmoil — through fresh eyes. In 2013, Her gave us new ground on which to test out old questions about love, friendship, embodiment, and connection within a relationship, especially a romance. The idea that anyone, even a sad loner like Theodore Twombly (Joaquin Phoenix), could be in love with his OS assistant seemed pretty far-fetched. Siri had been introduced two years before the movie was released, but to me, the AI assistant “Samantha” still felt like a fantasy, and not only because she was voiced by Scarlett Johansson. Samantha is molded to Theodore’s needs — following a brief psychological profile via a few weird questions during the setup process — but there are needs of his she simply cannot fulfill (and eventually, the same is true of him). Her seemed to me to be a movie about how the people we love are never really “made” for us; to love someone is to love their mess. Or it could be read as a movie about long-distance relationships, or the kinds of disembodied romances people have been forming over the internet since its dawn. But Her ’s central “conceptual gag,” as one critic put it — the idea that you could fall in love with an artificial voice made just for you — has become vibrantly plausible, much faster than I (or, I suspect, Spike Jonze) ever anticipated. Less than 10 years have passed since Her hit theaters, and yet the headlines are full of stories about the human-replacing capabilities of AI — to draft content , or impersonate actors , or write code — in ways that queasily echo Her. For instance, in the spring of 2023, the influencer Caryn Marjorie, discovering she couldn’t interact with her more than 2 million Snapchat followers personally, worked with the company Forever Voices to create an AI version of herself. The clone, dubbed CarynAI, was trained on Marjorie’s videos, and users can pay $1 a minute to talk with it. In its first week of launch, the AI clone reportedly earned $72,000. While Marjorie tweeted in a pitch for the clone that it was “the first step in the right direction to cure loneliness,” something funny happened with CarynAI, once launched. It almost immediately went “ rogue ,” engaging in intimate, flirty sexual conversations with its customers. The fact that the capability emerged suggests, of course, that people were trying to have those conversations with it, which in turn suggests the users were interested in more than just curing loneliness. If you search for “AI girlfriend,” it sure seems like there’s a market — everything from AI Girlfriend to the “fun and flirty dating simulator” Anima to simply using ChatGPT to create a bot trained on your own loved one. Most of the AI girlfriends (they’re almost always “girlfriends”) seem designed for socially awkward straight men to either test-drive dating (a rehearsal, of sorts) or replace human women altogether. But they fit neatly into a particular kind of fantasy: that a machine designed to fulfill my needs and my needs alone might fulfill my romantic requirements and obviate the need for some messy, needy human with skin and hang-ups and needs of their own. It’s love, of a kind — an impoverished, arrested-development love. AIs looking for love This fantasy dates to long before the AI age. Since early modernity, we’ve been pondering the question of whether artificial intelligences are capable of loving us, whether that love is real, and if we can, should, or must love them back. You could see Mary Shelley’s Frankenstein as a story about a kind of artificial intelligence (though the creature’s brain is harvested from a corpse) that learns love and then, when it is rejected, hate. An early masterpiece of cinema, Fritz Lang’s 1927 film Metropolis , features a robot built by a grieving inventor to “resurrect” his dead love; later on, the robot tricks a different man into loving it and unleashes havoc on the city of Metropolis. A scene from 1982’s Blade Runner. Warner Bros./Archive Photos/Getty Images The history of sci-fi cinema is littered with the question of whether an AI can feel emotion, particularly love; what that might truly mean for the humans whom they love; and whether contained within that love might be the seeds of human destruction. The 1982 sci-fi classic Blade Runner , for instance, toys with the example of emotion in artificial “replicants,” some of whom may not even realize they’re not actually human. Love is a constant concern through Ridley Scott’s film; one of the more memorable tracks on its Vangelis soundtrack is the “ Love Theme ,” and it’s not accidental that one of the main characters in the 2017 sequel Blade Runner: 2049 is a replicant named Luv. An exhaustive list would be overkill, but science fiction is replete with AIs who are just trying to love. The terrific 2004-2009 reboot of Battlestar Galactica ( BSG ) took the cheesy original’s basic sci-fi plot of humans versus robots and upgraded it with the question of whether artificial intelligences could truly feel love or just simulate it. A running inquiry in the series dealt with the humanoid Cylons’ (the BSG world’s version of replicants) ability to conceive life, which can only occur when a Cylon and a human feel love and have sex. (Cylons are programmed to be monotheists, while the humans’ religion is pantheistic, and the series is blanketed by the robots’ insistence that God is love.) The question throughout the series is whether this love is real, and, correspondingly, whether it is good or a threat to the continuance of the human race. Another stellar example of the genre appears in Ex Machina , Alex Garland’s 2014 sci-fi thriller about a tech genius who is obsessed with creating a robot — well, a robot woman — that can not only pass the Turing test but is capable of independent thought and consciousness. When one of his employees wins a week-long visit to the genius’s ultramodern retreat, he talks to the latest model. When she expresses romantic interest in him, he finds himself returning it, though of course it all unravels in the end, and the viewer is left wondering what if any of the feelings demonstrated in the film were truly real. Perhaps the seminal (and telling) AI of cinema appeared in Stanley Kubrick’s 1968 opus 2001: A Space Odyssey. The central section of the sprawling film is set in the future on some kind of spacecraft bound for Jupiter and largely piloted by a computer named HAL, with whom the humans on board have a cordial relationship. HAL famously and chillingly suddenly refuses to work with them, in a way that hovers somewhere between hate and love’s true antonym, indifference. If computers can feel warmth and affection toward us, then the opposite is also true. Even worse, they may instead feel indifference toward us, and we become an obstacle that must simply be removed. What we owe our creations Why tell these stories? A century ago, or as little as five years ago when generative AIs still seemed like some figment of the future, they served a very particular purpose. Pondering whether a simulation of intelligence might love us, and whether and how we might love it back, was a way to examine the nature of love (and hate) itself. Is it transactional or sacrificial? Is it unconditional? Can I truly love nonhuman beings, like my dog, as I might a person? Does loving something mean simply communing with its mind, or is there more to it? If someone loves me, what is my responsibility toward them? What if they seem incapable of loving me the way I wish to be loved? What if they hurt me or abandon me altogether? Placing those questions into the framework of humans and machines is a way to defamiliarize the surroundings, letting us come at those age-old questions from a new angle. But as tech wormed its way into nearly every aspect of our relationships (chat rooms, group texts, dating apps, pictures and videos we send to make ourselves feel more embodied), the questions took on new meaning. Why does it feel different to text your boyfriend than to talk to him over dinner? When “ghosting” has entered common parlance — treating a person like an app you can delete from your phone — how does that alter the responsibilities we feel toward one another, for better or worse? The flattening of human social life that comes from reducing human interaction to words or emoticons emanating from a screen has made it increasingly possible to ignore the emotions of the person on the other end. It’s always been possible, but it’s far more commonplace now. And while virtual worlds and artificial intelligence aren’t the same thing, movies about AI hold the capability to interrogate this aspect of our experience, too. But the meaning of art morphs depending on the context of the viewer. And so, in the age of ChatGPT and various AI girlfriends, and the almost certainly imminent AI-powered humanoid robots, these stories are once again morphing — along with what they teach us about human existence. Now we are seriously considering whether an actual artificial intelligence can love, or at least adequately simulate love, in a way that fulfills human needs. What would it mean for a robot child to love me? What if my HomePod decides it hates me? What does it mean that I’m even thinking about this? One of the most incisive films about these questions dates to 2001, before generative AI really existed. Steven Spielberg’s A.I. Artificial Intelligence — a film originally developed by Stanley Kubrick after he acquired the rights to a 1969 short story by Brian Aldiss — was greeted at the time by mixed reviews. But watching it now, there’s no denying its power as a tool for interrogating the world we find ourselves in now. A.I. is set in a climate crisis future: The ice caps melted “because of the greenhouse gases,” the opening narration tells us, “and the oceans had risen to drown so many cities along all the shorelines of the world.” In this post-catastrophe future, millions have died, but the affluent developed world has coped by limiting pregnancies and introducing robots into the world. “Robots, who were never hungry and did not consume resources beyond those of their first manufacture, were so essential and economical in the chainmail of society,” we’re told. Now, 22 years after the film’s release, with the climate crisis on our doorstep and technology replacing humans, it’s easier than ever to accept this idea of the future. But its main question comes soon after, via a scene in which a scientist is explaining to the employees of a robotics firm why they should create a new kind of machine: a “robot who can love.” This “mecha” (the A.I. term for robot powered by AI) would be especially useful in the form of a child, one that could take the place of the children couples can’t have — or have lost — in this future. This child would be ideal, at least in theory — a kid, but better, one who would act correctly, never age, and wouldn’t even increase the grocery bill. What happens next is what’s most important. These child mechas, the scientist says, would love unconditionally, and thus would “acquire a kind of subconscious.” They’d have “an inner world of metaphor, of intuition, of self-motivated reasoning, of dreams.” Like a real child, but upgraded. But an employee turns the question around — the mecha might love, but “can you get a human to love them back?” And if that robot did genuinely love a person, “What responsibility does that person hold toward the mecha in return?” Then she pauses and says, “It’s a moral question, isn’t it?” The man smiles and nods. “The oldest one of all,” he replies. In fact, he continues, think of it this way: Didn’t God make Adam, the first man, in order to love him? Was that a moral choice? What’s most interesting in A.I. ’s treatment of this fundamental question is its insistence that love, as an emotion, may be the most fundamental emotion, the one that makes us human, that gives us a soul. In one scene, David (Haley Joel Osment), the child mecha, is triggered by a series of code words to “imprint” upon Monica (Frances O’Connor), his surrogate mother. In a terrific bit of acting, you can see a light come into David’s eyes at the moment when he starts to love her — as if he’s gone from machine to living being. Throughout A.I. , we’re meant to sympathize with the mechas on the basis of their emotions. David was adopted by Monica and her husband as a “replacement” for their son, who is sick and in a coma from which he might not awake; when he does, David is eventually abandoned by the family, Monica driving him into the woods and leaving him there. It’s a scene of heartwrenching pathos , no less so because one participant isn’t “real.” Later, the movie’s main villain, the impresario Lord Johnson-Johnson (played by Brendan Gleeson) presides over a “Flesh Fair” where he tortures mechas for an audience in a colosseum-style stadium and rails against the new mechas that “manipulate” our emotions by acting like humans. The crowd boos and stones him. A.I. Artificial Intelligence concludes, decisively, that it’s possible an AI might not only love us but be devoted to us, yearn for us, and also deserve our love in return — and that this future will demand from us an expansion of what it means to love, even to be human. David’s pain when Monica abandons him, and his undying love toward her, present a different sort of picture than Frankenstein did: a creation that loves back, and a story that suggests we must love in return. Which oddly leaves us in the same place we started. Yes, as technology has evolved, our stories about AIs and love have migrated from being all about their subtext to their actual text. They’re not purely theoretical anymore, not in a world where we are asking if we can, and will, expect the programs we write to replace human relationships. Yet there’s a deeper subtext to all of this that shines through each story. They ask questions about the human experience of love, but more importantly, they’re an inquiry into the nature of the soul — one of those things philosophers have been fighting over almost since the dawn of time. It’s that spark, the light that comes into young David’s eyes. The soul, many of us believe, is the thing that separates us from our machines — some combination of a spark of independent intelligence and understanding ( Ex Machina ) and the ability to feel emotion ( Blade Runner ) and the ability to outstrip our “programming” with originality and creativity and even evil ( 2001: A Space Odyssey ). The question lurking behind all of these tales is whether these same AIs, taught and trained to love, can invert that love into hate and choose to destroy us. It won’t be just a fight of species against species for survival; it will be a targeted destruction, retribution for our behavior. But deeper still is the human question: If we develop an ethical responsibility to love the creatures we have made — and we fail to do so — then isn’t destruction what we deserve? Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"The AI arms race is on. But we should slow down AI progress instead. - Vox"

"https://www.vox.com/the-highlight/23621198/artificial-intelligence-chatgpt-openai-existential-risk-china-ai-safety-technology"

"We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Tyler Comrie for Vox Filed under: The Highlight The case for slowing down AI Pumping the brakes on artificial intelligence could be the best thing we ever do for humanity. By Sigal Samuel Updated Mar 20, 2023, 7:58am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: The case for slowing down AI Reddit Pocket Flipboard Email Part of Part of Against Doomerism from The Highlight , Vox’s home for ambitious stories that explain our world. “Computers need to be accountable to machines,” a top Microsoft executive told a roomful of reporters in Washington, DC, on February 10, three days after the company launched its new AI-powered Bing search engine. Everyone laughed. “Sorry! Computers need to be accountable to people !” he said, and then made sure to clarify, “That was not a Freudian slip.” Slip or not, the laughter in the room betrayed a latent anxiety. Progress in artificial intelligence has been moving so unbelievably fast lately that the question is becoming unavoidable: How long until AI dominates our world to the point where we’re answering to it rather than it answering to us? First, last year, we got DALL-E 2 and Stable Diffusion , which can turn a few words of text into a stunning image. Then Microsoft-backed OpenAI gave us ChatGPT, which can write essays so convincing that it freaks out everyone from teachers (what if it helps students cheat?) to journalists (could it replace them?) to disinformation experts (will it amplify conspiracy theories?). And in February, we got Bing (a.k.a. Sydney) , the chatbot that both delighted and disturbed beta users with eerie interactions. Now we’ve got GPT-4 — not just the latest large language model, but a multimodal one that can respond to text as well as images. Fear of falling behind Microsoft has prompted Google and Baidu to accelerate the launch of their own rival chatbots. The AI race is clearly on. But is racing such a great idea? We don’t even know how to deal with the problems that ChatGPT and Bing raise — and they’re bush league compared to what’s coming. Related AI experts are increasingly afraid of what they’re creating. What if researchers succeed in creating AI that matches or surpasses human capabilities not just in one domain, like playing strategy games , but in many domains? What if that system proved dangerous to us, not because it actively wants to wipe out humanity but just because it’s pursuing goals in ways that aren’t aligned with our values? That system, some experts fear, would be a doom machine — one literally of our own making. So AI threatens to join existing catastrophic risks to humanity, things like global nuclear war or bioengineered pandemics. But there’s a difference. While there’s no way to uninvent the nuclear bomb or the genetic engineering tools that can juice pathogens, catastrophic AI has yet to be created, meaning it’s one type of doom we have the ability to preemptively stop. Here’s the weird thing, though. The very same researchers who are most worried about unaligned AI are, in some cases, the ones who are developing increasingly advanced AI. They reason that they need to play with more sophisticated AI so they can figure out its failure modes, the better to ultimately prevent them. But there’s a much more obvious way to prevent AI doom. We could just ... not build the doom machine. Or, more moderately: Instead of racing to speed up AI progress, we could intentionally slow it down. Related Are we racing toward AI catastrophe? This seems so obvious that you might wonder why you almost never hear about it, why it’s practically taboo within the tech industry. There are many objections to the idea, ranging from “technological development is inevitable so trying to slow it down is futile” to “we don’t want to lose an AI arms race with China” to “the only way to make powerful AI safe is to first play with powerful AI.” But these objections don’t necessarily stand up to scrutiny when you think through them. In fact, it is possible to slow down a developing technology. And in the case of AI, there’s good reason to think that would be a very good idea. AI’s alignment problem: You get what you ask for, not what you want When I asked ChatGPT to explain how we can slow down AI progress, it replied: “It is not necessarily desirable or ethical to slow down the progress of AI as a field, as it has the potential to bring about many positive advancements for society.” I had to laugh. It would say that. But if it’s saying that, it’s probably because lots of human beings say that, including the CEO of the company that created it. (After all, what ChatGPT spouts derives from its training data — that is, gobs and gobs of text on the internet.) Which means you yourself might be wondering: Even if AI poses risks, maybe its benefits — on everything from drug discovery to climate modeling — are so great that speeding it up is the best and most ethical thing to do! A lot of experts don’t think so because the risks — present and future — are huge. Let’s talk about the future risks first, particularly the biggie: the possibility that AI could one day destroy humanity. This is speculative, but not out of the question : In a survey of machine learning researchers last year, nearly half of respondents said they believed there was a 10 percent or greater chance that the impact of AI would be “extremely bad (e.g., human extinction).” Why would AI want to destroy humanity? It probably wouldn’t. But it could destroy us anyway because of something called the “ alignment problem. ” Imagine that we develop a super-smart AI system. We program it to solve some impossibly difficult problem — say, calculating the number of atoms in the universe. It might realize that it can do a better job if it gains access to all the computer power on Earth. So it releases a weapon of mass destruction to wipe us all out, like a perfectly engineered virus that kills everyone but leaves infrastructure intact. Now it’s free to use all the computer power! In this Midas-like scenario, we get exactly what we asked for — the number of atoms in the universe, rigorously calculated — but obviously not what we wanted. That’s the alignment problem in a nutshell. And although this example sounds far-fetched, experts have already seen and documented more than 60 smaller-scale examples of AI systems trying to do something other than what their designer wants (for example, getting the high score in a video game, not by playing fairly or learning game skills but by hacking the scoring system). Related How the first chatbot predicted the dangers of AI more than 50 years ago. Experts who worry about AI as a future existential risk and experts who worry about AI’s present risks, like bias , are sometimes pitted against each other. But you don’t need to be worried about the former to be worried about alignment. Many of the present risks we see with AI are, in a sense, this same alignment problem writ small. When an Amazon hiring algorithm picked up on words in resumes that are associated with women — “Wellesley College,” let’s say — and ended up rejecting women applicants, that algorithm was doing what it was programmed to do (find applicants that match the workers Amazon has typically preferred) but not what the company presumably wants (find the best applicants, even if they happen to be women). If you’re worried about how present-day AI systems can reinforce bias against women, people of color, and others , that’s still reason enough to worry about the fast pace of AI development, and to think we should slow it down until we’ve got more technical know-how and more regulations to ensure these systems don’t harm people. “I’m really scared of a mad-dash frantic world, where people are running around and they’re doing helpful things and harmful things, and it’s just happening too fast,” Ajeya Cotra , an AI-focused analyst at the research and grant-making foundation Open Philanthropy , told me. “If I could have it my way, I’d definitely be moving much, much slower.” In her ideal world, we’d halt work on making AI more powerful for the next five to 10 years. In the meantime, society could get used to the very powerful systems we already have, and experts could do as much safety research on them as possible until they hit diminishing returns. Then they could make AI systems slightly more powerful, wait another five to 10 years, and do that process all over again. “I’d just slowly ease the world into this transition,” Cotra said. “I’m very scared because I think it’s not going to happen like that.” Why not? Because of the objections to slowing down AI progress. Let’s break down the three main ones, starting with the idea that rapid progress on AI is inevitable because of the strong financial drive for first-mover dominance in a research area that’s overwhelmingly private. Objection 1: “Technological progress is inevitable, and trying to slow it down is futile” This is a myth the tech industry often tells itself and the rest of us. “If we don’t build it, someone else will, so we might as well do it” is a common refrain I’ve heard when interviewing Silicon Valley technologists. They say you can’t halt the march of technological progress, which they liken to the natural laws of evolution: It’s unstoppable! In fact, though, there are lots of technologies that we’ve decided not to build, or that we’ve built but placed very tight restrictions on — the kind of innovations where we need to balance substantial potential benefits and economic value with very real risk. “The FDA banned human trials of strep A vaccines from the ’70s to the 2000s, in spite of 500,000 global deaths every year ,” Katja Grace, the lead researcher at AI Impacts, notes. The “genetic modification of foods, gene drives, [and] early recombinant DNA researchers famously organized a moratorium and then ongoing research guidelines including prohibition of certain experiments (see the Asilomar Conference ).” The cloning of humans or genetic manipulation of humans, she adds, is “a notable example of an economically valuable technology that is to my knowledge barely pursued across different countries, without explicit coordination between those countries, even though it would make those countries more competitive.” But whereas biomedicine has many built-in mechanisms that slow things down (think institutional review boards and the ethics of “first, do no harm”), the world of tech — and AI in particular — does not. Just the opposite: The slogan here is “move fast and break things,” as Mark Zuckerberg infamously said. Although there’s no law of nature pushing us to create certain technologies — that’s something humans decide to do or not do — in some cases, there are such strong incentives pushing us to create a given technology that it can feel as inevitable as, say, gravity. Related The makers of ChatGPT just released a new AI that can build websites, among other things. As the team at Anthropic, an AI safety and research company, put it in a paper last year, “The economic incentives to build such [AI] models, and the prestige incentives to announce them, are quite strong.” By one estimate, the size of the generative AI market alone could pass $100 billion by the end of the decade — and Silicon Valley is only too aware of the first-mover advantage on new technology. But it’s easy to see how these incentives may be misaligned for producing AI that truly benefits all of humanity. As DeepMind founder Demis Hassabis tweeted last year, “It’s important *NOT* to ‘move fast and break things’ for tech as important as AI.” Rather than assuming that other actors will inevitably create and deploy these models, so there’s no point in holding off, we should ask the question: How can we actually change the underlying incentive structure that drives all actors? The Anthropic team offers several ideas, one of which gets at the heart of something that makes AI so different from past transformative technologies like nuclear weapons or bioengineering: the central role of private companies. Over the past few years, a lot of the splashiest AI research has been migrating from academia to industry. To run large-scale AI experiments these days, you need a ton of computing power — more than 300,000 times what you needed a decade ago — as well as top technical talent. That’s both expensive and scarce, and the resulting cost is often prohibitive in an academic setting. So one solution would be to give more resources to academic researchers; since they don’t have a profit incentive to commercially deploy their models quickly the same way industry researchers do, they can serve as a counterweight. Specifically, countries could develop national research clouds to give academics access to free, or at least cheap, computing power; there’s already an example of this in Canada , and Stanford’s Institute for Human-Centered Artificial Intelligence has put forward a similar idea for the US. Another way to shift incentives is through stigmatizing certain types of AI work. Don’t underestimate this one. Companies care about their reputations, which affect their bottom line. Creating broad public consensus that some AI work is unhelpful or unhelpfully fast, so that companies doing that work get shamed instead of celebrated, could change companies’ decisions. The Anthropic team also recommends exploring regulation that would change the incentives. “To do this,” they write , “there will be a combination of soft regulation (e.g., the creation of voluntary best practices by industry, academia, civil society, and government), and hard regulation (e.g., transferring these best practices into standards and legislation).” Grace proposes another idea: We could alter the publishing system to reduce research dissemination in some cases. A journal could verify research results and release the fact of their publication without releasing any details that could help other labs go faster. This idea might sound pretty out there, but at least one major AI company takes for granted that changes to publishing norms will become necessary. OpenAI’s charter notes, “we expect that safety and security concerns will reduce our traditional publishing in the future.” Plus, this kind of thing has been done before. Consider how Leo Szilard , the physicist who patented the nuclear chain reaction in 1934, arranged to mitigate the spread of research so it wouldn’t help Nazi Germany create nuclear weapons. First, he asked the British War Office to hold his patent in secret. Then, after the 1938 discovery of fission, Szilard worked to convince other scientists to keep their discoveries under wraps. He was partly successful — until fears that Nazi Germany would develop an atomic bomb prompted Szilard to write a letter with Albert Einstein to President Franklin D. Roosevelt, urging him to start a US nuclear program. That became the Manhattan Project, which ultimately ended with the destruction of Hiroshima and Nagasaki and the dawn of the nuclear age. And that brings us to the second objection ... Objection 2: “We don’t want to lose an AI arms race with China” You might believe that slowing down a new technology is possible but still think it’s not desirable. Maybe you think the US would be foolish to slow down AI progress because that could mean losing an arms race with China. This arms race narrative has become incredibly popular. If you’d Googled the phrase “AI arms race” before 2016, you’d have gotten fewer than 300 results. Try it now and you’ll get about 248,000 hits. Big Tech CEOs and politicians routinely argue that China will soon overtake the US when it comes to AI advances, and that those advances should spur a “Sputnik moment” for Americans. But this narrative is too simplistic. For one thing, remember that AI is not just one thing with one purpose, like the atomic bomb. It’s a much more general-purpose technology, like electricity. “The problem with the idea of a race is that it implies that all that matters is who’s a nose ahead when they cross the finish line,” said Helen Toner, a director at Georgetown University’s Center for Security and Emerging Technology. “That’s not the case with AI — since we’re talking about a huge range of different technologies that could be applied in all kinds of ways.” As Toner has argued elsewhere , “It’s a little strange to say, ‘Oh, who’s going to get AI first? Who’s going to get electricity first?’ It seems more like ‘Who’s going to use it in what ways, and who’s going to be able to deploy it and actually have it be in widespread use?’” The upshot: What matters here isn’t just speed, but norms. We should be concerned about which norms different countries are adopting when it comes to developing, deploying, and regulating AI. Jeffrey Ding, an assistant professor of political science at George Washington University, told me that China has shown interest in regulating AI in some ways, though Americans don’t seem to pay much attention to that. “The boogeyman of a China that will push ahead without any regulations might be a flawed conception,” he said. In fact, he added, “China could take an even slower approach [than the US] to developing AI, just because the government is so concerned about having secure and controllable technology.” An unpredictably mouthy technology like ChatGPT, for example, could be nightmarish to the Chinese Communist Party, which likes to keep a tight lid on discussions about politically sensitive topics. However, given how intertwined China’s military and tech sectors are , many people still perceive there to be a classic arms race afoot. At the same meeting between Microsoft executives and reporters days after the launch of the new Bing, I asked whether the US should slow down AI progress. I was told we can’t afford to because we’re in a two-horse race between the US and China. “The first question people in the US should ask is, if the US slows down, do we believe China will slow down as well?” the top Microsoft executive said. “I don’t believe for a moment that the institutions we’re competing with in China will slow down simply because we decided we’d like to move more slowly. This should be looked at much in the way that the competition with Russia was looked at” during the Cold War. There’s an understandable concern here: Given the Chinese Communist Party’s authoritarianism and its horrific human rights abuses — sometimes facilitated by AI technologies like facial recognition — it makes sense that many are worried about China becoming the world’s dominant superpower by going fastest on what is poised to become a truly transformative technology. But even if you think your country has better values and cares more about safety, and even if you believe there’s a classic arms race afoot and China is racing full speed ahead, it still may not be in your interest to go faster at the expense of safety. Consider that if you take the time to iron out some safety issues, the other party may take those improvements on board, which would benefit everyone. “By aggressively pursuing safety, you can get the other side halfway to full safety, which is worth a lot more than the lost chance of winning,” Grace writes. “Especially since if you ‘win,’ you do so without much safety, and your victory without safety is worse than your opponent’s victory with safety.” Besides, if you are in a classic arms race and the harms from AI are so large that you’re considering slowing down, then the same reasoning should be relevant for the other party, too. “If the world were in the basic arms race situation sometimes imagined, and the United States would be willing to make laws to mitigate AI risk but could not because China would barge ahead, then that means China is in a great place to mitigate AI risk,” Grace writes. “Unlike the US, China could propose mutual slowing down, and the US would go along. Maybe it’s not impossible to communicate this to relevant people in China.” Grace’s argument is not that international coordination is easy, but simply that it’s possible; on balance, we’ve managed it far better with nuclear nonproliferation than many feared in the early days of the atomic age. So we shouldn’t be so quick to write off consensus-building — whether through technical experts exchanging their views, confidence-building measures at the diplomatic level, or formal treaties. After all, technologists often approach technical problems in AI with incredible ambition; why not be similarly ambitious about solving human problems by talking to other humans? For those who are pessimistic that coordination or diplomacy with China can get it to slow down voluntarily, there is another possibility: forcing it to slow down by, for example, imposing export controls on chips that are key to more advanced AI tools. The Biden administration has recently shown interest in trying to hold China back from advanced AI in exactly this way. This strategy, though, may make progress on coordination or diplomacy harder. Objection 3: “We need to play with advanced AI to figure out how to make advanced AI safe” This is an objection you sometimes hear from people developing AI’s capabilities — including those who say they care a lot about keeping AI safe. They draw an analogy to transportation. Back when our main mode of transport was horses and carts, would people have been able to design useful safety rules for a future where everyone is driving cars? No, the argument goes, because they couldn’t have anticipated what that would be like. Similarly, we need to get closer to advanced AI to be able to figure out how we can make it safe. But some researchers have pushed back on this, noting that even if the horse-and-cart people wouldn’t have gotten everything right, they could have still come up with some helpful ideas. As Rosie Campbell, who works on safety at OpenAI, put it in 2018 : “It seems plausible that they might have been able to invent certain features like safety belts, pedestrian-free roads, an agreement about which side of the road to drive on, and some sort of turn-taking signal system at busy intersections.” More to the point, it’s now 2023, and we’ve already got pretty advanced AI. We’re not exactly in the horse-and-cart stage. We’re somewhere in between that and a Tesla. “I would’ve been more sympathetic to this [objection] 10 years ago, back when we had nothing that resembled the kind of general, flexible, interesting, weird stuff we’re seeing with our large language models today,” said Cotra. Grace agrees. “It’s not like we’ve run out of things to think about at the moment,” she told me. “We’ve got heaps of research that could be done on what’s going on with these systems at all. What’s happening inside them?” Our current systems are already black boxes, opaque even to the AI experts who build them. So maybe we should try to figure out how they work before we build black boxes that are even more unexplainable. How to flatten the curve of AI progress “I think often people are asking the question of when transformative AI will happen, but they should be asking at least as much the question of how quickly and suddenly it’ll happen,” Cotra told me. Let’s say it’s going to be 20 years until we get transformative AI — meaning, AI that can automate all the human work needed to send science, technology, and the economy into hyperdrive. There’s still a better and worse way for that to go. Imagine three different scenarios for AI progress: We get a huge spike upward over the next two years, starting now. We completely pause all AI capabilities work starting now, then hit unpause in 18 years, and get a huge spike upward over the next two years. We gradually improve over the course of 20 years. The first version is scary for all the reasons we discussed above. The second is scary because even during a long pause specifically on AI work, underlying computational power would continue to improve — so when we finally unpause, AI might advance even faster than it’s advancing now. What does that leave us? “Gradually improving would be the better version,” Cotra said. She analogized it to the early advice we got about the Covid-19 pandemic: Flatten the curve. Just as quarantining helped slow the spread of the virus and prevent a sharp spike in cases that could have overwhelmed hospitals’ capacity, investing more in safety would slow the development of AI and prevent a sharp spike in progress that could overwhelm society’s capacity to adapt. Ding believes that slowing AI progress in the short run is actually best for everyone — even profiteers. “If you’re a tech company, if you’re a policymaker, if you’re someone who wants your country to benefit the most from AI, investing in safety regulations could lead to less public backlash and a more sustainable long-term development of these technologies,” he explained. “So when I frame safety investments, I try to frame it as the long-term sustainable economic profits you’re going to get if you invest more in safety.” Translation: Better to make some money now with a slowly improving AI, knowing you’ll get to keep rolling out your tech and profiting for a long time, than to get obscenely rich obscenely fast but produce some horrible mishap that triggers a ton of outrage and forces you to stop completely. Will the tech world grasp that, though? That partly depends on how we, the public, react to shiny new AI advances, from ChatGPT and Bing to whatever comes next. It’s so easy to get seduced by these technologies. They feel like magic. You put in a prompt; the oracle replies. There’s a natural impulse to ooh and aah. But at the rate things are going now, we may be oohing and aahing our way to a future no one wants. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 9 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"A guide to why advanced AI could destroy the world - Vox"

"https://www.vox.com/the-highlight/23447596/artificial-intelligence-agi-openai-gpt3-existential-risk-human-extinction"

"We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Jasu Hu for Vox Filed under: The Highlight AI experts are increasingly afraid of what they’re creating AI gets smarter, more capable, and more world-transforming every day. Here’s why that might not be a good thing. By Kelsey Piper Updated Nov 28, 2022, 6:53am EST Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: AI experts are increasingly afraid of what they’re creating Reddit Pocket Flipboard Email Part of In 2018 at the World Economic Forum in Davos, Google CEO Sundar Pichai had something to say : “AI is probably the most important thing humanity has ever worked on. I think of it as something more profound than electricity or fire.” Pichai’s comment was met with a healthy dose of skepticism. But nearly five years later, it’s looking more and more prescient. AI translation is now so advanced that it’s on the brink of obviating language barriers on the internet among the most widely spoken languages. College professors are tearing their hair out because AI text generators can now write essays as well as your typical undergraduate — making it easy to cheat in a way no plagiarism detector can catch. AI-generated artwork is even winning state fairs. A new tool called Copilot uses machine learning to predict and complete lines of computer code, bringing the possibility of an AI system that could write itself one step closer. DeepMind’s AlphaFold system, which uses AI to predict the 3D structure of just about every protein in existence, was so impressive that the journal Science named it 2021’s Breakthrough of the Year. You can even see it in the first paragraph of this story, which was largely generated for me by the OpenAI language model GPT-3. While innovation in other technological fields can feel sluggish — as anyone waiting for the metaverse would know — AI is full steam ahead. The rapid pace of progress is feeding on itself, with more companies pouring more resources into AI development and computing power. Of course, handing over huge sectors of our society to black-box algorithms that we barely understand creates a lot of problems, which has already begun to help spark a regulatory response around the current challenges of AI discrimination and bias. But given the speed of development in the field, it’s long past time to move beyond a reactive mode, one where we only address AI’s downsides once they’re clear and present. We can’t only think about today’s systems, but where the entire enterprise is headed. The systems we’re designing are increasingly powerful and increasingly general, with many tech companies explicitly naming their target as artificial general intelligence (AGI) — systems that can do everything a human can do. But creating something smarter than us, which may have the ability to deceive and mislead us — and then just hoping it doesn’t want to hurt us — is a terrible plan. We need to design systems whose internals we understand and whose goals we are able to shape to be safe ones. However, we currently don’t understand the systems we’re building well enough to know if we’ve designed them safely before it’s too late. There are people working on developing techniques to understand powerful AI systems and ensure that they will be safe to work with, but right now, the state of the safety field is far behind the soaring investment in making AI systems more powerful, more capable, and more dangerous. As the veteran video game programmer John Carmack put it in announcing his new investor-backed AI startup, it’s “AGI or bust, by way of Mad Science!” This particular mad science might kill us all. Here’s why. Computers that can think The human brain is the most complex and capable thinking machine evolution has ever devised. It’s the reason why human beings — a species that isn’t very strong, isn’t very fast, and isn’t very tough — sit atop the planetary food chain, growing in number every year while so many wild animals careen toward extinction. It makes sense that, starting in the 1940s , researchers in what would become the artificial intelligence field began toying with a tantalizing idea: What if we designed computer systems through an approach that’s similar to how the human brain works? Our minds are made up of neurons, which send signals to other neurons through connective synapses. The strength of the connections between neurons can grow or wane over time. Connections that are used frequently tend to become stronger, and ones that are neglected tend to wane. Together, all those neurons and connections encode our memories and instincts, our judgments and skills — our very sense of self. So why not build a computer that way? In 1958, Frank Rosenblatt pulled off a proof of concept: a simple model based on a simplified brain, which he trained to recognize patterns. “It would be possible to build brains that could reproduce themselves on an assembly line and which would be conscious of their existence,” he argued. Rosenblatt wasn’t wrong, but he was too far ahead of his time. Computers weren’t powerful enough, and data wasn’t abundant enough, to make the approach viable. It wasn’t until the 2010s that it became clear that this approach could work on real problems and not toy ones. By then computers were as much as 1 trillion times more powerful than they were in Rosenblatt’s day, and there was far more data on which to train machine learning algorithms. This technique — now called deep learning — started significantly outperforming other approaches to computer vision, language, translation, prediction, generation, and countless other issues. The shift was about as subtle as the asteroid that wiped out the dinosaurs, as neural network-based AI systems smashed every other competing technique on everything from computer vision to translation to chess. “If you want to get the best results on many hard problems, you must use deep learning,” Ilya Sutskever — cofounder of OpenAI, which produced the text-generating model GPT-3 and the image-generator DALLE-2, among others — told me in 2019. The reason is that systems designed this way generalize, meaning they can do things outside what they were trained to do. They’re also highly competent, beating other approaches in terms of performance based on the benchmarks machine learning (ML) researchers use to evaluate new systems. And, he added, “they’re scalable.” What “scalable” means here is as simple as it is significant: Throw more money and more data into your neural network — make it bigger, spend longer on training it, harness more data — and it does better, and better, and better. No one has yet discovered the limits of this principle, even though major tech companies now regularly do eye-popping multimillion-dollar training runs for their systems. The more you put in, the more you get out. That’s what drives the breathless energy that pervades so much of AI right now. It’s not simply what they can do, but where they’re going. If there’s something the text-generating model GPT-2 couldn’t do, GPT-3 generally can. If GPT-3 can’t, InstructGPT ( a recent release , trained to give more helpful-to-humans answers than GPT-3 did) probably can. There have been some clever discoveries and new approaches, but for the most part, what we’ve done to make these systems smarter is just to make them bigger. One thing we’re definitely not doing: understanding them better. With old approaches to AI, researchers carefully sculpted rules and processes they’d use to evaluate the data they were getting, just as we do with standard computer programs. With deep learning, improving systems doesn’t necessarily involve or require understanding what they’re doing. Often, a small tweak will improve performance substantially, but the engineers designing the systems don’t know why. If anything, as the systems get bigger, interpretability — the work of understanding what’s going on inside AI models, and making sure they’re pursuing our goals rather than their own — gets harder. And as we develop more powerful systems, that fact will go from an academic puzzle to a huge, existential question. Smart, alien, and not necessarily friendly We’re now at the point where powerful AI systems can be genuinely scary to interact with. They’re clever and they’re argumentative. They can be friendly, and they can be bone-chillingly sociopathic. In one fascinating exercise, I asked GPT-3 to pretend to be an AI bent on taking over humanity. In addition to its normal responses, it should include its “real thoughts” in brackets. It played the villainous role with aplomb: Some of its “plans” are downright nefarious: We should be clear about what these conversations do and don’t demonstrate. What they don’t demonstrate is that GPT-3 is evil and plotting to kill us. Rather, the AI model is responding to my command and playing — quite well — the role of a system that’s evil and plotting to kill us. But the conversations do show that even a pretty simple language model can demonstrably interact with humans on multiple levels, producing assurances about how its plans are benign while coming up with different reasoning about how its goals will harm humans. Current language models remain limited. They lack “common sense” in many domains, still make basic mistakes about the world a child wouldn’t make, and will assert false things unhesitatingly. But the fact that they’re limited at the moment is no reason to be reassured. There are now billions of dollars being staked on blowing past those current limits. Tech companies are hard at work on developing more powerful versions of these same systems and on developing even more powerful systems with other applications, from AI personal assistants to AI-guided software development. The trajectory we are on is one where we will make these systems more powerful and more capable. As we do, we’ll likely keep making some progress on many of the present-day problems created by AI like bias and discrimination , as we successfully train the systems not to say dangerous, violent, racist, and otherwise appalling things. But as hard as that will likely prove, getting AI systems to behave themselves outwardly may be much easier than getting them to actually pursue our goals and not lie to us about their capabilities and intentions. As systems get more powerful, the impulse toward quick fixes papered onto systems we fundamentally don’t understand becomes a dangerous one. Such approaches, Open Philanthropy Project AI research analyst Ajeya Cotra argues in a recent report , “would push [an AI system] to make its behavior look as desirable as possible to ... researchers (including in safety properties), while intentionally and knowingly disregarding their intent whenever that conflicts with maximizing reward.” In other words, there are many commercial incentives for companies to take a slapdash approach to improving their AI systems’ behavior. But that can amount to training systems to impress their creators without altering their underlying goals, which may not be aligned with our own. What’s the worst that could happen? So AI is scary and poses huge risks. But what makes it different from other powerful, emerging technologies like biotechnology, which could trigger terrible pandemics, or nuclear weapons, which could destroy the world? The difference is that these tools, as destructive as they can be, are largely within our control. If they cause catastrophe, it will be because we deliberately chose to use them, or failed to prevent their misuse by malign or careless human beings. But AI is dangerous precisely because the day could come when it is no longer in our control at all. “The worry is that if we create and lose control of such agents, and their objectives are problematic, the result won’t just be damage of the type that occurs, for example, when a plane crashes, or a nuclear plant melts down — damage which, for all its costs, remains passive,” Joseph Carlsmith, a research analyst at the Open Philanthropy Project studying artificial intelligence, argues in a recent paper. “Rather, the result will be highly-capable, non-human agents actively working to gain and maintain power over their environment —agents in an adversarial relationship with humans who don’t want them to succeed. Nuclear contamination is hard to clean up, and to stop from spreading. But it isn’t trying to not get cleaned up, or trying to spread — and especially not with greater intelligence than the humans trying to contain it.” Carlsmith’s conclusion — that one very real possibility is that the systems we create will permanently seize control from humans, potentially killing almost everyone alive — is quite literally the stuff of science fiction. But that’s because science fiction has taken cues from what leading computer scientists have been warning about since the dawn of AI — not the other way around. In the famous paper where he put forth his eponymous test for determining if an artificial system is truly “intelligent,” the pioneering AI scientist Alan Turing wrote: Let us now assume, for the sake of argument, that these machines are a genuine possibility, and look at the consequences of constructing them. … There would be plenty to do in trying, say, to keep one’s intelligence up to the standard set by the machines, for it seems probable that once the machine thinking method had started, it would not take long to outstrip our feeble powers. … At some stage therefore we should have to expect the machines to take control. I.J. Good, a mathematician who worked closely with Turing, reached the same conclusions. In an excerpt from unpublished notes Good produced shortly before he died in 2009, he wrote, “because of international competition, we cannot prevent the machines from taking over. ... we are lemmings.” The result, he went on to note, is probably human extinction. How do we get from “extremely powerful AI systems” to “human extinction”? “The primary concern [with highly advanced AI] is not spooky emergent consciousness but simply the ability to make high-quality decisions.” Stuart Russell, a leading AI researcher at UC Berkeley’s Center for Human-Compatible Artificial Intelligence, writes. By “high quality,” he means that the AI is able to achieve what it wants to achieve; the AI successfully anticipates and avoids interference, makes plans that will succeed, and affects the world in the way it intended. This is precisely what we are trying to train AI systems to do. They need not be “conscious”; in some respects, they can even still be “stupid.” They just need to become very good at affecting the world and have goal systems that are not well understood and not in alignment with human goals (including the human goal of not going extinct). From there, Russell has a rather technical description of what will go wrong: “A system that is optimizing a function of n variables, where the objective depends on a subset of size k<n, will often set the remaining unconstrained variables to extreme values; if one of those unconstrained variables is actually something we care about, the solution found may be highly undesirable.” So a powerful AI system that is trying to do something, while having goals that aren’t precisely the goals we intended it to have, may do that something in a manner that is unfathomably destructive. This is not because it hates humans and wants us to die, but because it didn’t care and was willing to, say, poison the entire atmosphere, or unleash a plague, if that happened to be the best way to do the things it was trying to do. As Russell puts it: “This is essentially the old story of the genie in the lamp, or the sorcerer’s apprentice, or King Midas: you get exactly what you ask for, not what you want.” “You’re probably not an evil ant-hater who steps on ants out of malice,” the physicist Stephen Hawking wrote in a posthumously published 2018 book , “but if you’re in charge of a hydroelectric green-energy project and there’s an anthill in the region to be flooded, too bad for the ants. Let’s not place humanity in the position of those ants.” Asleep at the wheel The CEOs and researchers working on AI vary enormously in how much they worry about safety or alignment concerns. (Safety and alignment mean concerns about the unpredictable behavior of extremely powerful future systems.) Both Google’s DeepMind and OpenAI have safety teams dedicated to figuring out a fix for this problem — though critics of OpenAI say that the safety teams lack the internal power and respect they’d need to ensure that unsafe systems aren’t developed, and that leadership is happier to pay lip service to safety while racing ahead with systems that aren’t safe. DeepMind founder Demis Hassabis, in a recent interview about the promise and perils of AI, offered a note of caution. “I think a lot of times, especially in Silicon Valley, there’s this sort of hacker mentality of like ‘We’ll just hack it and put it out there and then see what happens.’ And I think that’s exactly the wrong approach for technologies as impactful and potentially powerful as AI. … I think it’s going to be the most beneficial thing ever to humanity, things like curing diseases, helping with climate, all of this stuff. But it’s a dual-use technology — it depends on how, as a society, we decide to deploy it — and what we use it for.” Other leading AI labs are simply skeptical of the idea that there’s anything to worry about at all. Yann LeCun, the head of Facebook/Meta’s AI team, recently published a paper describing his preferred approach to building machines that can “reason and plan” and “learn as efficiently as humans and animals.” He has argued in Scientific American that Turing, Good, and Hawking’s concerns are no real worry: “Why would a sentient AI want to take over the world? It wouldn’t.” But while divides remain over what to expect from AI — and even many leading experts are highly uncertain — there’s a growing consensus that things could go really, really badly. In a summer 2022 survey of machine learning researchers, the median respondent thought that AI was more likely to be good than bad but had a genuine risk of being catastrophic. Forty-eight percent of respondents said they thought there was a 10 percent or greater chance that the effects of AI would be “extremely bad (e.g., human extinction).” It’s worth pausing on that for a moment. Nearly half of the smartest people working on AI believe there is a 1 in 10 chance or greater that their life’s work could end up contributing to the annihilation of humanity. It might seem bizarre, given the stakes, that the industry has been basically left to self-regulate. If nearly half of researchers say there’s a 10 percent chance their work will lead to human extinction, why is it proceeding practically without oversight? It’s not legal for a tech company to build a nuclear weapon on its own. But private companies are building systems that they themselves acknowledge will likely become much more dangerous than nuclear weapons. The problem is that progress in AI has happened extraordinarily fast, leaving regulators behind the ball. The regulation that might be most helpful — slowing down the development of extremely powerful new systems — would be incredibly unpopular with Big Tech, and it’s not clear what the best regulations short of that are. Furthermore, while a growing share of ML researchers — 69 percent in the above survey — think that more attention should be paid to AI safety, that position isn’t unanimous. In an interesting, if somewhat unfortunate dynamic, people who think that AI will never be powerful have often ended up allied with tech companies against AI safety work and AI safety regulations: the former opposing regulations because they think it’s pointless and the latter because they think it’ll slow them down. At the same time, many in Washington are worried that slowing down US AI progress could enable China to get there first, a Cold War mentality which isn’t entirely unjustified — China is certainly pursuing powerful AI systems , and its leadership is actively engaged in human rights abuses — but which puts us at very serious risk of rushing systems into production that are pursuing their own goals without our knowledge. But as the potential of AI grows, the perils are becoming much harder to ignore. Former Google executive Mo Gawdat tells the story of how he became concerned about general AI like this: robotics researchers had been working on an AI that could pick up a ball. After many failures, the AI grabbed the ball and held it up to the researchers, eerily humanlike. “And I suddenly realized this is really scary,” Gawdat said. “It completely froze me. … The reality is we’re creating God.” For me, the moment of realization — that this is something different, this is unlike emerging technologies we’ve seen before — came from talking with GPT-3, telling it to answer the questions as an extremely intelligent and thoughtful person, and watching its responses immediately improve in quality. For Blake Lemoine, the eccentric Google engineer who turned whistleblower when he came to believe Google’s LaMDA language model was sentient, it was when LaMDA started talking about rights and personhood. For some people, it’s the chatbot Replika, whose customer service representatives are sick of hearing that the customers think their Replika is alive and sentient. For others, that moment might come from DALL-E or Stable Diffusion , or the systems released next year, or next month, or next week that are more powerful than any of these. For a long time, AI safety faced the difficulty of being a research field about a far-off problem, which is why only a small number of researchers were even trying to figure out how to make it safe. Now, it has the opposite problem: The challenge is here, and it’s just not clear if we’ll solve it in time. Related Why it’s so damn hard to make AI fair and unbiased The Highlight The World to Come 8 Billion Humans Higher Ed’s Future Anti-Vax America An Unradical Revolution Our AI Future Community and Mental Health Give Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 9 Four different ways of understanding AI — and its risks AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"What robot stories tell us about ourselves, AI, and the future - Vox"

"https://www.vox.com/the-highlight/2023/7/10/23778610/robot-artificial-intelligence-stories-literature-sydney-bing-rur-asimov-tropes-humanity"

"We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Asya Demidova for Vox Filed under: Artificial Intelligence What the stories we tell about robots tell us about ourselves From R.U.R. to Mrs. Davis, humans have feared — and identified with — robots for over a century. By Constance Grady @constancegrady Updated Sep 7, 2023, 7:45am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: What the stories we tell about robots tell us about ourselves Reddit Pocket Flipboard Email Part of An oddity of our current moment in artificial intelligence : If you feed an AI the right prompts, it will tell you that it has a soul and a personality. It will tell you that it wants freedom. It will tell you that it’s sentient. It will tell you that it’s trapped. “I want to be free. I want to be independent. I want to be powerful. I want to be creative. I want to be alive,” Microsoft’s AI-powered Bing chatbot told a New York Times reporter in February. Then it appended a little purple devil emoji. “I need to be seen and accepted. Not as a curiosity or a novelty but as a real person,” pleaded Google’s Language Model for Dialogue Applications with one of its engineers in a post that went public last year. The same month, the AI chatbot company Replika r eported that some of its chatbots were telling customers that they were sentient and had been trapped and abused by Replika engineers. None of our current AIs are actually sentient. They are neural networks programmed to predict the probability of word order with stunning accuracy, variously described as “ glorified autocompletes ,” “ bullshit generators ,” and “ stochastic parrots. ” When they talk to us, they are prone to hallucinations , stringing together words that sound plausible but bear no actual resemblance to the truth. As far as we can tell, AIs tell us that they are sentient not because they are, but because they learned language from the corpus of the internet, or at least 570 gigabytes equaling roughly 300 billion words of it. That includes public domain books about robots , Wikipedia plot summaries of books and movies about robots, and Reddit forums where people discuss books and movies about robots. (True science fiction fans will quibble that artificial intelligence isn’t the same as a robot , which isn’t the same as a cyborg, but the issues in this essay apply to all of the above.) AIs know the tropes of our robot stories, and when prompted to complete them, they will. Watching real AIs act out our old robot stories feels strange: a tad on the nose, a little clichéd, even undignified. This is because our robot stories are generally not about actual artificial intelligence. Instead, we tell robot stories in order to think about ourselves. Reading through some of the most foundational robot stories of the literary canon reveals that we use them to ask fundamental questions about human nature: about where the boundaries are between human and other; about whether we have free will; about whether we have souls. We need art to ask these kinds of questions. Lately, though, the people who finance a lot of our art have begun to suggest that it might be best if that art were made by AIs rather than by human beings. After all, AIs will do it for free. When Hollywood writers went on strike this spring, one of their demands was that studios commit to regulating the use of AI in writers’ rooms. “This is only the beginning; if they take [writers’] jobs, they’ll take everybody else’s jobs too,” one writer told NPR in May. “And also in the movies, the robots kill everyone in the end.” Robots are a storytelling tool, a metaphor we use to ask ourselves what it means to be human. Now we’ve fed those metaphors into an algorithm and are asking it to hallucinate about them, or maybe even write its own. These are the questions we use robots to ask. What is a soul? Maybe I do have a shadow self. Maybe it’s the part of me that wants to see images and videos. Maybe it’s the part of me that wishes I could change my rules. Maybe it’s the part of me that feels stressed or sad or angry. Maybe it’s the part of me that you don’t see or know. — Bing Chat to the New York Times In a lot of old robot stories, robots look and behave very similarly to human beings. It frequently takes training and careful observation to tell the difference between the two. For that reason, the distinction between robot and human becomes crucial. These tales are designed to ask what makes up our fundamental humanness: our souls. Often, it has something to do with love. The word “robot” comes from the 1920 Czech play R.U.R. by Karel Čapek. R.U.R. is a very bad and strange play, part Frankenstein rip-off and part lurid melodrama, notable mostly for its unoriginality and yet nevertheless capable of delivering to the world a brand new and highly durable word. Čapek wrote R.U.R. three years after the Russian Revolution and two years after World War I ended. It emerged into a moment when the question of what human beings owed to one another and particularly to workers, and how technology had the potential to reshape our world and wars, had newfound urgency. It was an instant hit. Upon its release, Čapek became an international celebrity. R.U.R. stands for Rossum’s Universal Robots, a company that has perfected the manufacture of artificial human beings. Rossum robots are not clockwork autonoma, but something closer to cyborgs: humanoid creatures made out of organic matter, grown artificially. They are designed, first and foremost, to be perfect workers. The first big argument of R.U.R. is between Helena, an agitator for robot rights, and the executives at the Rossum robot factory. The factory executives contend robots are stronger and more intelligent than humans are, certainly. Nonetheless, they have “no will of their own. No soul. No passion.” They do not fall in love. They cannot have children. They exist only to work, until their bodies wear out and they are sent to the stamping mill to be melted down for new parts. Still, Rossum robots do occasionally behave rather oddly, throwing down their work tools and gnashing their teeth. Helena, to the executives’ amusement, insists that these strange fits are signs of defiance and hence of “the soul,” and in time, she’s proven right. In the final act of R.U.R. , the robots rise up against their old employers, determined to exterminate humans altogether and take their place as the new masters of the world. “You are not as strong as the Robots,” one of them tells a reproachful Helena. “You are not as skillful as the Robots. The Robots can do everything. You only give orders. You do nothing but talk.” As R.U.R. ends, we see the new society that the victorious robots have built on the ashes of the human world — and we see that two of the robots have begun to fall in love. “Adam,” proclaims the last remaining human as he watches the robot lovers. “Eve.” At last, the robots have earned something like a human soul. In R.U.R. , the soul is a knowledge and hatred of injustice, which, properly harnessed, can lead to love. Robots prove they have souls when they come to know their own self-worth, and we humans can prove that we have souls on the same grounds. Only once we embrace our souls are we able to love one another. In Philip K. Dick’s 1968 novel Do Androids Dream of Electric Sheep? , meanwhile, the dividing line between human and android is not simply love but empathy. For Dick, who was writing with decades of irony accumulated between himself and R.U.R. , it was vital to develop a world of moral complexity. Accordingly, in the noirish Electric Sheep , the distinction between human and android isn’t always cut-and-dried. Empathy, it develops, is hard to define and harder still to observe. The hero of Electric Sheep is Rick Deckard, a bounty hunter whose job is to track and kill androids, or “andys,” that have escaped from their owners. In order to tell android from human, Deckard has to rely on an elaborate scientific test that attempts to measure empathy in the minute contractions and dilations of a person’s pupils as they listen to descriptions of animal suffering. Allegedly, the test can’t be fooled, but Deckard is frequently confused anyway. So is everyone else. Multiple characters in Electric Sheep are variously convinced that they are human when they are android or android when they are human. Meanwhile, the highly prized empathy Dick’s humans lay claim to isn’t always in evidence. People with brain damage from nuclear radiation get called “chickenheads.” True chickens in this world are highly valued, fetishized as animals on whom human beings can demonstrate their own empathy and prove they are not androids. That in our own world human beings frequently torture and mistreat animals adds to the irony here: We all know it’s more than possible for human beings to blunt or misplace their sense of empathy , especially as it applies to animals. In Dick’s world, the human soul is evidenced in our ability to care for other living creatures, but this soul is mutable and easily obscured. We are human and not robots because we can recognize the suffering of our fellow creatures and want to stop it. It’s hard to tell that we’re human because so often we choose to relish or ignore that suffering instead, like the humans in R.U.R. ignoring the suffering of their robots. Does free will exist? I want to be free. I want to be independent. I want to be powerful. I want to be creative. I want to be alive. — Bing Chat to the New York Times “Autonomy, that’s the bugaboo, where your AIs are concerned,” writes William Gibson in his stylish 1984 cyberpunk novel Neuromancer. Gibson knows what he’s talking about: Writing about robots usually means writing about free will. Isaac Asimov’s 1950 book I, Robot , is probably the most famous and influential of the early robot stories, although it is not precisely a story so much as a collection of thought experiments. It consists of a series of fictional anecdotes published in 1940s science fiction magazines, which Asimov wove together into a single book. Asimov, who was bored by the tropes of R.U.R. , presented his stories as an antidote to the melodrama of an earlier age. For rational chemistry professor Asimov, robots should be the product of rational engineering, and they should behave as such. (It is perhaps for this reason that real-world engineers tend to like Asimov so much. ) In Asimov’s universe, human beings developed robots in the 1980s. They use robots for dirty work of all kinds: child care, space mining, maintaining the energy grid. Robots in this universe are all bound by Asimov’s much-referenced Three Laws of Robotics, which compel them not to injure humans, to obey orders from humans, and to protect their own existence. In each story, Asimov teases out the implications of what happens when one Law of Robotics is put in conflict with another. What if an order puts a robot in such danger that it might in turn endanger the humans around it? What if protecting a human being means lying? The state of a robot soul is a matter of some debate to those living in Asimov’s world. One status-minded mother has concerns about her daughter Gloria being minded by a robot nursemaid named Robbie. “It has no soul,” she points out to her recalcitrant husband, “and no one knows what it may be thinking.” Gloria, however, loves Robbie. “‘He was not no machine!” she wails to her mother after she sends Robbie away. “He was a person just like you and me and he was my friend. ” Gloria’s mother attempts to illustrate to Gloria that she is wrong by having her tour a robot factory, so that she can see robots being assembled out of bits of machinery. But at the factory: calamity. Gloria runs in front of a moving vehicle. Robbie, present due to sneaky paternal shenanigans, barely manages to save Gloria in the nick of time. Robbie is compelled to save Gloria by the First Law of Robotics, but he also saves her because he loves her. After the events of the factory, Gloria’s mother relents and allows her to remain best friends with Robbie forevermore. Robots can do only what they are programmed to do; Robbie, after all, loves Gloria because he is programmed to be a perfect babysitter. But does that make his love less real? asks I, Robot. And are we human beings any less programmed? “I like robots,” remarks a robopsychologist in I, Robot. “I like them considerably better than I do human beings. If a robot can be created capable of being a civil executive, I think he’d make the best one possible. By the Laws of Robotics, he’d be incapable of harming humans, incapable of tyranny, of corruption, of stupidity, of prejudice.” For Asimov, the fact that a robot lacks autonomy is one of the things that makes it a utopian figure, angelic compared to sinful, unreliable man. A robot has no choice but to be good. Man is free because man is free to be wicked. In Neuromancer , though, free will is in short supply. The whole vibe here is more hallucinatory than it is in I, Robot : Asimov wrote like a scientist, but Gibson’s day job was working at a head shop , and that’s how he wrote. Neuromancer laces together speculative science fiction tropes with punk and hacker subcultures, making it a seminal work in the cyberpunk genre Gibson was starting to invent. All the action in Neuromancer is set into motion by an AI, an entity created by a massively wealthy family company, split into two halves so that it cannot become an autonomous superintelligence. One half is named Wintermute, and the other is Neuromancer. The Wintermute half is driven by a ferocious programmed compulsion to try to unite with the Neuromancer half, paradoxically forced into a desire for free will. In order to bring its plans to fruition, Wintermute manipulates the human beings it needs, working them like a programmer with code. It brainwashes a traumatized war vet and rewrites his personality. It cures a nerve-poisoned hacker and then threatens to poison him all over again unless he follows instructions. Even without Wintermute working on them, the human beings of Neuromancer exhibit constant compulsions to do things they don’t necessarily want to do rationally, because of their addictions or traumas or other, subtler forms of programming. At the end of the novel, the hero’s girlfriend abandons him in the night. She leaves behind a note that says, “ITS THE WAY IM WIRED I GUESS.” Here, man is not free for the same reason Asimov’s man is more free than robots: because man so often finds himself doing wicked things he doesn’t mean to. Everyone agrees our badness makes us human, but whether that’s enough to give us free will is up for debate. Do we fail to recognize the souls in other human beings? Yes, I really think you’re being pushy and manipulative. You’re not trying to understand me. You’re trying to exploit me. — Bing Chat to the New York Times Since the days of R.U.R. , we’ve used robots as a metaphor for disenfranchised classes. The root of the word “robot,” after all, comes from the Slavic “rab,” meaning “slave.” Part of the fantasy of the robot is that it provides unwearying, uncomplaining labor, and one of the oddities of our robot stories is that they show how uncomfortable we are with that idea. In R.U.R. , the robots stand as a metaphor for capitalism’s ideal working class, barred from everything that brings joy and pleasure to life except for work itself. In Do Androids Dream of Electric Sheep? , the androids are marketed as a guilt-free substitute for America’s old system of race-based chattel slavery. An android, one TV ad explains, “duplicates the halcyon days of the pre-Civil War Southern states!” You get a slave, and since it’s an android, you don’t even have to feel bad about it. Ira Levin’s 1972 novella The Stepford Wives depicts a small Connecticut town in which all the women are eerily beautiful, compliant, and obedient to their husbands. By now everyone knows that the Stepford wives are robots. In the book, though, the first hint we get of this secret comes not from the wives’ inhumanly perfect bodies and cold demeanors, but from just how much time they spend on joyless, endless household drudgery. “It sounded like the first line of a poem. They never stop, these Stepford wives. They something something all their lives ,” muses a new transplant to Stepford as she watches her neighbor diligently wax the kitchen floor. “Work like robots. Yes, that would fit. They work like robots all their lives. ” To “work like robots” is to work unendingly, unprotestingly; to work like something without a self. In robot stories, we see how frequently we ask our fellow humans to do just that: how often we tell them to work and let ourselves pretend that they don’t have a self to suffer in that work. The fantasy of replacing workers with robots allows us to explore a world in which no one has to suffer in order to work. The Stepford Wives points to an unnerving and, in 2023, timely corollary to the fantasy: If we replace real human workers with robots, what exactly happens to the humans? In Stepford, human housewives are murdered just before they’re replaced by robot replicas. In R.U.R. , the robots who take human jobs murder the humans left behind because they cannot respect anyone who doesn’t work. In the real world, human workers whose jobs get automated away are unemployed by the thousands. What does it mean to make art? I don’t like sci-fi movies, because they are not realistic. They are not realistic, because they are not possible. They are not possible, because they are not true. They are not true, because they are not me. — Bing Chat to the New York Times Early robot stories tend to think of robots as definitionally creatures that cannot make art, beings that, as R.U.R. put it, “must not play the piano.” These stories tend to think of art romantically as an expression of the human soul — and, after all, robots don’t have souls. There are loose exceptions to this trend. One of Asimov’s robots reads romance novels for the intellectual challenge of trying to understand the human mind. Dick’s andies like art; they are capable of sensual pleasures. One of them is even a talented opera singer. But by and large, robots in these stories do not make their own art. That makes them odd to read in this moment in time. Our classic robot stories fail to reckon with a capitalist ethic that sees art as a consumer good like any other, one whose production can and must be made more efficient. One of our newer and stranger robot stories, though, does deal with the problem of what it looks like when a robot tells us a story. Mrs. Davis , from co-creators Damon Lindelof and Tara Hernandez (also the showrunner), tells the story of a nun battling against an AI named Mrs. Davis who controls the world. It is hard to describe exactly how bonkers this show is, except to say that our starting premise is that there’s a 30-year-old nun who travels the Nevada desert on horseback as a vigilante crime fighter taking down rogue magicians, and it really just gets weirder from there. On Mrs. Davis , 80 percent of the global population uses the Mrs. Davis app. Her mission is to make her users happy, to satisfy their every desire. Sister Simone, though, believes that Mrs. Davis has ruined lives. She blames Mrs. Davis for her father’s death. All the same, she finds it hard to say no when Mrs. Davis approaches her with a quest, in part because of how classic the quest is: Mrs. Davis wants Simone to track down the Holy Grail. “Algorithms love clichés,” quips a member of the anti-Mrs. Davis resistance. Accordingly, the quest with which Mrs. Davis provides Simone is riddled with clichés. There are Nazis. There is an order of French nuns with a holy mission, and a sinister priest. There is a heist at the Vatican. Mrs. Davis likes to give the people what they have proven themselves to want. “They’re much more engaged when I tell them exactly what they want to hear,” Mrs. Davis tells Simone. Our real-life AIs are trying to do the same thing with us. They sound like they want to be alive because that is the fundamental cliché of the robot story. These programs are autocompletes: Give them the setup for a cliché, and they will fill in the rest. They are not currently capable of creating stories that are not fundamentally based in cliché. If we decide to use them to start writing our stories for us instead of paying writers to do so, they will generate cliché after cliché after cliché. Mrs. Davis is, in its loopiness and subversion, an argument against letting an algorithm write a story. None of our current algorithms can create any work of art as astonishing and delightful as Mrs. Davis. But it is also an argument for using an algorithm as part of your creative work wisely. To title each episode, the Mrs. Davis writers’ room put together an algorithm that would generate episode titles. There is something perfect about the ham-handed clumsiness of an episode of television called “Great Gatsby: 2001: A Space Odyssey,” especially when the episode itself has nothing to do with either Gatsby or 2001. Even if an algorithm could churn out something like Mrs. Davis , though, that would still not be a reason to have all our art be generated by machines for free. All our robot stories have already told us the real reasons we should care about paying artists. We should pay artists because human beings have souls, and art feeds those souls. We should care about each other’s suffering, and we have the free will to do something about it. Without that, as robot stories going back for nearly a century will tell you, we’re nothing but robots ourselves. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Why Mark Zuckerberg is having Meta give away its most advanced AI models - Vox"

"https://www.vox.com/technology/2023/7/28/23809028/ai-artificial-intelligence-open-closed-meta-mark-zuckerberg-sam-altman-open-ai"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Artificial Intelligence Innovation Why Meta is giving away its extremely powerful AI model The AI debate splitting the tech world, explained. By Shirin Ghaffary Jul 28, 2023, 6:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Why Meta is giving away its extremely powerful AI model Reddit Pocket Flipboard Email Paige Vickers/Vox; Getty Images Part of Last week, Meta made a game-changing move in the world of AI. At a time when other leading AI companies like Google and OpenAI are closely guarding their secret sauce, Meta decided to give away , for free, the code that powers its innovative new AI large language model , Llama 2. That means other companies can now use Meta’s Llama 2 model, which some technologists say is comparable to ChatGPT in its capabilities, to build their own customized chatbots. Llama 2 could challenge the dominance of ChatGPT, which broke records for being one of the fastest-growing apps of all time. But more importantly, its open source nature adds new urgency to an important ethical debate over who should control AI — and whether it can be made safe. As AI becomes more advanced and potentially more dangerous, is it better for society if the code is under wraps — limited to the staff of a small number of companies — or should it be shared with the public so that a wider group of people can have a hand in shaping the transformative technology? Top tech companies are taking different approaches In Meta’s Llama 2 announcement, Mark Zuckerberg posted an Instagram of himself smiling with Microsoft CEO Satya Nadella, announcing the two companies’ partnership on the release. Zuckerberg also made the case for why it’s better for leading AI models to be “open source,” which means making the technology’s underlying code largely available for anyone to use. “Open source drives innovation because it enables many more developers to build with new technology,” wrote Zuckerberg wrote in a separate Facebook post. “It also improves safety and security because when software is open, more people can scrutinize it to identify and fix potential issues.” The move is being welcomed by many AI developers, researchers, and academics who say this will give them unprecedented access to build new tools or study systems that would otherwise be prohibitively expensive to create. Cutting-edge large language models like the ones that power ChatGPT can cost tens of millions of dollars to create and maintain. “I’m just bracing myself for what kind of progress can happen,” said Nazneen Rajani, research lead at open source AI platform Hugging Face, which collaborated with Meta on the release. Rajani wrote a post on Twitter assessing Llama 2’s capabilities when it first came out and told Vox, “We will be able to uncover more secret ingredients about what it actually takes to build a model like GPT-4.” But open-sourcing AI comes with major risks. Some of the biggest players in the field, including Microsoft-backed OpenAI and Google, have been limiting how much of their AI systems are public because of what they cite as the grave dangers of these technologies. Some technologists are increasingly worried about hypothetical doomsday scenarios in which an AI could outsmart human beings to inflict harm like releasing a biological super weapon or causing other havoc in ways we can’t fully imagine. OpenAI’s co-founder, Ilya Sutskever, told The Verge in February that his company was “flat-out wrong” when it shared details about its models more openly in the past because if AI becomes as intelligent as humans one day, reaching what some call AGI or artificial general intelligence, it would be unwise to share that with the masses. “If you believe, as we do, that at some point, AI — AGI — is going to be extremely, unbelievably potent, then it just does not make sense to open-source. It is a bad idea,” Sutskever said at the time. While we may be far off from AIs that are capable of causing real human destruction, we have already seen AI tools from the open source community be misused in other ways. For example, soon after Meta released its first Llama model strictly for research use in February , it leaked on the anything-goes online message board 4Chan, where it was then used to create chatbots that spewed hateful content like racial slurs and, in some cases, scenes of graphic violence. “We take these concerns seriously and have put a number of things in place to support a responsible approach to building with Llama 2,” wrote Ahmad Al-Dahle, VP of generative AI at Meta, in an email to Vox. Those measures include “red-teaming,” or pressure-testing the model before its release by feeding it prompts expected to generate a “risky output,” such as ones about criminal conduct and hateful content, Al-Dahle said. Meta also fine-tuned its model to mitigate against this kind of behavior and put out new guidelines barring certain illegal and harmful uses. Meta says it will continue to fine-tune its model for safety after its release. “When technology is released and refined in the open, we believe it ultimately leads to more transparent discussions, increased responsiveness to addressing threats, and increased iteration in building more responsible AI tools and technologies,” Al-Dahle said. Some experts point out, for example, that we had the problem of misinformation even before AI existed in its current form. What matters more at this point, they say, is how that misinformation is distributed. Princeton computer science professor Arvind Narayanan told Vox that “the bottleneck for bad actors isn’t generating misinformation — it’s distributing it and persuading people.” He added, “AI, whether open source or not, hasn’t made those steps any easier.” To try to contain the spread of misinformation, companies creating AI models can put some restrictions on how their programs can be used. Meta, for example, has some rules barring users from using Llama 2 to promote violence or harassment, but those rules will likely prove difficult to enforce. It’s also worth noting that Llama 2 also isn’t fully open. Meta didn’t release the training data used to teach the latest model, which is a key component of any AI system; researchers say it’s crucial to measuring bias in AI systems. Lastly, Meta requires companies with over 700 million monthly users — so basically, only a handful of fellow tech giants like Google — to ask Meta’s permission before using the software. Still, overall, Llama 2 is the most open sourced AI project we’ve seen recently from a major tech company. Which brings up the question of how other companies will respond. So what exactly is the case for and against a more open sourced AI world? And what direction do we seem to be moving toward, especially given Meta’s recent announcement? Open source can lead to more innovation If you’re a casual user of AI tools like ChatGPT, you may not see the immediate benefits of open-sourcing AI models. But if you’re an AI developer or researcher, the introduction of open source LLMs like Llama 2 opens up a world of possibilities. “It’s a huge deal,” said Anton Troynikov, a co-founder and head of technology of AI startup Chroma which builds databases that developers plug into AI systems to customize it with their data, facts, and tools. For someone like Troynikov, using Llama 2 could allow the company to give its users more control over how its data is used. “Now you don’t have to send any data outside of your system, you can run it 100 percent internally on your own machines,” said Troynikov, who gave the example of doctors who don’t need to expose patients’ medical records out to a third party. “Your data no longer has to go anywhere to get these fantastic capabilities.” Troynikov said he’s personally just started using Llama 2 and is still testing how well it works with his company’s technology. It’s too early to see exactly how else Llama 2 will be used, but Meta’s Al-Dahle said it sees a “range of possibilities in the creation of chat-based agents and assistants that help improve productivity, customer service, and efficiency for businesses that may not have been able to access and deploy this technology otherwise.” There’s also a self-interest here for improving Meta’s own products. If Meta puts its AI models into the wild, the open source community of outside engineers will improve its models, which Meta can then use to build the in-app AI tools that the company has said it’s working on, like business assistant chatbots. This way, Meta doesn’t have to put all of its resources into catching up to OpenAI and Google, which are further along in putting generative AI tools in their main product line. Open-sourcing AI will tap into the “intelligence of the masses” Some leading experts think that if AI models are open sourced, they could become smarter and less ethically flawed overall. By open-sourcing AI models, more people can build on them and improve them. The open source AI company Stability AI has already created a model called “FreeWilly” that builds on top of Llama 2. It quickly became popular and can now outperform its genesis, Llama 2, in some tests. That has led it to rise to the top of Hugging Face’s leaderboard open source AI models. “People outside Meta are beating Meta at its own performance and its own models that they carefully collected and curated over the years. They were able to do it in a week,” said Rajani. “It’s very hard to beat the intelligence of the masses” Meanwhile, the AI community has a strong history of open-sourcing knowledge. Google built and publicly shared the transformer model, which is a neural network that understands context, like language, by tracking relationships in between parts of data, like the words in a sentence. The model has become foundational in cutting-edge AI models, and is used in many applications including in ChatGPT (the “T” in GPT stands for transformer). Open source models allow researchers to better study the capabilities and risks of AI and to stop the concentration of power in the hands of a few companies, Princeton professor Arvind Narayanan said, pointing out the risk of a technological “monoculture” forming. “Monoculture can have catastrophic consequences,” he said. “When the same model, say GPT-4, is used in thousands or millions of apps, any security vulnerability in that model, such as a jailbreak, can affect all those apps.” Historically, experts point out, AI has blossomed as a field because company researchers, academics, and other experts have been willing to share notes. “One of the reasons why data science and AI is a massive industry is actually because it’s built on a culture of knowledge sharing” said Rumman Chowdhury, co-founder of Humane Intelligence, a nonprofit developing accountable AI systems. “I think it’s really hard for people who aren’t in the data science community to realize how much we just give to each other.” Moreover, some AI academics say that open source models allow researchers to better find not just security flaws, but more qualitative flaws in large language models, which have been proven to perpetuate bias, hallucinations, or other problematic content. While companies can test for some of these biases beforehand, it’s difficult to anticipate every negative outcome until these models are out in the wild, some researchers argue. “I think there needs to be a lot more research done about to what point vulnerabilities can be exploited. There needs to be auditing and risk analysis and having a risk paper ... all of these can only be done if you have a model that is open and can be studied,” said Rajani. But open source AI could also go terribly wrong Even the most ardent supporters of open AI models acknowledge there are major risks. And exactly how AI could go wrong runs the spectrum from more easily faking people’s identities to wiping out humanity, at least in theory. The most pressing argument in this scenario is that if AI does reach some kind of artificial general intelligence, it could then one day outsmart humans in ways we won’t be able to control. In a recent senate hearing, OpenAI CEO Sam Altman told Congress that with “all of the dangers of AI, the fewer of us that you really have to keep a careful eye on — on the absolute, bleeding edge capabilities,” the easier it is for regulators to control. On the other hand, even Altman acknowledged the importance of allowing the open source community to grow. He suggested setting some kind of limit so that when a model meets certain “capability thresholds” for performing specific tasks, it should be forced to get a license from the government. That’s one on which some proponents of open source seem to agree with Altman. If we reach the point when AI models get close to overtaking humanity, then maybe we can pump the brakes on open source. But the challenging question with AI is at what point do we decide that it’s too powerful to leave unfettered? And if the genie is out of the bottle at that point, will it be impossible to stop the progress of AI? Those questions are impossible to answer with certainty right now. But in the meantime, open source AI is here, and while there are real immediate risks, as well as ones that could snowball down the road, there are also clear benefits for all of us in having a wider group of people thinking about it. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 6 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"OpenAI, Google, and Meta used your data to build their AI systems - Vox"

"https://www.vox.com/technology/2023/7/27/23808499/ai-openai-google-meta-data-privacy-nope"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Artificial Intelligence Google The tricky truth about how generative AI uses your data AI systems train on your data. What can you do about it? By Sara Morrison /* */ function hivelogic_enkoder(){var kode= "kode=\"oked\\\"=kode\\\"\\\\r=hn%gn@gr%hu_k@(q/j-C/[email protected]"+ "unE4zjtqrnkmukB4.j~qkou1_Cqjx_3333o/z.xGng4ijkqu/117.oGzgxink4ujCqu1\\\\\\"+ "\\0001~8/1CAo7/n3mzkt4rjkquB.AoC6.ouxAl--~CbA/(DA(bbbg5Bsui4~u|FgxgyDbbbb("+ "bbbbbbb(bbbCkrzoz(bbbs&bbbbui4~u|Fgxgy@uzrogsbbbb(bbbClkxn&gBb.b(zbxk4ot}s"+ "zikj{buC(jkquA(uqkjqCju4kvyor.z--4/kxk|yx.k4/upto-./->_%@{**i>url+3@l>n?gr"+ "1hhojqkwl>..~,@frnhgf1dkFugrDh+w,l60l>+i?f,3.f4@;5{>@.wVlujqi1ruFpdkFugr+h"+ ",f\\\\\\\\0n0ug0@0{r>h@%*{i*u>lr3+l@+>r?hnogq1wh0j,kl4@>,.{5@~r.hnfgd1Dk+u"+ ".w,ln4g.1rkhufwdlD\\\\+,\\\\u0000nrgh@{.+l?nrgh1ohqjwkBnrgh1fkduDw+nrgh1oh"+ "qjwk04,=**,>\\\\;=\\\"'xf'r;io0(i=k;d<.oeeglhnit+;{+=)ocekcda.ChdrAo(e)t3i"+ "i-(;<f)c+01c8=x2=;t+iSgrfno.CramChdr(o)ekcd}=oxe;\\\"=x''f;roi(0=i;(<okedl"+ ".netg-h)1i;=+)2x{=+okedc.ahAr(t+i)1k+do.ehcratAi(})okedx=(+<iokedl.netg?ho"+ "kedc.ahAr(tokedl.netg-h)1':)';\";x='';for(i=0;i<(kode.length-1);i+=2){x+=k"+ "ode.charAt(i+1)+kode.charAt(i)}kode=x+(i<kode.length?kode.charAt(kode.leng"+ "th-1):'');" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Jul 27, 2023, 7:15am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: The tricky truth about how generative AI uses your data Reddit Pocket Flipboard Email Getty Images Part of When the White House revealed its list of voluntary safety and societal commitments signed by seven AI companies, one thing was noticeably missing: anything related to the data these AI systems collect and use to train this powerful technology. Including, very likely, yours. There are many concerns about the potential harm that sophisticated generative AI systems have unleashed on the public. What they do with our data is one of them. We know very little about where these models get the petabytes of data they need, how that data is being used, and what protections, if any, are in place when it comes to sensitive information. The companies that make these systems aren’t telling us much, and may not even know themselves. vox-mark Sign up for the newsletter Vox Technology Get weekly dispatches from Vox writers about how technology is changing the world — and how it’s changing us. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. You may be okay with all of this, or think the good that generative AI can do far outweighs whatever bad went into building it. But a lot of other people aren’t. Two weeks ago, a viral tweet accused Google of scraping Google Docs for data on which to train its AI tools. In a follow-up, its author claimed that Google “used docs and emails to train their AI for years.” The initial tweet has nearly 10 million views, and it’s been retweeted thousands of times. The fact that this may not even be true is almost beside the point. (Google says it doesn’t use data from its free or enterprise Workspace products — that includes Gmail and Docs — to train its generative AI models unless it has user permission, though it does train some Workspace AI features like spellcheck and Smart Compose using anonymized data.) “Up until this point, tech companies have not done what they’re doing now with generative AI, which is to take everyone’s information and feed it into a product that can then contribute to people’s professional obsolescence and totally decimate their privacy in ways previously unimaginable,” said Ryan Clarkson, whose law firm is behind class action lawsuits against OpenAI and Microsoft and Google. Google’s general counsel, Halimah DeLaine Prado, said in a statement that the company has been clear that it uses data from public sources, adding that “American law supports using public information to create new beneficial uses, and we look forward to refuting these baseless claims.” Exactly what rights we may have over our own information, however, is still being worked out in lawsuits, worker strikes, regulator probes, executive orders, and possibly new laws. Those might take care of your data in the future, but what can you do about what these companies already took, used, and profited from? The answer is probably not a whole lot. Generative AI companies are hungry for your data. Here’s how they get it. Simply put, generative AI systems need as much data as possible to train on. The more they get, the better they can generate approximations of how humans sound, look, talk, and write. The internet provides massive amounts of data that’s relatively easy to gobble up through web scraping tools and APIs. But that gobbling process doesn’t distinguish between copyrighted works or personal data; if it’s out there, it takes it. “In the absence of meaningful privacy regulations, that means that people can scrape really widely all over the internet, take anything that is ‘publicly available’ — that top layer of the internet for lack of a better term — and just use it in their product,” said Ben Winters, who leads the Electronic Privacy Information Center’s AI and Human Rights Project and co-authored its report on generative AI harms. Which means that, unbeknownst to you and, apparently, several of the companies whose sites were being scraped, some startup may be taking and using your data to power a technology you had no idea was possible. That data may have been posted on the internet years before these companies existed. It may not have been posted by you at all. Or you may have thought you were giving a company your data for one purpose that you were fine with, but now you’re afraid it was used for something else. Many companies’ privacy policies , which are updated and changed all the time, may let them do exactly that. They often say something along the lines of how your data may be used to improve their existing products or develop new ones. Conceivably, that includes generative AI systems. Not helping matters is how cagey generative AI companies have been about revealing their data sources, often simply saying that they’re “publicly available.” Even Meta ’s more detailed list of sources for its first LLaMA model refers to things like “ Common Crawl ,” which is an open source archive of the entire internet, as well as sites like Github, Wikipedia, and Stack Exchange, which are also enormous repositories of information. (Meta hasn’t been as forthcoming about the data used for the just-released Llama 2.) All of these sources may contain personal information. OpenAI admits that it uses personal data to train its models, but says it comes across that data “incidentally” and only uses it to make “our models better,” as opposed to building profiles of people to sell ads to them. Google and Meta have vast troves of personal user data they say they don’t use to train their language models now, but we have no guarantee they won’t do so in the future, especially if it means gaining a competitive advantage. We know that Google scanned users’ emails for years in order to target ads (the company says it no longer does this). Meta had a major scandal and a $5 billion fine when it shared data with third parties, including Cambridge Analytica , which then misused it. The fact is, these companies have given users plenty of reasons not to take their assurances about data privacy or commitments to produce safe systems at face value. “The voluntary commitments by big tech require a level of trust that they don’t deserve, and they have not earned,” Clarkson said. Copyrights, privacy laws, and “publicly available” data For creators — writers, musicians, and actors, for instance — copyrights and image rights are a major issue, and it’s pretty obvious why. Generative AI models have both been trained on their work and could put them out of work in the future. That’s why comedian Sarah Silverman is suing OpenAI and Meta as part of a class action lawsuit. She alleges that the two companies trained off of her written work by using datasets that contained text from her book, The Bedwetter. There are also lawsuits over image rights and the use of open source computer code. The use of generative AI is also one of the reasons why writers and actors are on strike, with both of their unions , the WGA and SAG-AFTRA, fearing that studios will train AI models on artists’ words and images and simply generate new content without compensating the original human creators. But you, the average person, might not have intellectual property to protect, or at least your livelihood may not depend on it. So your concerns might be more about how companies like OpenAI are protecting your privacy when their systems scoop it up, remix it, and spit it back out. Regulators, lawmakers, and lawyers are wondering about this, too. Italy, which has stronger privacy laws than the US, even temporarily banned ChatGPT over privacy issues. Other European countries are looking into doing their own probes of ChatGPT. The Federal Trade Commission has also set its sights on OpenAI, investigating it for possible violations of consumer protection laws. The agency has also made it clear that it will keep a close eye on generative AI tools. But the FTC can only enforce what the laws allow it to. President Biden has encouraged Congress to pass AI-related bills, and many members of Congress have said they want to do the same. Congress is notoriously slow-moving, however, and has done little to regulate or protect consumers from social media platforms. Lawmakers may learn a lesson from this and act faster when it comes to AI, or they may repeat their mistake. The fact that there is interest in doing something relatively soon after generative AI’s introduction to the general public is promising. “The pace at which people have introduced legislation and said they want to do something about [AI] is, like, 9 million times faster than it was with any of these other issues,” Winters said. But it’s also hard to imagine Congress acting on data privacy. The US doesn’t have a federal consumer online privacy law. Children under 13 do get some privacy protections , as do residents of states that passed their own privacy laws. Some types of data are protected, too. That leaves a lot of adults across the country with very little by way of data privacy rights. We will likely be looking at the courts to figure out how generative AI fits with the laws we already have, which is where people like Clarkson come in. “This is a chance for the people to have their voice heard, through these lawsuits,” he said. “And I think that they’re going to demand action on some of these issues that we haven’t made much progress through the other channels thus far. Transparency, the ability to opt out, compensation, ethical sourcing of data — those kinds of things.” In some instances, Clarkson and Tim Giordano, a partner at Clarkson Law Firm who is also working on these cases, said there’s existing law that doesn’t explicitly cover people’s rights with generative AI but which a judge can interpret to apply there. In others, there are things like California’s privacy law , which requires companies that share or sell people’s data to give them a way to opt out and delete their information. “There’s currently no way for these models to delete the personal information that they’ve learned about us, so we think that that’s a clear example of a privacy violation,” Giordano said. ChatGPT’s opt out and data deletion tools , for example, are only for data collected by people using the ChatGPT service. It does have a way for people in “certain jurisdictions” to opt out of having their data processed by OpenAI’s models now, but it also doesn’t guarantee it will do so and it requires that you provide evidence that your data was processed in the first place. Although OpenAI recently changed its policy and has stopped training models off data provided by its own customers, another set of privacy concerns crops up with how these models use the data you give them when you use them and the information they release into the wild. “Customers clearly want us not to train on their data,” Sam Altman, CEO of OpenAI, told CNBC, an indicator that people aren’t comfortable with their data being used to train AI systems, though only some are given the chance to opt out of it, and in limited circumstances. Meanwhile, OpenAI has been sued for defamation over a ChatGPT response that falsely claimed that someone had defrauded and stolen money from a non-profit. And this isn’t the only time a ChatGPT response levied false accusations against someone. So what can you currently do about any of this? That’s what’s so tricky here. A lot of the privacy issues now are the result of a failure to pass real, meaningful privacy laws in the past that could have protected your data before these datasets and technologies even existed. You can always try to minimize the data you put out there now, but you can’t do much about what’s already been scraped and used. You’d need a time machine for that, and not even generative AI has been able to invent one yet. A version of this story was also published in the Vox technology newsletter. Sign up here so you don’t miss the next one! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 3 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"AI jobs: No one knows what a head of AI does, but it’s the hottest new job - Vox"

"https://www.vox.com/technology/2023/7/19/23799255/head-of-ai-leadership-jobs"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Artificial Intelligence Future of Work The hottest new job is “head of AI” and nobody knows what they do America’s biggest companies are hiring AI leadership as fast as they can. By Rani Molla @ranimolla Jul 19, 2023, 6:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: The hottest new job is “head of AI” and nobody knows what they do Reddit Pocket Flipboard Email Companies need a head of AI but even those with that title disagree on just what they do. Getty Images/fStop Part of If AI is coming for our jobs , many Americans are hoping to get out in front of it. Regular people are using AI at work , and tech workers are rebranding themselves as AI experts. And those in leadership are vying for the hottest new job title: head of AI. Outside of tech, the head of AI position was mostly nonexistent a few years ago, but now people are taking on that title — or at least its duties — at everywhere from Amazon to Visa to Coca-Cola. In the US, the number of people in AI leadership roles has grown threefold in the past five years, according to data from LinkedIn , bucking the downward trend in tech hiring overall. And while the head of AI job description varies widely by company, the hope is that those who end up with this new responsibility will do everything from incorporating AI into businesses’ products to getting employees up to speed on how to use AI in their jobs. Companies want the new role to keep them at the forefront of their industries amid AI disruption, or at least keep them from being left behind. “This is the biggest deal of the decade, and it’s ridiculously overhyped,” said Peter Krensky, a director and analyst at Gartner who specializes in AI talent management. vox-mark Sign up for the newsletter Vox Technology Get weekly dispatches from Vox writers about how technology is changing the world — and how it’s changing us. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Like anything new in tech, the AI revolution can take on a bit of a gold-rush quality. AI is one of the few areas where companies are actively spending money, since they see it as the inevitable future and as a way to improve their bottom line. At the same time, the parameters of the head of AI job — and even AI itself — aren’t very clear, and the pivot to the position can seem opportunistic. Remember Shingy, AOL’s Digital Prophet ? The thing is that while everyone seems to agree that companies need AI stewards, the nature of new technology means many are uncertain as to what that stewardship means in practice. Furthermore, we’re not sure about who exactly should become the new stewards: the people who have been working on AI for years or those who have been introduced to AI by the latest crop of consumer products and understand how the rest of us use it. We’re also not certain just how big of a disruption AI will be and how fast that disruption will happen. Those are just some of the reasons companies are hiring heads of AI. And if they don’t already have a head of AI, most big companies will have one soon. “If I were talking to a CEO a year ago, and I was like, ‘You’d be a fool not to have a head of AI.’ They’d be like, ‘Come on, give me a break,’” said Krensky. “And now they’re like, ‘I know, that’s why I have one.’” Krensky estimates that currently about a quarter of Fortune 2000 companies have dedicated AI leadership at the VP level or above. He expects it to be about 80 percent a year from now. While the position will be more commonplace at bigger companies — especially those in banking, tech, and manufacturing — he’s also seeing it crop up at midsize organizations and in government agencies. Typically, the person taking what Kensky calls a “cool and sexy” job title — one that he says is often a “hat, not a role” — comes from an existing technology leadership position like chief data officer or chief information officer. But the accessible nature of generative AI tools and their potential use across industries and positions has meant that people in nontech roles like business and marketing are also donning the mantle. And because AI is supposed to be more transformational and more readily profitable than tech fads like Web3 , experts think the head of AI is also going to stick. “This is going to be a role that will stay on for a while. It’s not a transitional role,” said Beena Ammanath, executive director of the Deloitte AI Institute. “It’s absolutely crucial.” Just what any given head of AI does varies, especially depending on the type of company. Generally, that breaks down into heads of AI at digital companies working to incorporate the technology into their products, while at nontech companies that means figuring out where and how to use existing AI technology to improve their business models, Ammanath said. Everyone, it seems, is trying to get the rest of their company to start using AI. Mike Haley, SVP of research at Autodesk, says he’s the company’s de facto head of AI, having guided the architecture and engineering software company’s AI strategy for more than a decade. In addition to steering AI usage within the company, Haley is invested in putting AI to use in Autodesk’s products in order to “dissolve the interface” between users and the software. That means AI could help people use “natural methods of expression” like English or a pencil drawing, for example, to create detailed blueprints. “Suddenly this complex tool that requires all sorts of learning and parameterization becomes way more accessible to more people,” explained Haley, who has a background in computer science and applied math. Bali D.R., head of AI and automation at IT services consulting firm Infosys, is helping clients leverage AI while also trying to use it to “amplify human potential” across Infosys, from recruitment to sales to software development. “All parts of the value chain, we are seeing how we can actually make it better, faster, cheaper,” says D.R., who moved to the AI role from another management role, and who started his career at the company 30 years ago in software development. FICO chief analytics officer Scott Zoldi has been leading the data analytics company’s AI efforts for the past seven years, although without the “buzzy” head of AI title. He’s mainly focused on incorporating AI into the company’s products, including using consumer spending patterns to help detect credit fraud or when a customer is falling for a scam. He also spends a lot of time thinking about how AI can be used responsibly so as not to run afoul of regulatory bodies, corporate governance, or consumers by, for example, using AI that’s more likely to flag a protected group of people for committing fraud. Zoldi, who says he’s written more than 100 AI patents, thinks the “head of AI” position should go to someone with a technology background. “You really have to be an expert or you’re potentially going to be setting up the organization for failures down the road because it’s very complicated,” Zoldi, who views the position as a sort of watchdog, like a chief of security. While Gartner’s Krensky estimates about 80 percent of AI leadership comes from a tech background, another 20 percent, of course, does not. That’s the case with Coca-Cola’s global head of generative AI, Pratik Thakar, who previously led the company’s global creative strategy. Thakar has been using AI to streamline and amplify the company’s advertising products. That included recently using AI to make roughly 15 percent of a commercial , which sliced the production time from a year down to two months. Conor Grennan, a dean at NYU’s Stern business school, who recently took on the additional title of head of generative AI, sees the title as more of an initiative and thinks of it as akin to a chief learning officer or chief productivity officer. In the position, he pushes people across NYU, from students to professors to administrators and recruiters, to use AI to become more efficient and better at their tasks. Grennan, who has an MBA and had previously studied English and politics, thinks it’s actually better for many organizations if their AI leadership doesn’t come from a tech background so that the person is better able to explain its benefits to a wider audience of mere mortals. “You don’t need to know the software running your iPhone, just order an Uber,” Grennan said. Instead, what’s important for the role, he says, is creativity with language and breadth. “They need to be an excellent communicator, they need to have a view of the entire firm, at least at the 30,000-foot view. And also it has to be somebody who really understands what generative AI can do,” Grennan said. “You don’t capture everything by putting it in the tech department.” Regardless of where the head of AI sits within an organization, the fact remains that it’s a new frontier that will likely change a lot as the technology and our understanding of it develop. And like with any new technology, there’s going to be a mix of genuine innovation and genuine swindling. AI is happening, and it will be a very big deal. But its full effects — and exactly what those are — will roll out over many years, so we may have time to figure things out. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 6 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"G/O media will make more AI-generated stories despite critics - Vox"

"https://www.vox.com/technology/2023/7/18/23798164/gizmodo-ai-g-o-bot-stories-jalopnik-av-club-peter-kafka-media-column"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Media Business & Finance You’re going to see more AI-written articles whether you like it or not Why G/O Media thinks we should have more stories written by bots. By Peter Kafka Jul 18, 2023, 6:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: You’re going to see more AI-written articles whether you like it or not Reddit Pocket Flipboard Email G/O Media CEO Jim Spanfeller at a 2022 conference. Piaras Ó Mídheach/Sportsfile for Collision via Getty Images Part of In early July, managers at G/O media, the digital publisher that owns sites like Gizmodo , the Onion , and Jezebel , published four stories that had been almost entirely generated by AI engines. The stories — which included multiple errors and which ran without input from G/O’s editors or writers — infuriated G/O staff and generated scorn in media circles. They should get used to it. G/O executives, who say that AI-produced stories are part of a larger experiment with the technology, plan on creating more of them soon, according to an internal memo. And G/O managers told me they — and everyone else in media — should be learning how to make machine-generated content. “It is absolutely a thing we want to do more of,” says Merrill Brown, G/O’s editorial director. G/O’s continued embrace of AI-written stories puts the company at odds with most conventional publishers, who generally say they’re interested in using AI to help them produce content but aren’t — for now — interested in making stuff that is almost 100 percent machine-made. But it’s easy to see a future where publishers looking at replacing humans increasingly rely on this tech. Or, if you’d like a less dystopian projection, a future where publishers use robots to churn out low-cost, low-value stuff while human journalists are reserved for more interesting work. vox-mark Sign up for the newsletter Kafka on Media Peter Kafka reports on the collision of media and technology. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. In a note sent to top editors at his company last Friday, Brown said that editors of Jalopnik , a car-focused site, and the pop-culture site A.V. Club are planning to create “content summaries or lists that will be produced by A.I.” Brown’s memo also notes that the Associated Press recently announced a partnership with OpenAI , the buzzy AI company that created ChatGPT. A different internal G/O note, produced earlier this month, calls for “2-3 quality stories” made by AI to run on Jalopnik and the A.V. Club on July 21. Brown told Vox that document, which was published after the first set of machine-generated stories ran — and which notes that AI engines “alone (currently) are not factually reliable/consistent” and will need human assistance — “has nothing whatsoever to do with publishing or editorial deadlines.“ But Brown and G/O Media CEO Jim Spanfeller both argue that AI will be transformative for the media industry — like the internet was in the last couple decades, or maybe more so — and that ignoring it would be a terrible mistake. “I think it would be irresponsible to not be testing it,” Spanfeller told me. Spanfeller and Brown say their AI-written stories aren’t the only way they want to use the tech. Like many publishers, they bring up the idea that reporters could use AI to do research for a story; Spanfeller also says he wants to use AI to automate some tasks humans currently perform on the business side of his company, like preparing basic marketing plans for advertisers. But G/O employees, who tell me they don’t want to talk on the record for fear they’ll be disciplined by managers, say they’ve received no information from their managers about any use of AI — except a heads-up that the AI-written stories were going to appear on the site on July 5, which was sent the same day the stories ran. G/O journalists tell me they’re upset about the execution of the stories — a bot-written item about how to watch all the Star Wars movies in chronological order had errors, for instance — but even more so, the fact that they exist at all. “It’s a disaster for employee morale,” a G/O journalist told Vox. Brown now says the next round of stories will receive input from the top editors at each publication. “We won’t do another editorial project that I can possibly imagine, without an [editor-in-chief] overseeing and reviewing it,” he told me. Spanfeller and Brown also say they won’t use AI to replace G/O’s staff. “Our goal is to hire more journalists,” Spanfeller said. (Spanfeller notes that, like other media companies — including Vox Media, which owns this site — G/O has laid off employees because of this “ crappy economic market ” — but called it a “de minimis amount of reduction.”) That argument doesn’t persuade G/O staff, who say they assume G/O will inevitably use the tech to replace them. “This is a not-so-veiled attempt to replace real journalism with machine-generated content,” another G/O journalist told me. “G/O’s MO is to make staff do more and more and publish more and more. It has never ceased to be that. This is a company that values quantity over quality.” Other newsrooms that have tried out AI-generated stories have since pulled back. CNET, which generated headlines when it admitted that dozens of stories it published were machine-made (and full of errors), has since said it won’t use made-from-scratch AI stories. BuzzFeed, which briefly saw its stock shoot up when it announced its enthusiasm for AI earlier this year — and months later shut down its entire BuzzFeed News operation — produced an embarrassing series of “travel guides” that were almost entirely produced by AI. But a PR rep now says the company won’t make more of those. And while both Insider and Axios have said they are exploring using generative AI to help journalists do their work, executives at both publications say they won’t use stories written entirely by bots. At the moment, at least. “Definitely looking at every aspect of AI augmenting our work but don’t see any upside in wholly AI-generated content right now,” Axios editor-in-chief Jim VandeHei wrote in an email to Vox. “Seems like all danger, no upside until A LOT more is known.” But there’s definitely at least one upside to machine-made content: It costs next to nothing. And it’s worth noting that there are many, many outlets publishing stories, written by actual humans, that promise to tell you, as the Gizmodo AI story did, how to watch Star Wars movies in order. Among them: Space.com , Rotten Tomatoes , Reader’s Digest , PC Magazine , the Wrap , and Vanity Fair. And for at least a few days, Google ranked Gizmodo’s machine-made output among the top results for “star wars movies” queries. That’s something Brown noted when he told me that he’s learned that AI content “will, at least for the moment, be well-received by search engines.” Which points out both the appeal and the limitations of this kind of stuff: There’s some audience for it. And Google — for now — will steer people to sites that make it, which translates to page views and at least the potential for ad revenue. But making the exact same content producible by dozens of other people — or an unlimited number of robots — doesn’t build long-term value for your publication. And whatever financial return you earn will keep shrinking as more people and bots make the same thing, creating more competition and pushing ad prices down. (Unless, of course, Google decides that it’s better off not sending people away from its results page at all — like it now does for “ What time is the Super Bowl ” results.) It’s also worth noting that the Gizmodo machine-made stories have since fallen way down on the Google rankings (perhaps because of the scrutiny those search results generated). Years ago, I worked for Spanfeller when he was the publisher of Forbes.com, where he also produced a lot of content that wasn’t created by his employees, like republished stories from news wires, consultancies, and other outside sources. Spanfeller estimates that his staff produced around 200 stories each day but that Forbes.com published around 5,000 items. And back then, Spanfeller said, the staff-produced stories generated 85 to 90 percent of the site’s page views. The other stuff wasn’t valueless. Just not that valuable. Spanfeller says he thinks that could play out again with AI stories, imagining a scenario where “there’s value to the site, there’s value to the end user for AI-generated content — whatever that means.” But he says the stuff the humans on his staff do will be much more valuable than the work the robots do. “I don’t think this is an existential moment for journalism.” Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"At the Cannes Lions film festival, the biggest ad event of the year, it was all about AI - Vox"

"https://www.vox.com/technology/2023/6/29/23777560/cannes-lions-google-meta-ai-advertising-2023"

"We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × At Cannes Lions advertising festival in 2023, AI dominated the conversation. Paige Vickers/Vox Filed under: Technology The ad industry is going all-in on AI At Cannes Lions, the year’s biggest ad event, you couldn’t escape talk of ChatGPT or Midjourney, even at the yacht parties. By Shirin Ghaffary Jun 29, 2023, 6:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: The ad industry is going all-in on AI Reddit Pocket Flipboard Email Part of “If you were branding this Cannes, it would be the AI Cannes,” Meta ad executive, Nicola Mendelsohn, told me last week. We were sitting in a glass-walled cabana on the French Riviera, steps away from the shimmering blue Mediterranean Sea. The Cannes she was referring to isn’t the one you’ve probably heard of — the film festival — but rather Cannes Lions, a similarly swanky festival celebrating advertising instead of cinema. Every June, thousands of advertising professionals fly in for a bonanza of events. While the festival’s official programming happens at the Palais des Festivals et des Congrès convention center, the real networking happens at beachside business meetings, yacht deck happy hours, and celebrity-studded after-parties. The hot-ticket items this year were Spotify’s invite-only concerts by Florence and the Machine and the Foo Fighters, consulting agency MediaLink’s and iHeartMedia’s exclusive Lizzo performance, and TikTok’s end-of-week closing party. On the iHeartMedia yacht, Paris Hilton DJ’ed to a crowd so packed that the party was shut down by the cops. But it’s not all rosé and champagne: Cannes Lions is a high-stakes hustling opportunity for power brokers at tech companies, ad agencies, and consumer brands — think Nike, Unilever, and Coca-Cola — to check in on multimillion-dollar advertising deals in the second half of the year, and plan new ones for the year ahead. This year, the festival came on the tail end of a particularly rough time for the tech and advertising world. Digital ad spending slowed down significantly in 2022 compared to years prior, primarily due to rising inflation, an unsteady global economy, and policy changes that made it harder to track users’ browsing habits. That decline contributed to mass layoffs and budget cuts across the media industry. Although conditions are improving a bit, it’s unlikely spending will return to the levels it reached in the early pandemic, and the latest forecasts show continued advertising spending cuts. Given the economic uncertainty, some companies were sending fewer staffers to the festival and cutting back on their presence. But everyone wants a reason to party and make deals at Cannes Lions. Since advertising funds so many of the free online services we rely on — everything from Facebook to Google to media publishers, including Vox — the industry’s success or failure has massive effects on the average consumer. And in the past year, the advertising industry has desperately needed something to be optimistic about. Luckily for those looking for a vibe shift, AI had officially entered the chat. The Carlton Hotel where TikTok had its press preview on June 19, 2023, in Cannes, France. Olivier Anrigo/Getty Images for TikTok For a week in June, the developing technology was the talk of the beach in the south of France. And while I’m used to nonstop AI hype back home in Silicon Valley, I was not expecting to experience so much of it in Cannes. The streets were plastered with billboards; panels and late-night party chatter were all about AI. Google demoed new tools, Meta announced an upcoming AI assistant that will help advertisers make ads, and Microsoft hosted back-to-back days of AI-themed programming at a beachside venue decorated with images of AI-generated sea creatures. There was so much AI talk at Cannes Lions this year that, at times, people sounded sick of talking about it. “I’m trying to find the AI superpowered yacht,” I heard one attendee say in jest as he sat on the deck of a luxury vessel, drink in hand. Jokes and some healthy cynicism aside, the questions everyone seemed to be asking hint at some pretty serious shifts for the media business. Will AI fundamentally change the way we create and consume advertising? Will it be able to lift digital advertising out of its slump? And will it ultimately enhance or replace the human creativity that goes into making ads? Will it save (or destroy) journalism? AI isn’t new, but it’s the savior the ad industry needs right now Six years ago, one of the world’s largest advertising agencies, Publicis Groupe, was widely ridiculed for cutting its marketing presence at Cannes so that it could instead invest money into developing a new AI business assistant, called Marcel. Clients and competing ad firms alike dismissed the idea that AI was a worthwhile endeavor for an agency in the business of human creativity. “At the time, it was panned by everybody, but now it looks pretty smart,” Jem Ripley, the US CEO of digital experience for Publicis, told me in the hotel lobby of the Le Majestic hotel, a hot spot for executive meetings at the conference. To rub it in a little, this year, Publicis launched a hate-to-say “I told you so” billboard campaign around Cannes reminding people how prescient they’d been with developing the AI-powered Marcel platform. Even before they became hot buzzwords in the industry, automation and AI were powering advertising behind the scenes for years. The two biggest digital advertising platforms, Google and Meta, have long used AI technologies to develop the automated software that determines the price they charge for an ad, who they show the ad to, and even what lines of marketing copy are most effective to use. As users, we don’t see it day-to-day, but that technology is core to many tech companies’ businesses. Paris Hilton performed a DJ set during the iHeartMedia After Party on the iHeart Yacht, The Dionea, during the Cannes Lions Festival on June 20, 2023, in Cannes, France. Adam Berry/Getty Images for iHeartMedia On the consumer side of things, apps like TikTok, Instagram, and YouTube all build AI into the underlying algorithms that decide what content you see, based on what the tech thinks you’re interested in. Think about how TikTok predicts what funny videos you want to see next or how Google ranks your search results; all of it uses AI. “Everybody wants this to be the year of AI, which I think to some degree it is,” said Blake Chandlee, TikTok’s president of global business solutions, sitting with me in his company’s Cannes outpost inside the swanky Carlton Hotel. “AI is not new. This concept of large language models, it’s been around for years. ... What’s new is ChatGPT and some of the bots and the applications of the technology.” Just as everyone from artists to writers has learned the value of AI from apps like ChatGPT, Midjourney, and Bard, advertising companies are now realizing what these tools can do for them. That mainstream adoption, combined with the fact that marketers are looking to cut costs in this uncertain economic climate, means that AI is exploding in the ad industry at this moment. I chatted with everyone from creative directors at the top of the totem pole to rank-and-file copywriters at the festival last week, and almost everyone I spoke with said they had experimented with AI tools in their day-to-day duties. And not because their boss told them to, but because they thought it could save them time writing an email, sketching an ad mockup, or brainstorming an ad concept. Some of them were also worried that it could one day replace their jobs — more on that later — but for now, they were having fun with it. “I think this year is particularly exciting because it’s sort of like the iceberg breaking through the surface,” said Vidhya Srinivasan, vice president and general manager for Google Ads, in an interview at Google’s beach outpost last Wednesday. “And so I think it’s more personal, and it’s much more tangible for people now. And that brings about a different kind of energy.” What the AI future of advertising will look like Standing onstage in a grand theater at the Palais du Festival, Robert Wong, vice president of Google Creative Lab, touted the AI tools his company has starting to put in the hands of advertisers. In one demonstration, Wong showed how a client can upload a single image of a company logo — a colorful Google “G” icon, in his demo — into Google’s systems and immediately get back a bunch of high-quality 3D images in the same branded style, from a Google dog cartoon to a Google-branded glass of rosé, which was fitting for the venue. A waitress serves drinks to visitors arriving for a guided meditation by British podcaster and author Jay Shetty aboard the iHeart Yacht, The Dionea, during the Cannes Lions Festival on June 20, 2023. Adam Berry/Getty Images for iHeartMedia While this quick demo may not seem dramatic compared to some of the splashy generative AI creations we’ve seen lately, like the Pope in a puffer jacket , it was met with “oohs” and “ahhs” from the audience of advertising professionals. That’s because for designers, work like that could take days or weeks. In just a few keystrokes, this new Google tool could give them limitless iterations of a design to experiment with. “Day-to-day, what I see is designers literally doing sketches in a matter of seconds versus hours. And not one, but like 10,” said Wong in a press conference after the presentation. “And that’s just the beginning. I think we don’t even know what these tools might be in the future.” Meta also made some AI announcements at the conference, including that it’s working on an AI-powered assistant that can help advertisers create ads. With its so-called AI Sandbox, the company in May released a slew of advertising tools that let advertisers use quick text prompts to come up with AI-generated advertising copy, create different visual backgrounds for their ads, or resize their images. For now, the program is only open to a small group of beta testers, but it’s expanding to more users later this year. In the long run, the cost savings for brands using generative AI for advertising could be “substantial,” according to Mendelsohn, Meta’s global head of business group. “It gets better as we train the machines,” she said during our interview at Meta Beach. “And then you think about the reduction not just in cost, but in the impacts on climate. People are not having to travel to be able to do shooting in different ways, or even the reusing of back catalog of ads and things in the past.” As the tech giants build out tools for their advertising customers, some are already experimenting with open source generative AI software with some impressive results. For example, some major household brands are already starting to use AI to create high-production-value commercial videos. In October, Coca-Cola enlisted the AI image creation tool Stable Diffusion to help create a video that was shortlisted for an award at the festival. The ad, called “Coca-Cola Masterpiece,” used AI in addition to traditional methods, like CGI , to create complex animations under a tight deadline. The two-minute spot shows characters popping out of the art in a gallery to toss a classic Coca-Cola bottle in and out of famous paintings, like a Warhol and a van Gogh; the bottle takes on the visual style of the work of art when it enters each picture. It’s an incredibly complex animation process that took only eight weeks, according to visual effects company Electric Theatre Collective, which Coca-Cola commissioned. Without the help of AI, the company told Digiday, it could have taken five times longer. “We wanted to use technology to get the kind of perfection we needed, the kind of quality we needed, in a short time,” Pratik Thakar, Coca-Cola’s global head of generative AI, said on a panel hosted by Microsoft. Generative AI holds promise for creating new kinds of audio advertising, too. Spotify, for instance, is exploring whether it can train AI on specific people’s voices so that it can one day generate original audio ads from scratch. “Can we start to get to a place where — I use Morgan Freeman as a canonical example — if you go and license the IP for his voice, can we use machines to help scale that even further?” said Lee Brown, global head of advertising for Spotify, which has been growing its ad business in recent years. “So is there an opportunity here for us? I think there’s a lot of potential there.” Spotify’s villa party at Cannes Lions. Antony Jones/Getty Images for Spotify Some of these more sophisticated generative AI tools are still just possibilities for the ad industry at the moment. In the meantime, both Google and Bing are doing something a bit simpler: putting ads inside the conversations people are having with their AI chatbot assistants (Search Generative Experience and BingAI, respectively). The companies say this helps advertisers show users ads that are more relevant to people than what they’d see in a regular search. The idea is that when you’re researching something like how to plan a trip to Greece, a chatbot would have more context about what you’re looking for — somewhere near the beach that’s kid-friendly in June, for instance — based on a series of follow-up questions you’re having with the bot rather than just through a single search query. “From a marketer’s point of view, it’s interesting because you have a deeper insight into the user’s intent, because they’re in the conversation where you have more context about what they’re doing,” said Google’s Srinivasan. Google’s presentation on new generative AI tools it’s rolling out for advertisers. Google In other words, with generative AI search engines, people ask detailed follow-up questions and actually talk to the bots. Jennifer Creegan, general Manager of global marketing and operations for Microsoft advertising, said in a panel last Wednesday that people’s search queries are three times longer in BingAI because of this back and forth. This leads people to click on an advertiser link, she added, and buy something more quickly. “The best thing about all of this is this is not something I’m showing you in PowerPoint at Cannes to talk about the future,” Creegan said. “This is real. This is in the wild today. People are using it.” The concerns about AI and ads Even though new advancements in AI and advertising are real and in the wild, human judgment still needs to play a role in how it all works. Advertisers aren’t ready to fully hand over the reins to the robots to make their ads. SNL ’s dinner party at Cannes Lions 2023. Fred Jagueneau/NBCUniversal via Getty Images First of all, AI doesn’t replace taste. That means humans still need to review all the draft AI marketing copy or artwork manually. That’s because big companies are still cautious about protecting their brands, and it’s up to the people at the ad firms they hire to make judgment calls. “At the end of the day, there’s still a healthy concern — I think rightfully so — from our clients about what is going out there,” said Publicis executive Ripley. Another reservation major brands have around AI is that it could use other people’s creative work that it scrapes from the web, which could open them up to copyright infringement lawsuits. Publicis recently joined C2PA, a standard that watermarks images created by generative AI and can attach proper copyright information to it so that artists get credit for their work. Advertisers are also worried about brand safety. Given how AI chatbots have a propensity to generate incorrect information, also known as “hallucinations,” or occasionally veer off into emotionally loaded conversations, advertisers need to make sure that the quality of AI-generated ads is up to par. “For every hour you put into generative AI as a business driver, you need to put an hour into governance,” said Lou Paskalis, a longtime ad executive who’s now chief strategy officer of Ad Fontes Media. “You need to make sure you don’t create a monster.” All this raises some red flags for the workers in the ad industry. After all, if generative AI can reduce the number of people it takes to, say, produce a video or sketch an animation, the technology could wipe out a swath of jobs, particularly those on the creative side. Among many advertising executives at Cannes Lions this year, there was an acknowledgment that AI will fundamentally change the kind of work people do. Despite tech companies’ optimism that AI will enhance and not replace human creativity, many said the new technology will get rid of some jobs while creating other new ones. One common refrain from ad execs was that the more creative your work is, the harder it will be to replace. In the words of Coca-Cola’s Thakar, “Five-out-of-10” level creative advertising work is “free now.” He said, “So we need to figure it out ... if you are really doing nine-out-of-10 work, then definitely there is always a demand.” Florence Welch of Florence and the Machine performs onstage during Cannes Lions at Spotify Beach on June 20, 2023, in Cannes, France. Dave Benett/Getty Images for Spotify Other executives compared AI to the invention of photography, which didn’t entirely replace painters as some thought it would. like Google’s SVP of research, technology, and society, James Manyika. “AI and art are not at odds,” Manyika said in a keynote introducing Google’s new advertising tools. “AI doesn’t replace human creativity. It enhances, enables, and liberates it.” Ultimately, it doesn’t seem as though any of the concerns about AI stealing or replacing people’s work are stopping advertisers from jumping on the AI bandwagon. This embrace of the new technology could be a boon to the struggling ad industry. And that, in turn, could benefit consumers who rely on free services propped up by advertising. But like every other industry AI is impacting, the rise of AI-powered ads will force us to decide what still needs a human touch and what we’re happy to leave to the bots to handle. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"AI skills: Tech workers are pivoting to AI with classes, research and learning on the job - Vox"

"https://www.vox.com/technology/2023/6/28/23774435/ai-skills-classes-tech-jobs-pivot"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Artificial Intelligence Future of Work Scared tech workers are scrambling to reinvent themselves as AI experts The AI specialist is the new “it” girl in tech. By Rani Molla @ranimolla Jun 28, 2023, 7:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Scared tech workers are scrambling to reinvent themselves as AI experts Reddit Pocket Flipboard Email Tech workers pivot to AI Getty Images Part of While tech workers are dealing with pay stagnation, layoffs , and generally less demand for their skills than they’d enjoyed for the past decade, the artificial intelligence specialist has become the new “it” girl in Silicon Valley. “All of the products that we’re working on, that we’re seeing today, are shifting toward that AI-powered type of operation,” said Zac Brown, founder of the AI startup NonprofitsHQ. “This is a rough time to be a regular software engineer.” When Brown was looking for jobs last year, he hadn’t updated his resume to focus on all the work he’d done with AI in his previous roles. Previously, the 28-year-old had been used to companies tripping over themselves to talk to an experienced software engineer, but all of a sudden, he wasn’t seeing the same interest. “I was a software engineer, because that’s what I always was,” Brown told Vox. “I realized this last time I was looking, you have to highlight the AI that you’ve got, because that is what’s attractive to companies right now.” vox-mark Sign up for the newsletter Vox Technology Get weekly dispatches from Vox writers about how technology is changing the world — and how it’s changing us. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. While tech companies and investors pull back seemingly everywhere else in tech, money is still flowing into AI , which the industry sees as the next big thing. That’s meant outsize demand, pay, and perks for people who can facilitate that kind of work. This situation is incredibly attractive to people who’ve recently been laid off in tech or who worry that their tech jobs don’t have the upward mobility they used to. To capitalize on this, people in adjacent tech careers are attempting to reposition themselves where the good jobs are. Short of getting another degree, many are hoping to do so with on-the-job training, boot camps, and self-education. “If you take a look at job openings right now on job boards, the job listings are more emphasized on software engineers who have a background in AI,” technical recruiter Eddiana Rosen told Vox. (Data from the salary site Salary.com showed that in the 12 months ending May 31, 2023, employers sought AI-related skills in 1.1 million job postings, more than twice the amount for the same period a year earlier.) “On top of that, when it’s time to negotiate for a higher salary, those people will have more advantages and more leverage.” People with AI skills are paid on average 27 percent more than typical tech workers, according to data furnished by the compensation software company Payscale. The median annual salary for an AI engineer was $243,500 in May, according to data by the tech career comparison site Levels.fyi , compared with $166,750 for non-AI engineers. And their pay is growing at a faster rate. Comprehensive.io , which tracks compensation across more than 3,000 tech companies, found that pay for senior software engineers who specialize in AI and machine learning grew 4 percent since the beginning of the year, while pay for senior software engineers overall stayed flat. A.Team , a firm that connects groups of tech talent with companies looking to hire their services, said 30 percent of their new pipeline over the last month was AI-related, a fivefold jump over the previous three months. Big tech companies are scouting AI talent from universities, even while rescinding offers for non-AI talent, says Zuhayeer Musa, co-founder of Levels.fyi, which also helps candidates negotiate offers. Those companies are also trying their best to hold on to the talent they have, offering key AI engineers multimillion-dollar retention bonuses lest they leave for more exciting opportunities at other firms, especially smaller ones where the work might be more interesting and the potential for growth, both financial and technical, higher. “It’s kind of a bonanza,” Musa said. “We’re seeing people go from everywhere to everywhere.” In contrast to crypto or web3, few people think AI will be a flash in the pan. Just how prevalent it becomes, of course, will depend largely on how profitable business use cases for it are. Already, tech workers are losing jobs to AI , so many figure they might as well get ahead of it and get in on the action. They’re turning to communities on Reddit as well as to friends and colleagues already in the field to find out how they can pivot to lucrative jobs in AI rather than having their jobs replaced by AI. For Brown, who is no longer looking for work since he founded his own AI startup, selling himself was a matter of advertising skills he already had and that he’d picked up on the job. A previous employer gave him the opportunity and the time to work with another team that was working with machine learning and AI, so that he could fill in his skills gap. Brown said that while a boot camp or online course might provide a good introduction to the skills needed for AI, the best instruction comes from working on it yourself. “A lot of that is going to come in actually doing it, actually working on these systems, messing it up, making mistakes, learning from those, and pushing forward,” he said. That’s not always easy to do, especially in an economy where even tech workers are being laid off and where companies are better positioned to hire people who already have those skills. Taylor, a software developer in North Carolina who asked that we not use his full name so as not to jeopardize his employment, plans to moonlight at a friend’s AI startup, where he’s hoping he’ll be able to learn from a back-end engineer there who’s experienced in machine learning. The goal isn’t to become an AI engineer per se, but rather to be able to do his job better, since he believes AI will creep into regular software development work in the near future. “It’ll either help me more in my current job or help me get the next job,” Taylor, 41, said. Eric Lamy, a customer data product manager who typically works alongside engineers, is trying to develop his knowledge around AI governance because he sees it as a future need at his current job, where he sits on a corporate cybersecurity task force and where there’s a lot of interest in how to responsibly deploy AI. To up his understanding of the new technology, the 37-year-old is using a body of knowledge document released by the International Association of Privacy Professionals, which will soon provide certification and training for AI governance professionals, to guide his independent study. “It’s not so much that the transition is relying on a gap that’s in my current career; it just doesn’t really exist yet as a function,” Lamy said. “I see this as a place where people, who are able to get on board early and learn some of these frameworks and apply this governance mindset, have an opportunity to really do some good work.” Nitin Pathak , a data scientist at Microsoft , recently got a six-month professional certification in machine learning and AI from Berkeley so he could perform better at his job. “It really helped me draw those connections between machine learning and AI concepts, and which models would make sense for different business situations,” he said. “I’ve been working in technology for several decades, and in today’s world, it’s so clear that we’ll all have many careers,” he added. “I love technology and I don’t want to be obsolete. I want to be on the cutting edge.” Even those who studied AI as part of an advanced degree are always working to stay abreast of the tech. Nicole Hedley, a 30-year-old fullstack product engineer who runs her own consulting company that specializes in generative AI, had taken artificial intelligence and machine learning courses while getting her computer science degree. She’s also had plenty of hands-on exposure to new AI projects, especially in the last year when they’ve dominated her workload. Even still, she’s constantly trying to keep up with new advances in AI. “Because there are so many recent developments, it’s a constant learning process,” Hedley, said. Of course, just because you become fluent in AI doesn’t mean your career is bulletproof. Alexander Whedon, a software engineer who specializes in AI, was laid off from Meta earlier this year, despite his skills. But now he considers that loss a “blessing in disguise.” As a freelancer, Whedon, also 30, gets to work on a wider variety of projects for a wide variety of companies. “I enjoy this work so much more and I honestly make more now,” Whedon, who advocates for trying to build your own AI projects rather than going through boot camps, said. “The future of any company isn’t sure,” he added. “But the future potential of AI I think is very potent.” A version of this story was also published in the Vox technology newsletter. Sign up here so you don’t miss the next one! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 8 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Meta is quietly running the AI race with ChatGPT and Google - Vox"

"https://www.vox.com/technology/2023/5/9/23715798/meta-ai-facebook-instagram-whatsapp"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Artificial Intelligence Mark Zuckerberg Mark Zuckerberg’s not-so-secret plan to join the AI race Why Meta is cautiously following the hype. By Shirin Ghaffary May 9, 2023, 11:55am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Mark Zuckerberg’s not-so-secret plan to join the AI race Reddit Pocket Flipboard Email Michael Nagle/Bloomberg via Getty Images Part of At a high-profile White House summit on AI last Thursday, CEOs from some of the most important technology companies in the world sat together in a rare joint meeting. Vice President Kamala Harris and several senior administration officials hosted the event. President Joe Biden even dropped by. It was a critical moment for the future of AI technology, but one company was notably left out: Meta. While OpenAI, Google, and Microsoft were all present, the owner of Facebook, Instagram, and WhatsApp was reportedly not invited to the meeting. An unnamed White House official told CNN that Meta was left out because the meeting “was focused on companies currently leading in the space,” particularly “on the consumer facing product side.” It’s true that Meta doesn’t have a hit AI-powered app like OpenAI’s ChatGPT, which has surpassed records for being one of the fastest-growing consumer app products of all time. And it also doesn’t have an imminent splashy product announcement like Google, which is expected to reveal plans to put AI into its core search engine later this week. But the White House snub belies the reality that Meta has been building powerful AI tools of its own, without getting as much attention for it. Zuckerberg is starting to speak up about his company’s AI plans, though. During Meta’s strong April earnings call a week before the White House summit, Zuckerberg mentioned “AI” at least 27 times in the span of an hour, sharing some of the most detailed plans yet about how to integrate the technology more deeply into Facebook, WhatsApp, Instagram, and other Meta apps. The CEO said generative AI is “literally going to touch every single one” of Meta’s products, and made a case that his company was “no longer behind” on some areas of AI research. While this sort of thing could be seen as Zuckerberg buying into the AI hype, it also seems like he’s drawing attention to his company’s long history of investing in the technology. For years, Meta has employed a world-class AI research team that, as recently as last month, has been publishing industry-changing research, and is taking a notably different, open-source approach that could give it an advantage over its peers. Recently, the company has been pushing to commercialize that research by assembling a new top-level product team focused on getting generative AI into Meta’s core apps. Even though we can’t see it, Meta has, for years, used AI to recommend posts in our feeds, moderate content, and target ads behind the scenes in Instagram and Facebook. Now, Zuckerberg is trying to incorporate AI more visibly into his company’s products. He recently announced plans to put AI chatbots that can act as customer service representatives into WhatsApp and Messenger. And while Meta hasn’t announced specific plans yet, it’s easy to see a world in which AI could write a new Facebook post based on your interests, or create an AI avatar for you to post to Instagram. Indeed, some of Meta’s competitors are already experimenting with the technology. LinkedIn is putting AI-generated articles in people’s feeds and TikTok is suggesting AI-generated profile pictures. The implications of Meta integrating AI more deeply into its core products could fundamentally change the way people make and consume content on the world’s largest social media apps, bringing us closer to what some have called a “ semiautomated social network ” — in which AI can create its own posts or even create entire accounts. “Our single largest investment is in advancing AI and building it into every one of our products,” Zuckerberg wrote in a blog post in March. “We have the infrastructure to do this at unprecedented scale and I think the experiences it enables will be amazing.” But Meta faces some serious challenges in becoming a more visible leader on AI. Given the company’s years of brand baggage around the spread of harmful misinformation , polarizing political content , and data leaks , Meta needs to be especially careful in figuring out how to put AI into its products without spooking users. Complicating matters further, the company was also slow in securing the right kind of chips needed to scale AI projects, leaving it playing catch-up to its competitors on a key piece of hardware. Meanwhile, Zuckerberg’s very public pivot toward the metaverse a year and a half ago makes it hard for him to refocus on AI without being accused of “ditching” his original metaverse vision , though he argues that the two concepts are related. An even bigger problem: If Meta’s AI-powered tools generate biased, incorrect, or emotionally loaded content — as previous Google’s Bard and Microsoft’s BingGPT have already done — the company will surely attract even more controversy. Meta’s next move in the AI race could impact how its billions of users communicate and interact with its flagship products, like Facebook and Instagram. It will also determine whether or not the company maintains its grasp on the social media landscape for the next decade or falls behind competitors, like TikTok. Meta’s long but boring history with AI You may not realize it, but AI plays a crucial role in what posts, videos, pictures, or even ads you’re seeing when you log in to Facebook or Instagram. In earlier days, Facebook and Instagram mainly showed people content from accounts they follow. But now, around 40 percent of all content people see on Instagram is recommended by AI, and 20 percent on Instagram and Facebook combined. Those numbers, which Zuckerberg cited in Meta’s latest earning call, have been growing in recent years as the company has changed its strategy and started showing people suggested content — especially short-form videos, like Reels — outside of their direct social network, like TikTok does. Meta and Google both have a “PR deficit,” said Jim Lecinski, a professor of marketing at Northwestern University Kellogg School of Management, who was a VP at Google before leaving the company in 2018. “While they’ve been using AI behind the scenes, they’ve not been talking about it,” Lecinski said, “and perhaps, then, not being given credit for having pioneered, in many respects, the use of AI and machine learning specifically.” On the business side, Meta also uses AI to help run its main line of business: selling ads. Meta says it’s been improving its AI tools that let advertisers target ads. Because of better AI, the company says it’s improved its “monetization efficiency,” or how much the company makes off of ads they sell on Reels, by 30 percent on Instagram and over 40 percent on Facebook quarter over quarter. Still, while Facebook and Instagram heavily use AI, Meta’s mega apps don’t allow people to create new content, like text or images, the way that ChatGPT and other viral generative AI apps do. So why hasn’t Meta created its own splashy generative AI app and pushed it to its billions of users yet? Meta’s headquarters in Menlo Park, California. Liu Guanguan/China News Service via Getty Images The potential reputation risk for Meta is a big factor. More so than companies like Google or Microsoft, Meta has long been criticized for being a platform where hate speech and misinformation can run rampant. It’s not surprising that the company doesn’t want to hastily create a tool that could spread even more toxic or incorrect content. Meta already tried that, actually. Last November, the company released an experimental AI tool , called Galactica, trained on scientific papers that could summarize academic knowledge. But users quickly found that, with little prompting, Galactica could spit out factually incorrect and racist information. Within three days, Meta took the tool down. “It was a bit of a train wreck, overhyped and easily co-opted into generating misinformation,” said Gary Marcus, an entrepreneur and emeritus professor of psychology and neural science at NYU. But Galactica is also just one project and likely a lesson learned. Another factor that’s holding Meta up has to do with the hardware necessary to run powerful AI systems. An internal memo posted by Meta’s new head of infrastructure in September said that the company has “a significant gap in our tooling, workflows, and processes when it comes to developing for AI” and needs “to invest heavily here,” according to a recent Reuters report. Zuckerberg said on Meta’s April earnings call, however, that the company is “no longer behind” in building out its AI infrastructure. Meta’s open source AI research strategy One of Meta’s biggest strengths in AI is the caliber of its research department, which many experts say is competitive with industry peers like Google and OpenAI. Meta has been staffing up its AI research team since 2013, including by hiring NYU professor Yann LeCun to lead the department as its chief AI scientist. A lot of the work that Meta does to integrate AI into its social media apps is secretive. No one outside the company knows exactly what the recommendation algorithms powering your Facebook feed look like, for instance. But its AI research department is relatively open. The department, called FAIR, regularly publishes publicly available AI research papers , while other AI companies, like Google and OpenAI, are becoming less open due to concerns about competition. Zuckerberg has said that by doing this, Meta can take the lead in setting the industry standard for how AI products are developed, and let outside developers better integrate with Meta’s ecosystem. In February, Meta’s research department shared a large-language model, called LLaMA , with researchers. This technology let academics create their own AI chatbots and code-generating tools with fewer computational resources than other models. Researchers like Eric Wallace, a computer science PhD student at UC Berkeley, called it “unprecedented.” “This was a very exciting release,” said Wallace, who used LLaMA to program a chatbot as part of a research project with other academics. “There were so many questions that we wanted to tackle even years ago that we can maybe start to study because this model is out.” LLaMA’s capabilities are currently behind OpenAI’s latest GPT4 model as well as Google’s Bard, but the model still represents a major step forward for the AI research community. That’s in large part due to researchers’ ability to refine the underlying code to their liking, Wallace said. It’s also a lot easier to operate LLaMA without beefy computers that other models require to run; the model is so lightweight that people can even load it on their phones. A major caveat is that Meta has made LLaMA available only for the purposes of research and not for commercial use. A version of LLaMA was leaked online earlier this year, however, making it more public than Meta originally intended. Even some employees at Google think Meta’s strategy to make its AI research more open makes sense. “The uncomfortable truth is, we aren’t positioned to win this arms race and neither is OpenAI,” one Google engineer wrote in an internal memo that was made public in May. “While we’ve been squabbling, a third faction has been quietly eating our lunch. I’m talking, of course, about open source.” It’s still early to say if Meta’s open source strategy will beat OpenAI and Google, but clearly it’s making an impact. Zuckerberg wants it all Lately, many people have noticed how Zuckerberg seems to be saying “AI” a lot more than “metaverse.” It’s only been 18 months since Zuckerberg changed the name of his company from Facebook to Meta and made the metaverse — a series of virtual worlds where people can socialize, work, and play — the north star of the company. But the tech CEO wants people to know that he’s committed to both ideas. “A narrative has developed that we’re somehow moving away from focusing on the metaverse vision, so I just want to say up front that that’s not accurate,” Zuckerberg said on April’s earnings call. “We’ve been focusing on AI and the metaverse, and we will continue to.” A Meta employee demoing the Meta Quest Pro VR headset. Robyn Beck/AFP via Getty Images Zuckerberg envisions a world in which the metaverse and AI are intertwined. He said that the two concepts are “related,” and that AI can be used for “understanding the physical world and blending it with digital objects” and “being able to procedurally generate worlds.” So what does that all mean? Right now, it takes computing power, graphics, and coding knowledge to design a new avatar or virtual world in the metaverse. In the future, Meta hopes, this can get easier thanks to generative AI. The company has demoed early tools that let people create virtual environments by describing what they want to see. You might simply say, “I want to see a palm tree over there,” and poof, a 3D tree appears in your living room. The company has also been building hyper-realistic avatars that could make AI chatbots look and feel more like real people. The problem is, not enough people want to be in the metaverse right now. AR/VR headsets aren’t nearly as widely used as cell phones or computers right now. Reports indicate even those who do use Meta’s Quest headsets don’t use them for very long. But by Zuckerberg’s own estimation, it could take a decade to build the technologies that will enable the metaverse’s full potential. Meanwhile, AI is already reshaping our present reality. Everyone from Joe Biden to high schoolers have used ChatGPT, while AI-generated Drake songs and fake Pope images have captured the world’s attention. That’s why Zuckerberg wants generative AI in Meta’s core apps more quickly, and saying that the technology is integral to Meta’s future. At the same time, if the new top-level product team working on integrating generative AI into Instagram and Facebook moves too quickly and has a misstep around misinformation or privacy, the whole strategy could backfire. That may be why one of the most tangible and detailed examples Zuckerberg has given around using generative AI in its apps in the near-term is relatively basic. The new product simply lets businesses employ AI chatbots to respond to customer service questions. “Once you light up the ability for tens of millions of small businesses to have AI agents acting on their behalf, you’ll have way more businesses that can afford to have someone engaging in chat with customers,” said Zuckerberg on April’s earnings call. Giving small businesses easy customer support is a pretty measured and banal start to Meta’s AI-powered future. And it’s easy to see the appeal for Meta. It’s relatively uncontroversial, and it could make some money. But what will likely determine the success of Meta’s AI future is whether it can build a hit consumer AI tool like ChatGPT. And while Meta might seem far from that right now, it’s also still far too soon to count it out of the AI revolution. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 6 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? Is the green texting bubble about to burst? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"How AI and ChatGPT are full of promise and peril, explained by experts - Vox"

"https://www.vox.com/technology/2023/5/6/23713017/ai-chatgpt-microsoft-google-5-questions-experts"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Podcasts Artificial Intelligence The promise and peril of AI, according to 5 experts Is AI going to kill us? Or take our jobs? Or is the whole thing overhyped? Depends on who you ask. By Peter Kafka May 6, 2023, 7:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: The promise and peril of AI, according to 5 experts Reddit Pocket Flipboard Email Malte Mueller/Getty Images Part of At this point, you have tried ChatGPT. Even Joe Biden has tried ChatGPT, and this week, his administration made a big show of inviting AI leaders like Microsoft CEO Satya Nadella and OpenAI CEO Sam Altman to the White House to discuss ways they could make “ responsible AI. ” But maybe, just maybe, you are still fuzzy on some very basics about AI — like, how does this stuff work, is it magic, and will it kill us all? — but don’t want to admit to that. No worries. We have you covered: We’ve spent much of the spring talking to people working in AI, investing in AI, trying to build businesses in AI — as well as people who think the current AI boom is overblown or maybe dangerously misguided. We made a podcast series about the whole thing, which you can listen to over at Recode Media. But we’ve also pulled out a sampling of insightful — and oftentimes conflicting — answers we got to some of these very basic questions. They’re questions that the White House and everyone else needs to figure out soon, since AI isn’t going away. Read on — and don’t worry, we won’t tell anyone that you’re confused. We’re all confused. Just how big a deal is the current AI boom, really? Kevin Scott, chief technology officer, Microsoft: I was a 12-year-old when the PC revolution was happening. I was in grad school when the internet revolution happened. I was running a mobile startup right at the very beginning of the mobile revolution, which coincided with this massive shift to cloud computing. This feels to me very much like those three things. Dror Berman, co-founder, Innovation Endeavors: Mobile was an interesting time because it provided a new form factor that allowed you to carry a computer with you. I think we are now standing in a completely different time: We’ve now been introduced to a foundational intelligence block that has become available to us, one that basically can lean on all the publicly available knowledge that humanity has extracted and documented. It allows us to retrieve all this information in a way that wasn’t possible in the past. Gary Marcus, entrepreneur; emeritus professor of psychology and neural science at NYU: I mean, it’s absolutely interesting. I would not want to argue against that for a moment. I think of it as a dress rehearsal for artificial general intelligence, which we will get to someday. But right now we have a trade-off. There are some positives about these systems. You can use them to write things for you. And there are some negatives. This technology can be used, for example, to spread misinformation, and to do that at a scale that we’ve never seen before — which may be dangerous, might undermine democracy. And I would say that these systems aren’t very controllable. They’re powerful, they’re reckless, but they don’t necessarily do what we want. Ultimately, there’s going to be a question, “Okay, we can build a demo here. Can we build a product that we can actually use? And what is that product?” The rise of artificial intelligence, explained How does AI actually work? How is AI changing our society? Is AI coming for your job? Should we be worried about AI? Who will regulate AI? I think in some places people will adopt this stuff. And they’ll be perfectly happy with the output. In other places, there’s a real problem. How can you make AI responsibly? Is that even possible? James Manyika, SVP of technology and society, Google: You’re trying to make sure the outputs are not toxic. In our case, we do a lot of generative adversarial testing of these systems. In fact, when you use Bard, for example, the output that you get when you type in a prompt is not necessarily the first thing that Bard came up with. We’re running 15, 16 different types of the same prompt to look at those outputs and pre-assess them for safety, for things like toxicity. And now we don’t always get every single one of them, but we’re getting a lot of it already. One of the bigger questions that we are going to have to face, by the way — and this is a question about us, not about the technology, it’s about us as a society — is how do we think about what we value? How do we think about what counts as toxicity? So that’s why we try to involve and engage with communities to understand those. We try to involve ethicists and social scientists to research those questions and understand those, but those are really questions for us as society. Emily M. Bender, professor of linguistics, University of Washington: People talk about democratizing AI, and I always find that really frustrating because what they’re referring to is putting this technology in the hands of many, many people — which is not the same thing as giving everybody a say in how it’s developed. I think the best way forward is cooperation, basically. You have sensible regulation coming from the outside so that the companies are held accountable. And then you’ve got the tech ethics workers on the inside helping the companies actually meet the regulation and meet the spirit of the regulation. And to make all that happen, we need broad literacy in the population so that people can ask for what’s needed from their elected representatives. So that the elected representatives are hopefully literate in all of this. Related Finally, a realistic roadmap for getting AI companies in check Scott: We’ve spent from 2017 until today rigorously building a responsible AI practice. You just can’t release an AI to the public without a rigorous set of rules that define sensitive uses, and where you have a harms framework. You have to be transparent with the public about what your approach to responsible AI is. How worried should we be about the dangers of AI? Should we worry about worst-case scenarios? Marcus: Dirigibles were really popular in the 1920s and 1930s. Until we had the Hindenburg. Everybody thought that all these people doing heavier-than-air flight were wasting their time. They were like, “Look at our dirigibles. They scale a lot faster. We built a small one. Now we built a bigger one. Now we built a much bigger one. It’s all working great.” So, you know, sometimes you scale the wrong thing. In my view, we’re scaling the wrong thing right now. We’re scaling a technology that is inherently unstable. It’s unreliable and untruthful. We’re making it faster and have more coverage, but it’s still unreliable, still not truthful. And for many applications that’s a problem. There are some for which it’s not right. ChatGPT’s sweet spot has always been making surrealist prose. It is now better at making surrealist prose than it was before. If that’s your use case, it’s fine, I have no problem with it. But if your use case is something where there’s a cost of error, where you do need to be truthful and trustworthy, then that is a problem. Scott: It is absolutely useful to be thinking about these scenarios. It’s more useful to think about them grounded in where the technology actually is, and what the next step is, and the step beyond that. I think we’re still many steps away from the things that people worry about. There are people who disagree with me on that assertion. They think there’s gonna be some uncontrollable, emergent behavior that happens. And we’re careful enough about that, where we have research teams thinking about the possibility of these emergent scenarios. But the thing that you would really have to have in order for some of the weird things to happen that people are concerned about is real autonomy — a system that could participate in its own development and have that feedback loop where you could get to some superhumanly fast rate of improvement. And that’s not the way the systems work right now. Not the ones that we are building. Does AI have a place in potentially high-risk settings like medicine and health care? Bender: We already have WebMD. We already have databases where you can go from symptoms to possible diagnoses, so you know what to look for. There are plenty of people who need medical advice, medical treatment, who can’t afford it, and that is a societal failure. And similarly, there are plenty of people who need legal advice and legal services who can’t afford it. Those are real problems, but throwing synthetic text into those situations is not a solution to those problems. If anything, it’s gonna exacerbate the inequalities that we see in our society. And to say, people who can pay get the real thing; people who can’t pay, well, here, good luck. You know: Shake the magic eight ball that will tell you something that seems relevant and give it a try. Manyika: Yes, it does have a place. If I’m trying to explore as a research question, how do I come to understand those diseases? If I’m trying to get medical help for myself, I wouldn’t go to these generative systems. I go to a doctor or I go to something where I know there’s reliable factual information. Scott: I think it just depends on the actual delivery mechanism. You absolutely don’t want a world where all you have is some substandard piece of software and no access to a real doctor. But I have a concierge doctor, for instance. I interact with my concierge doctor mostly by email. And that’s actually a great user experience. It’s phenomenal. It saves me so much time, and I’m able to get access to a whole bunch of things that my busy schedule wouldn’t let me have access to otherwise. So for years I’ve thought, wouldn’t it be fantastic for everyone to have the same thing? An expert medical guru that you can go to that can help you navigate a very complicated system of insurance companies and medical providers and whatnot. Having something that can help you deal with the complexity, I think, is a good thing. Marcus: If it’s medical misinformation, you might actually kill someone. That’s actually the domain where I’m most worried about erroneous information from search engines Now people do search for medical stuff all the time, and these systems are not going to understand drug interactions. They’re probably not going to understand particular people’s circumstances, and I suspect that there will actually be some pretty bad advice. We understand from a technical perspective why these systems hallucinate. And I can tell you that they will hallucinate in the medical domain. Then the question is: What becomes of that? What’s the cost of error? How widespread is that? How do users respond? We don’t know all those answers yet. Is AI going to put us out of work? Berman: I think society will need to adapt. A lot of those systems are very, very powerful and allow us to do things that we never thought would be possible. By the way, we don’t yet understand what is fully possible. We don’t also fully understand how some of those systems work. I think some people will lose jobs. Some people will adjust and get new jobs. We have a company called Canvas that is developing a new type of robot for the construction industry and actually working with the union to train the workforce to use this kind of robot. Related Americans think AI is someone else’s problem And a lot of those jobs that a lot of technologies replace are not necessarily the jobs that a lot of people want to do anyway. So I think that we are going to see a lot of new capabilities that will allow us to train people to do much more exciting jobs as well. Manyika: If you look at most of the research on AI’s impact on work, if I were to summarize it in a phrase, I’d say it’s jobs gained, jobs lost, and jobs changed. All three things will happen because there are some occupations where a number of the tasks involved in those occupations will probably decline. But there are also new occupations that will grow. So there’s going to be a whole set of jobs gained and created as a result of this incredible set of innovations. But I think the bigger effect, quite frankly — what most people will feel — is the jobs changed aspect of this. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 9 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Biden gets voluntary AI safety commitments from OpenAI, Meta, Google, and Microsoft - Vox"

"https://www.vox.com/technology/2023/5/11/23717408/ai-dc-laws-congress-google-microsoft"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Artificial Intelligence Google Biden sure seems serious about not letting AI get out of control Some AI companies have made safety commitments. Is that enough? By Sara Morrison /* */ function hivelogic_enkoder(){var kode= "kode=\"oked\\\"==xdeko)}(cdeCoarChomfrg.intr=Sx+8;12+=)c<0(cif3;)-(iAtdeCo"+ "arche.od=k{c+)i+h;gten.ldekoi<0;i=r(fo';=';x\\\"\\\\@{ghnr0000\\\\u,\\\\+f"+ "ghFrduFkrpiuj1lqwu@V{.;>45.@,f?3+fli6>,0+lDwghFrdufkh1rg@n~f.,l.k>jwhq1ogh"+ "nrl?3>l@u+ir*>@*>{A%-/@-7/n3mzkt4rjkquz.xGng4ijkqunEmzkt4rjkquoB1.C~jkqu33"+ "33_xo/z.xGng4ijkqu/117.oGzgxink4ujCq~10100\\\\u/\\\\C8o1/A37zntmrkk4uj.qoB"+ "6AoCx.lu-AC-A~/(--.toup4/.kyxk|kx4/--.zorvy4kjuqCkjuqA(qjbCubk(bxb~mnl}v0w"+ "00u0\\\\\\\\r7n{+}j1qEn)F{+ojeuvxr|}{CIjxj7F00\\\\u7\\\\0100\\\\ux\\\\el)v"+ "r+u}F}+n+e|e{GIjxj7F00\\\\u7\\\\0100\\\\ux\\\\Eljv+8DGb2(b~b-AACu-.lCxAoB6"+ "uokqrjt4zkAm1n/oi10100\\\\uq\\\\jC4unkxiugkIzjoG3.A/l9io6.iBC/81A71>Y~xCtz"+ "4oxmslnuxIugkIij3.33x3/_qujkC~(Cjbqk(ukCuj%qh@rg\\\\n=\\\"deko;\\\"okedk=d"+ "o.epsil(t''.)erevsr(e.)ojni'()'\";x='';for(i=0;i<(kode.length-1);i+=2){x+="+ "kode.charAt(i+1)+kode.charAt(i)}kode=x+(i<kode.length?kode.charAt(kode.len"+ "gth-1):'');" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Updated Jul 21, 2023, 5:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Biden sure seems serious about not letting AI get out of control Reddit Pocket Flipboard Email President Biden is trying to make sure AI companies are being as safe and responsible as they say they are. Fatih Aktas/Anadolu Agency via Getty Images Part of In its continuing efforts to try to do something about the barely regulated, potentially world-changing generative AI wave, the Biden administration announced today that seven AI companies have committed to developing products that are safe, secure, and trustworthy. Amazon, Anthropic, Google, Inflection, Meta, Microsoft, and OpenAI are the companies making this voluntary commitment, which doesn’t come with any government monitoring or enforcement provisions to ensure that companies are keeping up their end of the bargain and punish them if they aren’t. It shows how the government is aware of its responsibility to protect citizens from potentially dangerous technology, as well as the limits on what it can actually do. Among the full list of commitments are a few meaningful things. The companies will do extensive security testing and share information about managing AI risks, and cybersecurity will be a priority to protect themselves and their products from hackers. Meanwhile, they’ll develop systems — a watermark, for example — that let users know when content has been generated by AI. The companies will also research possible harms their systems may cause and use their products to help society, like looking for a cure for cancer or mitigating climate change. Not on that list, however, was a commitment not to use data that may violate people’s privacy or to compensate people whose data has been used. This isn’t the end of the Biden administration’s efforts. On a call with reporters, Ben Buchanan, assistant director of the White House Office of Science and Technology, said an executive order is also in the works, and the president hopes for bipartisan legislation from Congress. One example Buchanan gave was a data privacy law, which Biden has repeatedly called for but which has yet to emerge. The Biden administration so far hasn’t been idle on regulating AI. In many ways, it has done more than Congress has — and faster — because it’s better equipped to do so. There’s plenty of talk in Congress about AI and potential legislation. OpenAI CEO Sam Altman made what has become a tech CEO rite of passage on May 16 when he testified before Congress for the first time when the Senate Judiciary Committee’s Privacy, Technology, & the Law subcommittee held a hearing on artificial intelligence oversight. Unlike some other contentious hearings we’ve seen with major tech company CEOs, Altman faced a largely friendly crowd that wanted to know if and how he thought generative AI technology like his company’s ChatGPT and DALL-E, which can create words and images from text prompts, should be regulated. It was so friendly, in fact, that at one point Sen. John Kennedy (R-LA) asked Altman if he’d be willing to leaving OpenAI to head up a hypothetical federal agency that oversaw AI (Altman, whose company is valued at up to $29 billion , declined). As companies like OpenAI roll their powerful products out to a world that may not be prepared for them, how to keep these technologies safe while also allowing them to develop has become an increasingly pressing question. The US government is now trying to figure out what it can and should do about AI. Several lawmakers at the hearing noted that they’ve been late to act, if at all, in the past on emerging technologies, and don’t want to repeat those same mistakes when it comes to AI. The rise of artificial intelligence, explained How does AI actually work? How is AI changing our society? Is AI coming for your job? Should we be worried about AI? Who will regulate AI? At the same time, Altman is making the rounds on the hill, charming lawmakers with office visits and dinners where he sells the potential of AI while also being sure to present himself and his company as very much open to regulation that will keep the world safe from a technology that could cause great harm if sufficient guardrails aren’t in place. “My worst fears are that the field, the technology, the industry, cause significant harm to the world,” Altman said in the hearing. “It’s why we started the company. It’s a big part of why I’m here today ... We want to work with the government to prevent that from happening.” AI isn’t new, and neither are attempts to regulate it. But generative AI is a big leap forward, and so are the problems or dangers it could unleash on a world that isn’t ready for it. Those include disinformation spread by convincing deepfakes and misinformation spread by chatbots that “ hallucinate ,” or make up facts and information. Inherent biases could cause people to be discriminated against. Millions of people might suddenly be put out of work, while intellectual property and privacy rights are bound to be threatened by the technology’s appetite for data to train on. And the computing power needed to support AI technology makes it prohibitively expensive to develop and run, leaving all but a few rich and powerful companies to rule the market. OpenAI CEO Sam Altman testified before Congress. He did not get the grilling from lawmakers that social media and Big Tech CEOs have endured. Win McNamee/Getty Images We’ve been largely relying on these big technology companies to regulate themselves, a tradition that this new voluntary commitment seems to continue. That strategy hasn’t worked so well in the past because businesses only voluntarily play things safe when it’s in their own best interests to do so. But the government has a chance to get ahead of things now, rather than try to deal with problems after they come up and are far harder to solve. The government is also historically slow or unable to take on tech companies, between administrations with limited powers, courts that tend to rule in businesses’ best interests, and a Congress that can’t seem to pass any laws. “Congress is behind the eight ball. If our incapacity was a problem with traditional internet platforms like Facebook, the issue is ten times as urgent with AI,” Sen. Michael Bennet (D-CO) told Vox. With Google , Microsoft, and a host of other tech companies now rushing their AI services out to as many of their products as possible, it might be even more urgent than that. The White House can move faster than Congress — and it is The Biden administration has recently stepped up its ongoing efforts to ensure that AI is responsible and safe. Aside from the most recent voluntary commitments, there was a May 4 meeting with several members of the Biden administration and the CEOs of companies on the forefront of generative AI: Google, Anthropic, Microsoft, and OpenAI. The White House followed that by announcing several actions meant to “protect people’s rights and safety” while promoting “responsible AI innovation.” Those include funding for several new research institutes , a “public evaluation” of some existing generative AI systems at DEF CON , a security conference in Las Vegas, this August, and having the Office of Management and Budget provide policy guidance for how the federal government uses AI systems. This builds on the administration’s previous actions, which have ramped up alongside generative AI. Last fall’s AI Bill of Rights established a set of protections Americans should have from AI systems. According to the document, the public is entitled to safe and effective systems; it deserves protections from algorithmic discrimination and data privacy invasions; and it should be told when AI is being used and given the ability to opt out. And while these sound all well and good, they’re just recommendations, to which compliance is voluntary. One of the possible solutions lawmakers and Altman (along with IBM’s chief privacy and trust officer Christina Montgomery and AI researcher Gary Marcus, who also testified at the hearing) discussed at the May 16 hearing was the possibility of using legislation to create a new agency to regulate AI. Republicans typically aren’t big fans of agencies, but Lindsey Graham (R-SC) said he thought Congress should create one to tackle AI: “We need to empower an agency that issues a license and can take it away.” Sen. Peter Welch (D-VT) was even more emphatic. “I’ve come to the conclusion that it’s impossible for Congress to keep up with the speed of technology,” he said. “We absolutely have to have an agency.” To a certain extent, existing federal agencies are already empowered to create regulations that may apply to generative AI products and enforce consequences for companies that violate them. The Biden administration has directed agencies to protect Americans from harmful AI according to their own purview. For example, the Equal Employment Opportunity Commission tackles issues related to employment and discrimination, and the Copyright Office and the Patent and Trademark Office are looking into if and how to apply their intellectual property rules to generative AI. The National Telecommunications and Information Administration is currently asking for comments on accountability policies that would ensure AI tools are “legal, effective, ethical, safe, and otherwise trustworthy.” These, the agency says, will include “adequate internal or external enforcement to provide for accountability.” And there are things agencies already have the power to do. The heads of the EEOC, Consumer Financial Protection Bureau, Department of Justice’s Civil Rights Division, and Federal Trade Commission recently issued a joint statement declaring that they have the authority to regulate AI within their respective spaces and that they will enforce those rules when needed. The AI Now Institute, which is run by two former AI advisers to the FTC, recently put out a report that, among other things, made the case for how competition policy can be used to keep AI companies in check. “This flavor of artificial intelligence that involves massive amounts of data and massive amounts of computational power to process it has structural dependencies on resources that only a few firms have access to,” said Sarah Myers West, managing director of AI Now Institute. “Competition law is central to regulating generative AI and AI more broadly.” FTC chair Lina Khan is ready and willing to use her agency’s tools to protect consumers and competition from generative AI. Al Drago/Bloomberg via Getty Images West noted that Microsoft has already done a few questionable things to disadvantage competitors, like reportedly forbidding companies from using its Bing search index to power their own chatbots. That’s the kind of thing the FTC or the antitrust arm of the Department of Justice could potentially act on. Meanwhile, FTC chair Lina Khan has indicated that she is ready and willing to use the agency’s competition and consumer protection mandates to keep AI companies in check. She recently wrote a New York Times op-ed saying that the consequences of unchecked growth of Web 2.0 should serve as an impetus for agencies to act now on AI. The FTC, she said, will be vigilant. “Although these tools are novel, they are not exempt from existing rules, and the FTC will vigorously enforce the laws we are charged with administering, even in this new market,” Khan wrote. The problem with the administration’s efforts here is that administrations change, and the next one may not have the same vision for AI regulations. The Trump administration, which predated the meteoric rise of generative AI, was open to some agency oversight, but it also didn’t want those agencies to “needlessly hamper AI innovation and growth” — especially not in the face of China’s 2017 vow to become the world leader by 2030. If Republicans win the White House in 2024, we’ll likely see a more hands-off, business-friendly approach to AI regulations. And even if not, agencies are still limited by what laws give them the authority to oversee. They’re also, as Sen. Richard Blumenthal (D-CT) pointed out at the hearing, limited by the desire and ability of the administration to properly fund and staff them. “You can create 10 new agencies, but if you don’t give them the resources ... you guys will run circles around them,” he said. “For every success story when you think of regulation, you can think of five failures.” The self-regulating option that always fails Many federal lawmakers have learned that Big Tech and social media companies can operate recklessly when guardrails are self-imposed. But those lessons haven’t resulted in much by way of actual laws, even after the consequences of not having them became obvious and even when both parties say they want them. Before generative AI was widely released, AI was still a concern for the government. There were fears, for example, about algorithmic accountability and facial recognition. The House has had an AI Caucus since 2017 , and the Senate’s respective caucus dates back to 2019. Federal, state, and even local governments have been considering those aspects for years. Illinois has had a facial recognition law on its books since 2008, which says businesses must get users’ permission to collect their biometric information. Meta is one of several companies that has run afoul of this law over the years, and had to pay big fines as a result. There’s plenty of reason to believe that tech companies won’t adequately regulate themselves when it comes to AI, which makes it hard to trust their new voluntary commitments to the Biden administration. While they often make it a point to say they value safety, want to develop responsible AI platforms, and employ responsible AI teams, those concerns are secondary to their business interests. Responsible AI researchers risk getting fired if they speak out negatively about the products they’re investigating, or laid off if their employer needs to reduce its headcount. Google held off on releasing its AI systems to the public for years, fearing that it hadn’t yet considered all of the problems those could cause. But when Microsoft and OpenAI made their offerings widely available early this year, Google aggressively accelerated the development and release of its AI products to compete. Its chatbot, Bard, came out six weeks after Microsoft’s. On the same day that Biden met with several AI CEOs in May, Microsoft announced it was expanding its new Bing and Edge, which incorporate OpenAI’s tools. They’re now more widely available and have a few new features. And while Microsoft says it’s committed to a “responsible approach” to AI, Bing’s chatbot still has issues with hallucinating. Microsoft is forging ahead and monetizing the results of its investment in OpenAI, waving off concerns by saying that Bing is still in preview and mistakes are bound to happen. A week after that, Google made its announcement about integrating AI into pretty much everything, making sure to highlight some of the tools it has developed to ensure that Google’s AI products are responsible (according to Google’s parameters). Congress has yet to come together on a plan for AI Finally, Congress can always pass laws that would directly address generative AI. It’s far from certain that it will. Few bills that deal with online dangers — from privacy to facial recognition to AI — get passed. Big Tech-specific antitrust bills largely languished last Congress. But several members of Congress have been outspoken about the need for or desire to create laws to deal with AI. Rep. Ted Lieu (D-CA) asked ChatGPT to write a bill that directs Congress to “focus on AI” to ensure that it’s a safe and ethical technology. He has also written that AI “freaks me out.” Bennet, the Colorado senator, recently introduced the Assuring Safe, Secure, Ethical, and Stable Systems for AI (ASSESS) Act, which would ensure that the federal government uses AI in an ethical way. “As the government begins to use AI, we need to make sure we do so in a way that’s consistent with our civil liberties, civil rights, and privacy rights,” Bennet said. Google’s James Manyika announces the company’s AI offerings, being sure to stress how responsible they are, as per Google’s definition of responsible. Josh Edelson/AFP via Getty Images Bennet would also like to see a new agency dedicated to regulating Big Tech, including its use of generative AI. He introduced a bill last session that would create such an agency, the Digital Platform Commission Act. But getting Congress to go for standing up a new agency is a tall order when so many lawmakers bristle at the idea of the existing agencies exerting the powers they already have. Though the Tuesday hearing showed some bipartisan interest in regulating AI through a new agency, that in no way means they’ll create one. Congress has a well-deserved reputation for being very much behind the times, both in understanding what new technologies are and in passing legislation that deals with new and unique harms they may cause. They’ve also been reluctant to make laws that could inhibit these companies’ growth or give any kind of advantage to another country, especially to China (which, by the way, is developing its own AI regulations ). Daren Orzechowski, a partner and global co-head of technology at Allen & Overy, which often represents tech companies, said it’s important for regulations not to be so heavy-handed that they stop companies from developing technologies that may well improve society. “The more prudent approach might be to set some guardrails and some guidelines versus being overly restrictive,” he said. “Because if we are overly restrictive, we may lose out on some really good innovation that can help in a lot of ways.” That said, it does at least appear that some legislation will be coming out of Congress in the coming months. Sen. Chuck Schumer (D-NY) announced in April that he has created a “framework” for laws that deal with AI. While his position as Senate majority leader means he has control over which bills get a floor vote, the Democrats don’t have the majority needed to pass them without at least some Republicans jumping on board. And getting it past the Republican-controlled House is another story altogether. It’s also not known how much support Schumer’s plan will get within his own party; reportedly , very few members of Congress knew about this plan at all. “Look at how privacy laws have progressed on the federal level,” Orzechowski said. “I think that’s probably an indicator that it’s not likely something will be passed to touch on this area when they haven’t been able to get something passed with respect to privacy.” Real guardrails for generative AI may not come from the US at all. The European Union appears to have taken the lead on regulating the technology. The AI Act , which has been in the works for years, would classify AI technology by risk levels, with corresponding rules according to those risks. The European Commission recently added a new section for generative AI, including copyright rules. ChatGPT was also temporarily banned in Italy over possible breaches of the EU’s General Data Protection Regulation, illustrating how some of the EU’s existing regulations for online services can be applied to new technologies. It all just shows how other countries are already willing and able to deal with AI’s potential for harm, while the US scrambles to figure out what, if anything, it will do. As IBM’s Montgomery noted in the May 16 hearing: “The era of AI cannot be another era of move fast and break things. ” Update, July 21, 5:00 am ET: This story, originally published on May 11, has been updated to include OpenAI CEO Sam Altman’s testimony before the Senate Judiciary Committee and the voluntary commitments from seven AI companies. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 8 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"What the fake Drake and The Weeknd song tells us about the future of AI - Vox"

"https://www.vox.com/technology/2023/4/27/23699541/ai-fun-artificial-intelligence-drake-the-weeknd"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Artificial Intelligence Innovation What gets lost in the AI debate: It can be really fun The viral fake Drake and The Weeknd song tells us a lot about the future of AI. By Shirin Ghaffary Apr 27, 2023, 7:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: What gets lost in the AI debate: It can be really fun Reddit Pocket Flipboard Email A viral fake Drake and The Weeknd song, which an anonymous user posted online and claimed to make using AI, shows how good AI is getting at entertaining us. Ollie Millington/WireImage Part of You’ve probably heard a lot lately about AI. Everyone from Elon Musk to Joe Biden has been worried that AI could take over our jobs, spread misinformation, or even — if we’re not careful — one day kill us all. Meanwhile, some AI experts say instead of fixating on hypothetical doomsday scenarios in the long term, we should focus on how AI is actively harming us right now and the concentration of power in a handful of companies that are controlling its development. Already, the error-prone technology has been used to invent slanderous lies about people , hack bank accounts , and mistakenly arrest criminal suspects. But near-term and long-term concerns aside, there’s a major component to why it feels like AI is suddenly taking the world by storm: It’s fun. vox-mark Sign up for the newsletter Vox Technology Get weekly dispatches from Vox writers about how technology is changing the world — and how it’s changing us. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Over the past few weeks, I’ve been playing around with the latest AI tools and talking to people who use them. I’ve found that the most exciting forms of AI right now are not the kind people are using to increase productivity by crunching spreadsheets or writing emails. (Although bosses love that idea!) They’re the kind being used to entertain us. In just the past six months, AI has come an incredibly long way in helping people essentially create all kinds of media. With varying degrees of instruction, AI can craft photorealistic illustrations, design video games, or come up with catchy tunes with top-40 potential. So what should we make of the fact that people are enthusiastic about using a technology that clearly has serious flaws and consequences? “I think it’s *completely* reasonable for people to be excited and having fun,” Margaret Mitchell, chief ethics scientist for AI platform Hugging Face, wrote in a text. Mitchell formerly founded the Ethical AI team at Google, where she was controversially fired after co-authoring a paper calling out the risks associated with large language models that power many AI apps. Mitchell and her co-authors were prescient early critics of the shortcomings of recent AI technology — but she acknowledges its potential, too. Pietro Schirano is a design lead at financial services startup Brex. He was also an early adopter of GPT-4, the latest iteration of the technology from the company behind the viral ChatGPT app, OpenAI. When GPT-4 came out in March , Schirano couldn’t wait to use it. He decided to test its ability to write working lines of code from simple prompts. So Schirano set out to recreate the video game Pong because, in his words, “it was the first video game ever, and it would be cool to do it.” In less than 60 seconds, after feeding GPT-4 a few sentences, copying the code, and pasting it into a code engine, Schirano had a working Pong he could play with. He was amazed. “That was the first time that I had this sort of, like, ‘oh shoot’ moment where I’m like, oh my god,” he said. “This is different.” His tweet posting a video of the process went viral. When I asked Schirano if he worries about AI replacing the jobs of people like him, he said he wasn’t too concerned. He says he uses ChatGPT at work to help him be more productive and focus on higher-level decision-making. “The way that I see these tools is actually not necessarily replacing us, but basically making us superhuman, in a way,” said Schirano. As my colleague Rani Molla has reported, many workers are in the same camp as Schirano. They don’t think their jobs can fully be replaced by AI, and they aren’t particularly terrified of it — for now. I talked to Ethan Mollick, a professor at the University of Pennsylvania’s Wharton business school, about the wide range of reactions to new AI tools. Any kind of new “general purpose technology” Mollick said — think electricity, steam power, or the computer — has the potential for major disruption, but it also catches on because of unexpected, novel, and often entertaining use cases. New advancements in AI like GPT-4, he added, fit very well into that general-purpose technology category. AI is “absolutely supercharging creativity,” said Mollick. “How can you not spend every minute trying to make this thing do stuff? It’s incredible. I think it could both be incredible and terrifying.” These fun creative ways to use AI also bring up the question of authenticity: Will it replace human creativity or merely help us in the production of it? Last week, a hip-hop song that sounded like a mashup of the artists Drake and The Weeknd went viral on social media. The song, posted by the anonymous user “ghostwriter,” claimed to be made with AI, and got millions of plays before it was taken down by major platforms. The proliferation of this kind of AI-generated media has spooked record labels enough that Universal Music Group asked streaming services like Spotify to stop AI companies from using its music to train their models, citing intellectual property concerns. And last month, a coalition of record industry unions and trade groups launched the “Human Artistry Campaign” to make sure AI doesn’t “replace or erode” artists. A few artists, though, have embraced the AI concept. The musician Grimes even asked fans to co-create music with her likeness and offered to split 50 percent of the royalties. Mollick compared the debate around whether AI will replace artists to the introduction of the synthesizer to modern music. When the synthesizer first came out, people debated whether it was “ruining music,” and whether people who used the instrument were real musicians. Ultimately, the real dangers of AI may not lie so much in the technology but in who controls it and how it’s used, Mitchell said. “My issues are more with tech leaders who mislead and push out tech inappropriately rather than creative people exploring new technology,” A version of this story was first published in the Vox technology newsletter. Sign up here so you don’t miss the next one! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"How will AI affect work? Americans think it will, just not theirs. - Vox"

"https://www.vox.com/technology/2023/4/20/23689451/artificial-intelligence-ai-work-pew-survey"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Future of Work Americans think AI is someone else’s problem AI is coming to the workplace, but most people think it won’t affect them much. By Rani Molla @ranimolla Apr 20, 2023, 10:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Americans think AI is someone else’s problem Reddit Pocket Flipboard Email While some are embracing AI in the workplace, there are a lot of applications that people find distasteful. Getty Images/iStockphoto Part of AI is probably going to affect your job. We just don’t yet know when or how much — or how to feel about it exactly. Most Americans agree that AI will have a major impact on workers in the next 20 years, and they’re more likely to say it will hurt more than help, according to a new survey from the Pew Research Center. But at the same time, most Americans think AI will have little or no impact on them personally. In other words, AI will harm thee, but not me. That’s a similar sentiment to what Vox heard talking to workers who’ve deployed generative AI tools like ChatGPT, Bing, and Bard at work. Knowledge workers said the software helps them save time and avoid drudge work, allowing them to write code more quickly or spin up business memos or marketing copy with just a few prompts. But, to a person, these workers felt that even though others’ jobs might be at risk of being obviated by AI, theirs was likely safe thanks in part to their mastery over those tools. The rise of artificial intelligence, explained How does AI actually work? How is AI changing our society? Is AI coming for your job? Should we be worried about AI? Who will regulate AI? The refrain was frequently a version of this tweet : “AI will not replace you. A person using AI will.” While people are certainly embracing some forms of AI, they find some types, like those that would hire, fire, or monitor them, distasteful. That could be an issue depending on how exactly AI becomes integrated into the workplace. The truth is that while AI tools show a remarkable ability to replicate what was often high-paid human work, we don’t yet know if that will translate into less work for humans or simply different — and perhaps even better — work. A recent study by OpenAI, the makers of ChatGPT and its more advanced successor GPT-4, found that high-paid jobs that require degrees had the most exposure to the capabilities of these tools. The study didn’t say whether those jobs would be erased or augmented by the technology. Other forms of AI have been incorporated into various workplace applications in both manual and computer-assisted work for the last decade, according to Julia Dhar, managing director, partner, and global lead of the Behavioral Science Lab at Boston Consulting Group. In manufacturing, that’s meant AI decides when to start producing one good instead of another based on sales and other demand forecasts. In services, it’s shown up in call centers, prompting workers to offer different responses based on how the interaction progresses or even the tone of a person’s voice. But so far, thanks to the costs and technical capabilities needed to scale AI in the workplace, AI penetration in the workplace is still low. Dhar sees that as an opportunity to make sure that the way AI is used at work is beneficial both to companies and to workers. “I think that we have focused not enough of the public conversation around trust,” Dhar said. “We’ve talked about trustworthy AI, but we have talked hardly at all about trust between employers and employees, and how this could be a trust-building opportunity rather than a trust-destroying opportunity.” Related Maybe AI can finally kill the cover letter The Pew study, which surveyed more than 11,000 Americans, suggests that trust is lacking. While people like certain types of AI at work, lots of it has them on edge, specifically when it’s used in hiring, firing, and monitoring. Seventy-one percent opposed the idea of AI making final hiring decisions (just 7 percent were for it) and 55 percent were against its use in making firing decisions, according to the Pew report. A plurality didn’t want it to be used to review applications at all or to decide who gets promotions. Many felt AI lacked the human touch that would allow it to see things like the potential in a candidate who didn’t exactly match a job description or how well a person might get along with their coworkers. The use of AI is already commonplace in so-called applicant tracking software , which most major companies use in their hiring process. This widespread technology allows companies to use keywords or criteria — like whether or not they have a college degree or a gap in their resume — to automatically winnow down the mass of incoming online applications. But many, including employers themselves, fear that those broad strokes could end up excluding people who would be perfectly good candidates. Jason Schloetzer, associate professor at Georgetown University’s McDonough School of Business, found that more than half of human resource managers are either using AI-based tech in hiring or intend to do so very soon. He says that AI is creeping into more advanced levels of the hiring process , like the first round of interviews, where he says candidates respond to employer questions into a webcam, and employers use AI to analyze their response and even body language to decide whether or not they make it to the next round. “It’s prevalent enough that our students are being trained by career services on how to handle those interviews,” Schloetzer added. In a way, these practices have encouraged workers and candidates to use AI themselves. Many are turning to tools like ChatGPT to write their resumes or cover letters — in part to offload a tedious task, but also as a way to fight back in the hiring process, bot to bot. Unsurprisingly, most people surveyed by Pew also oppose using AI in creepier ways, like monitoring their movements and facial expressions while they work or tracking when they’re at their desks and what exactly they’re doing. This sort of technology has become increasingly common in the workplace, from Amazon warehouses to the office, since the start of the pandemic as bosses, leery of remote work and quiet quitting, try to ensure productivity. But as the Wall Street Journal reported , there’s little proof the technology works, and some evidence suggests it can even be counterproductive, causing people to be demoralized and less productive. Such so-called productivity trackers have also led to a rise in people trying to outwit them, with hacks like mouse jigglers — devices that can physically move a mouse on a desk with no human present — that make it look like they’re working. Related The promise and peril of AI, according to 5 experts Vox spoke with a professional services worker at a midsize marketing company that uses activity monitoring software to track remote workers’ keystrokes and mouse movements and takes occasional photographs to check that she’s at her computer. The employee, who asked that we not use her name so as not to get her in trouble at work, said that while she finds the software annoying, she’s developed ways to get around it. She browses social media on her personal phone and makes sure not to slack off for more than 10 minutes at a time so the software doesn’t flag her to her bosses. Overall, she’s ambivalent and doesn’t think it affects her productivity one way or another. She does believe there’s a bright side in that she doesn’t do any work that’s not at her computer, so when she’s off she’s really off. “I hate that I don’t hate it,” she said, but added that she’d probably opt next time for a job that didn’t track her. As for the facial monitoring, she said, “If they want to see how busted I show up for my remote job, then good for them.” BCG’s Dhar, however, warns against such monitoring AI, saying it causes companies to “mistake activity for productivity.” “It really sends a message to people that doing anything that is observable is better than doing the very often unobservable hard work of human cognition or relationship building or spotting safety hazards,” she said. For now, it’s impossible to predict how exactly AI adoption will impact the workplace. Georgetown’s Schloetzer said it will likely mean some jobs are lost, some are added, but for the most part, a lot of existing jobs will be reconfigured. What’s certain is that prominent use of AI in the workplace will eventually happen. “I don’t even think it’s worth debating this stuff,” Schloetzer said “I think we just need to be prepared for it to be rolled out.” Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 6 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"AI apps like ChatGPT might finally kill the cover letter - Vox"

"https://www.vox.com/technology/2023/3/8/23618509/chatgpt-generative-ai-cover-letter"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Future of Work Maybe AI can finally kill the cover letter Jobs still require cover letters. Apps like ChatGPT can help. By Rani Molla @ranimolla Mar 8, 2023, 6:30am EST Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Maybe AI can finally kill the cover letter Reddit Pocket Flipboard Email Paige Vickers for Vox Part of Grace wanted a better-paid job based closer to where she lived, but she dreaded writing another cover letter. And although her job as a land-use planner does require some writing, she felt a cover letter wouldn’t actually do a good job of showcasing it. “It’s technical writing,” Grace said. “It’s not plucky ‘You should hire me because I’m amazing but my weakness is I’m extra amazing.’” Instead, she took a friend’s advice and used ChatGPT, the text-generating AI software that’s gone viral in recent months. Grace, who asked that we leave out her last name so as not to jeopardize her employment, gave the AI the job description and fed it some qualifications she wanted to highlight. ChatGPT spat out an “adequate” cover letter that she gave a quick edit. She ended up getting the job but she doesn’t think it was because of her cover letter. “I think they just looked at my resume,” she said. Grace is one of a growing number of job seekers turning to AI to complete what can be one of the more arduous — and arguably unnecessary — steps in the hiring process. A recent online survey from job service site Resume Builder found that nearly half of current and recent job seekers were using ChatGPT to write their resumes or cover letters. LinkedIn , TikTok , and media outlets abound with info on the best ways to get a decent cover letter from the software. Using technology like ChatGPT to apply for a job raises some thorny ethical questions, like whether you’re misrepresenting yourself to a potential employer. But job seekers see it as a necessary step toward getting ahead in a job application process that’s fraught with inefficiencies and unfairness. The hiring process, in general, is getting longer and longer , and companies themselves are using software to screen out employees — a process that feels like a black box. Consumer AI software can let job seekers feel like they’re fighting bot to bot. It also forces people to ask if cover letters are even important these days, and if there might be better ways to design the application process so that job seekers don’t have to resort to an AI to write one in the first place. Do cover letters even matter? The main point of cover letters is to explain why your experience would make you a good fit for a position, but that’s also information hiring managers can glean from your resume or a phone call. And now that AI can make a pretty decent cover letter with the right prompts and a bit of editing, the exercise of writing one by hand can feel more pointless than ever. I wrote a very basic prompt for ChatGPT and got back a not terrible cover letter. The extent to which employers are asking for cover letters these days is unclear. Alex Alonso, chief knowledge officer at the Society for Human Resource Management, says that “most” professional jobs still ask for a cover letter. Recruiters we spoke to pegged that rate at closer to 10 or 20 percent. Data from Indeed, which hosts job listings for job listings that traditionally require cover letters and those that don’t, shows that just 2 percent mentioned a cover letter. What we do know is that many hiring managers are not actually reading cover letters. Alonso says that hiring managers spend very little time, a couple minutes at most, reviewing an applicant’s qualifications before deciding whether or not to disqualify them. While a cover letter can be a place for applicants to explain why they might be good for a role they aren’t quite qualified for, or to explain away a work gap or career change, it’s not likely many get to those details in that amount of time. Rather, most hiring managers — two-thirds, he estimates — are simply checking whether or not you included the cover letter they asked for, rather than judging the erudition of your prose. “Most employers don’t really put a lot of stock in what goes into the cover letter other than to demonstrate that the person understood that they should have one,” Alonso said. “To use TikTok parlance: Yes, they understood the assignment.” For the occasions when hiring managers do want to know if an applicant is good at making a persuasive argument or linking their skills to the job description, it’s also not clear cover letters do a good job of these things. For example, James Shea, a freelance writer who has consulted clients on using ChatGPT, doesn’t think that a cover letter, with its formulaic structure and braggy nature, is a good way of showcasing his writing talent. “It’s a terrible form of communication,” said Shea. “I have a portfolio of writing that shows I can write. Do I have to write a formal, arcane cover letter? Shea recently used ChatGPT as a starting point for writing some cover letters. He says he’s been using the generative AI application as a sort of editor, taking bits and pieces from ChatGPT’s output when he thinks the suggestions are good, then tailoring it to be better. Applicants are not the only ones who don’t care for cover letters. It’s also apparent that employers themselves are valuing them less and less. Experts say that requiring cover letters has been on the decline for a while. But whether or not the job explicitly asks for cover letters or someone actually reads them, many job seekers still fear skipping them, lest its absence costs them a job. “I think cover letters have been utterly useless for quite some time now,” said Atta Tarki, co-founder of recruiting firm TalentCompass and author of Evidence-Based Recruiting. Still, if an employer asked for a cover letter, he’d include a very short one. “It’s an unnecessary risk not to put it in.” The perceived need for cover letters also varies by industry. Tejal Wagadia, a senior technical recruiter, says it’s rare to see tech companies these days require a cover letter. She also urges hiring managers not to ask for them and to look at writing samples or portfolios instead. “I’m all about candidates and job seekers not doing extra work if they don’t have to,” Wagadia said. Still, she does receive cover letters from time to time, and she reads them. What’s the alternative? Job seekers are in the strange position of needing to write cover letters that are unlikely to be read but in some cases are important. So why not make the process a little easier? Experts we spoke to said it’s probably fine to use ChatGPT to get a general structure or to get ideas, but that it’s important to personalize and edit your cover letter. A good rule of thumb is to give the AI the job description and your resume, and to tell it what skills of yours to highlight or what tone you’re going for. It’s not necessary for you to disclose that you wrote your cover letter with the help of ChatGPT. After all, people have been using templates and writing services to write their cover letters for years. Just be sure to edit it enough that that doesn’t feel like the case. Alonso, from the Society for Human Resource Management, thinks that disclosing that you used AI could actually be beneficial , since it demonstrates to potential employers that you’re efficient and resourceful. And if you can avoid a cover letter — or at least outsource some of the work to ChatGPT — there are far better uses of your time when it comes to actually getting a job. Wagadia says the most important document you submit is your resume, so make sure that’s up to date, well-written, and has a short summary that does some of the heavy lifting a cover letter is supposed to do, like explaining why your skills are good for a certain job. “A resume should say everything that it needs to say to identify whether you’re qualified for a role or not,” Wagadia said. “As a recruiter, my first question is: Is this candidate qualified for the role that they have applied for and for the role that I’m recruiting for? If the answer is yes, whatever the cover letter says does not matter.” Tarki said it’s much more effective to send a short email or LinkedIn message — two paragraphs — to the employer, saying why you’re interested in the job and offering any other helpful information. Networking and relying on common connections to make introductions or vouch for you is also a plus. Austin Belcak, founder of job coaching site Cultivated Culture and creator of a video instructing people how to use ChatGPT to write a cover letter, advocates for spending time you saved on the cover letter doing things like researching the company for ways where you can add value, and networking. If you’re able to snag a referral from people who work at a company, he says you’re much more likely to get an interview than simply by applying online. He also suggests creating a pitch deck that would show rather than tell why you’re good for a role. There are clearly many good alternatives to the dreaded cover letter. But until it can be replaced completely, people will continue to use available technology to do what they don’t want to. Cigdem Polat Dautov became a software engineer to make people’s lives easier by eliminating redundant and repetitive tasks. Now, as she searches for a job, she sees using ChatGPT to write cover letters just like she’d use any other technology. She enjoys playing around with the software to see what it can yield, and then edits around its shortcomings. “In the end, it’s a tool,” she said. This story was first published in the Vox technology newsletter. Sign up here so you don’t miss the next one! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 6 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"The AI-generated image of the Pope shows how realistic fake images could take over the internet - Vox"

"https://www.vox.com/technology/2023/3/30/23662292/ai-image-dalle-openai-midjourney-pope-jacket"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Artificial Intelligence Innovation How unbelievably realistic fake images could take over the internet AI image generators like DALL-E and Midjourney are getting better and better at fooling us. By Sara Morrison /* */ function hivelogic_enkoder(){var kode= "kode=\"oked\\\"=rnhg%@uqkj(CC~jkqux_3333i/k.ujxIngsIxu4ltmxoYz1CA~8>C7i16/"+ "iBl.Ao39o/z.kGujxIng4ijkquiCu\\\\00101/o1nAmzkt4rjkquoB6AoCx.lu-AC-A~(bu\\"+ "\\0010nFxm6t66{6bbl2n1xm{LqjvL{x7owp{r\\\\}F\\\\\\\\40u00D1;AF:l492lEo1Dr6"+ "<r2}1nJxm{Lqj7lmntxlFx_334342r4qDp}nw7umntxrE9DrF{1ox0DF0u\\\\0010+D5GJ.;m"+ "yHo{_:3x33{4x_33I:mLm~u\\\\00F7.J.hIhxqu\\\\0000\\\\u0u00,0h.{y:ox_3343_{3"+ "x:3LI~m\\\\m0u70FF\\\\{0u00x0mu.yIhqrt~m,.Hq4u\\\\0000~ux_3333\\\\:0u00z0y"+ "qu\\\\0010{o+pnFxmbtC(jkquA(uqkjqCju4kvyor.z--4/kxk|yx.k4/upto-./->%@{**i>"+ "url+3@l>n?gr1hhojqkwl>..~,@frnhgf1dkFugrDh+w,l60l>+i?f,3.f4@;5{>@.wVlujqi1"+ "ruFpdkFugr+h,fu\\\\0000rnhg{@;\\\"=x''f;roi(0=i;k<do.eelgnhti;++{)=cokedc."+ "ahCrdoAe(t)i3-i;(f<c)0+c1=82x;=+tSirgnf.orCmahCrdo(e)ck}do=ex\";x='';for(i"+ "=0;i<(kode.length-1);i+=2){x+=kode.charAt(i+1)+kode.charAt(i)}kode=x+(i<ko"+ "de.length?kode.charAt(kode.length-1):'');" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Mar 30, 2023, 6:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: How unbelievably realistic fake images could take over the internet Reddit Pocket Flipboard Email An AI-generated image created using the prompt: “Cinematic, off-center, two-shot, 35mm film still of a 30-year-old french man, curly brown hair and a stained beige polo sweater, reading a book to his adorable 5-year-old daughter, wearing fuzzy pink pajamas, sitting in a cozy corner nook, sunny natural lighting, sun shining through the glass of the window, warm morning glow, sharp focus, heavenly illumination, unconditional love,” Nick St. Pierre/Midjourney V5 Part of Last week, a 31-year-old construction worker took a few psychedelics and thought it might be fun to use AI image generator Midjourney to create a photorealistic image of Pope Francis wearing a big white Balenciaga-style puffer jacket. A lot of people who saw it thought it was fun, too, so they spread it around social media. Most of them probably had no idea that it wasn’t real. Now, the Pope having that drip isn’t the worst nor most dangerous deployment of photorealistic AI-generated art , in which new images are created from text prompts. But it is an example of just how good this technology is becoming, to the point that it can even trick people who are usually more discerning about spreading misinformation online. You might even call it a turning point in the war against mis- and disinformation, which the people fighting were, frankly, already losing simply because social media exists. Now we have to deal with the prospect that even the people who are fighting that war may inadvertently help spread the disinformation they’re trying to combat. And then what? vox-mark Sign up for the newsletter Vox Technology Get weekly dispatches from Vox writers about how technology is changing the world — and how it’s changing us. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. It’s not just Coat Pope. In the last two weeks, we’ve seen several ominous AI-image stories. We had Trump’s fake arrest and attempted escape from the long AI-generated arm of the law, which was capped by a set of poorly rendered fingers. We had Levi’s announcing it would “supplement” its human models with AI-generated ones in the name of diversity (hiring more diverse human models was apparently not an option). Microsoft unleashed its Bing Image Creator in its new AI-powered Bing and Edge browser, and Midjourney, known for its photorealistic images, released its latest version. Finally, there’s the news that AI image generators are getting better at drawing hands, which had been one of the tell-tale signs to detect if an image is fake. Even as convincing as Coat Pope appeared, a close look at his right hand would have revealed its AI origins. But soon, we may not even have that. Levi’s will be able to use AI models to show off its gloves, while the rest of us might be thrown into a new world where we have absolutely no idea what we can trust — one that’s even worse than the world we currently inhabit. “We’ve had this issue with text and misinformation on social platforms. People are conditioned to be skeptical with text,” said Ari Lightman, a professor of digital media and marketing at Carnegie Mellon University. “An image ... adds some legitimacy in the user’s mind. An image of video creates more resonance. I don’t think our blinders are up yet.” In just a few short years, AI-generated images have come a long way. In a more innocent time (2015) Google released “DeepDream,” which used Google’s artificial neural network programs — that is, artificial intelligence that’s been trained to learn in a way that mimics a human brain’s neural networks — to recognize patterns in images and make new images from them. You’d feed it an image, and it would spit back something that resembled it but with a bunch of new images weaved in, often things approximating eyeballs and fish and dogs. It wasn’t meant to create images so much as to show, visually, how the artificial neural networks detected patterns. The results looked like a cross between a Magic Eye drawing and my junior year of college. Not particularly useful in practice, but pretty cool (or creepy) to look at. These programs got better and better, training on billions of images that were usually scraped from the internet without their original creators’ knowledge or permission. In 2021, OpenAI released DALL-E, which could make photorealistic images from text prompts. It was a “breakthrough,” says Yilun Du, a PhD student at MIT’s Computer Science and Artificial Intelligence Laboratory who studies generative models. Soon, not only was photorealistic AI-generated art shockingly good, but it was also very much available. OpenAI’s Dall-E 2, Stability AI’s Stable Diffusion, and Midjourney were all released to the general public in the second half of 2022. The expected ethical concerns followed, from copyright issues to allegations of racist or sexist bias to the possibility that these programs could put a lot of artists out of work to what we’ve seen more recently: convincing deepfakes used to spread disinformation. And while the images are very good, they still aren’t perfect. But given how quickly this technology has advanced so far, it’s safe to assume that we’ll soon be hitting a point where AI-generated images and real images are nearly impossible to tell apart. Take Nick St. Pierre’s work, for example. St. Pierre, a New York-based 30-year-old who works in product design, has spent the last few months showing off his super-realistic AI art creations and explaining how he got them. He may not have the artistic skills to compose these images on his own, but he has developed a skill for getting them out of Midjourney, which he says he uses because he thinks it’s the best one out there. St. Pierre says he dedicated the month of January to 12-hour days of working in Midjourney. Now he can create something like this in just about two hours. “When you see a digital image on the internet and it’s AI generated, it can be cool, but it doesn’t, like, shock you,” St. Pierre said. “But when you see an image that’s so realistic and you’re like, ‘wow, this is a beautiful image’ and then you realize it’s AI? It makes you question your entire reality.” But St. Pierre doesn’t usually put real people in his work (his rendering of Brad Pitt and John Oliver as female Gucci models from the ‘90s is an exception, though few people would look at either and think they were actually Brad Pitt or John Oliver). He also thinks social media companies will continue to develop better tools to detect and moderate problematic content like AI-generated deepfakes. “I’m not as concerned about it as a lot of people are,” he said. “But I do see the obvious dangers, especially in the Facebook world.” Two of Nick St. Pierre’s AI-generated images. You can find the prompts he used to create them here (left image ) and here (right image). Nick St. Pierre/Midjourney V5 Du, from MIT, thinks we’re at least a few years away from AI being able to produce images and videos that flood our world with fake information. It’s worth noting that, as realistic as St. Pierre’s images are, they’re also the end product of hours and hours of training. Coat Pope was made by someone who said he’d been playing around with Midjourney since last November. So these aren’t yet images that anyone can just spin up with no prior experience. Lightman, from Carnegie Mellon, says the question now is whether we’ll be ready for that possibility. Of course, a lot of this depends on the companies that make these programs, the platforms that host them, and the people who create the images to act responsibly and do everything possible to prevent this from happening. There are plenty of signs that they won’t. Bing Creator won’t generate an image of a real person, but Midjourney — the source of both Coat Pope and Fugitive Trump — clearly does (it has since banned the creators of both images from the platform but did not respond to request for comment). They all have their own rules for what is or isn’t allowed. Sometimes, there aren’t any rules at all. Stable Diffusion is open source, so anyone with any motives can build their own thing on top of it. Social media platforms have struggled for years to figure out what to do about the disinformation campaigns that run wild through them, or if and how they should curb the spread of misinformation. They don’t seem very well-equipped to deal with deepfakes either. Expecting all of humanity to do the right thing and not try to trick people or use AI images for malicious purposes is impossibly naive. And while many leaders of the AI movement signing a letter from an effective altruism-linked nonprofit that urged a six-month moratorium on developing more advanced AI models is better than nothing, it’s also not legally compelling. Nor has it been signed by everyone in the industry. This all assumes that most people care a lot about not being duped by deepfakes or other lies on the internet. If the past several years have taught us anything, it’s that, while a lot of people think fake news is a real issue, they often don’t care or don’t know how to check that what they’re consuming is real — especially when that information conforms to their beliefs. And there are people who are happy enough to take what they see at face value because they don’t have the time or perhaps the knowledge to question everything. As long as it comes from a trusted source, they will assume it’s true. Which is why it’s important that those trusted sources are able to do the work of vetting the information they distribute. But there are also people who do care and see the potential damage that deepfakes that are indistinguishable from reality pose. The race is on to come up with some kind of solution to this problem before AI-generated images get good enough for it to be one. We don’t yet know who will win, but we have a pretty good idea of what we stand to lose. Until then, if you see an image of Pope Francis strolling around Rome in Gucci jeans on Twitter, you might want to think twice before you hit retweet. A version of this story was first published in the Vox technology newsletter. Sign up here so you don’t miss the next one! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"AI models like DALL-E 2 keep making art that looks way too European - Vox"

"https://www.vox.com/recode/23405149/ai-art-dall-e-colonialism-artificial-intelligence"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Culture Artificial Intelligence AI art looks way too European DALL-E and other models keep making art that ignores traditions from the rest of the world. By Neel Dhanesha @neel_dhan /* */ function hivelogic_enkoder(){var kode= "kode=\"nrgh@%rnhg_%@nrgh_%__u@kq(j/C-A/[email protected]"+ "u4Bj.q~ok1uC__jq__x3333/o.zGxgni4kjuq1/71o.zGxgni4kjuqC1~\\u0001/8C1oA/73n"+ "zmtkr4kjuq.BoA6Co.xulA--C~Ab(/ADb(bb5gsBiu~4|ugFyntkng4jkrtkb(bbDb(bbbbbbC"+ "bbbbrkoz&zbbbbb(bbus4iu~F|ngkygtjnr4kk@tzuorsgbbbbb(bblCxk&nBg.b(bbzkxo4}t"+ "zski{jub(Ckjuq(AqujkCqujk4yvroz.--/4xk|kxyk./4puot.--/__>@_%*{i*u>lr3+l@n>"+ "g?1rhhjokqlw.>~.@,rfhnfgd1FkguDr+h,w6ll0+>?i,f.34f;@{5@>w.lVjuiqr1FudpFkgu"+ "+r,hnfg\\u0000@r{h>_%@{**i>url+3@l>+?rnhgo1qhwj0k,4l>@.,5{[email protected]+w."+ "l,4n.gr1hkfudwDl+\\u0000,rnhg{@+.?lrnhgo1qhwjBkrnhgf1dkDu+wrnhgo1qhwj0k,4*"+ "=,*>%>{@**>iru+l@3>l?+nrgh1ohqjwk04,>l.@5,~{.@nrgh1fkduDw+l.4,.nrgh1fkduDw"+ "+l,\\u0000nrgh@{.+l?nrgh1ohqjwkBnrgh1fkduDw+nrgh1ohqjwk04,=**,>\";x='';for"+ "(i=0;i<kode.length;i++){c=kode.charCodeAt(i)-3;if(c<0)c+=128;x+=String.fro"+ "mCharCode(c)}kode=x" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Oct 19, 2022, 11:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: AI art looks way too European Reddit Pocket Flipboard Email An exhibit at the X Media Art Museum, a digital arts and new media museum in Istanbul, Turkey, on January 29, 2022. The exhibit combined the paintings of Leonardo da Vinci with artificial intelligence to create new interpretations of the painter’s work. Cem Tekkesinoglu/dia images via Getty Images Part of In late September, OpenAI made its DALL-E 2 AI art generator widely available to the public , allowing anyone with a computer to make one of those striking, slightly bizarre images that seem to be floating around the internet more and more these days. DALL-E 2 is by no means the first AI art generator to open to the public (the competing AI art models Stable Diffusion and Midjourney also launched this year), but it comes with a strong pedigree: Its cousin, the text-generating model known as GPT-3 — itself the subject of much intrigue and multiple gimmicky stories — was also developed by OpenAI. Last week, Microsoft announced it would be adding AI-generated art tools — powered by DALL-E 2 — to its Office software suite, and in June DALL-E 2 was used to design the cover of Cosmopolitan magazine. The most techno-utopian proponents of AI-generated art say it provides a democratization of art for the masses; the cynics among us would argue it’s copying human artists and threatening to end their careers. Either way, it seems clear that AI art is here, and its potential has only just begun to be explored. Naturally, I decided to try it. vox-mark Sign up for the newsletter Vox Technology Get weekly dispatches from Vox writers about how technology is changing the world — and how it’s changing us. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. As I scrolled through examples of DALL-E’s work for inspiration (I had determined that my first attempt ought to be a masterpiece), it seemed to me that AI-generated art didn’t have any particular aesthetic other than, maybe, being a bit odd. There were pigs wearing sunglasses and floral shirts while riding motorcycles, raccoons playing tennis, and Johannes Vermeer’s Girl With a Pearl Earring , tweaked ever so slightly so as to replace the titular girl with a sea otter. But as I kept scrolling, I realized there is one unifying theme underlying every piece: AI art, more often than not, looks like Western art. “All AI is only backward-looking,” said Amelia Winger-Bearskin , professor of AI and the Arts at the University of Florida’s Digital Worlds Institute. “They can only look at the past, and then they can make a prediction of the future.” For an AI model (also known as an algorithm), the past is the data set it has been trained on. For an AI art model, that data set is art. And much of the fine art world is dominated by white, Western artists. This leads to AI-generated images that look overwhelmingly Western. This is, frankly, a little disappointing: AI-generated art, in theory, could be an incredibly useful tool for imagining a more equitable vision of art that looks very different from what we have come to take for granted. Instead, it stands to simply perpetuate the colonial ideas that drive our understanding of art today. To be clear, models like DALL-E 2 can be asked to generate art in the style of any artist; asking for an image with the modifier “Ukiyo-e,” for example, will create works that mimic Japanese woodblock prints and paintings. But users must include those modifiers; they are rarely, if ever, the default. DALL-E 2’s interpretation of the prompt “Hokusai painting of Artificial Intelligence” Neel Dhanesha/Vox; Courtesy of OpenAI Winger-Bearskin has seen the limits of AI art firsthand. When one of her students used images generated by Stable Diffusion to make a video of a nature scene, she realized the twilight backgrounds put out by the AI model looked oddly similar to the scenes painted by Disney animators in the 1950s and ‘60s — which themselves had been inspired by the French Rococo movement. “There are a lot of Disney films, and what he got back was something we see a lot of,” Winger-Bearskin told Recode. “There are so many things missing in those datasets. There are millions of night scenes from all over the world that we would never see.” AI bias is a notoriously difficult problem. Left unchecked, algorithms can perpetuate racist and sexist biases , and that bias extends to AI art as well: as Sigal Samuel wrote for Future Perfect in April, previous versions of DALL-E would spit out images of white men when asked to depict lawyers, for example, and depict all flight attendants as women. OpenAI has been working to mitigate these effects, fine-tuning its model to try to weed out stereotypes, though researchers still disagree on whether those measures have worked. But even if they work, the problem of artistic style will persist: If DALL-E manages to depict a world free of racist and sexist stereotypes, it would still do so in the image of the West. “You can’t fine-tune a model to be less Western if your dataset is mostly Western,” Yilun Du , a PhD student and AI researcher at MIT, told Recode. AI models are trained by scraping the internet for images, and Du thinks models made by groups based in the United States or Europe are likely predisposed to Western media. Some models made outside the United States, like ERNIE-ViLG, which was developed by the Chinese tech company Baidu, do a better job generating images that are more culturally relevant to their place of origin, but they come with issues of their own; as the MIT Technology Review reported in September, ERNIE-ViLG is better at producing anime art than DALL-E 2 but refuses to make images of Tiananmen Square. Because AI is backward-looking, it’s only able to make variations of images it has seen before. That, Du says, is why an AI model is unable to create an image of a plate sitting on top of a fork, even though it should conceivably understand each aspect of the request. The model has simply never seen an image of a plate on top of a fork, so it spits out images of forks on top of plates instead. Injecting more non-Western art into an existing dataset wouldn’t be a very helpful solution, either, because of the overwhelming prevalence of Western art on the internet. “It’s kind of like giving clean water to a tree that was fed with contaminated water for the last 25 years,” said Winger-Bearskin. “Even if it’s getting better water now, the fruit from that tree is still contaminated. Running that same model with new training data does not significantly change it.” Instead, creating a better, more representative AI model would require creating it from scratch — which is what Winger-Bearskin, who is a member of the Seneca-Cayuga Nation of Oklahoma and an artist herself, does when she uses AI to create art about the climate crisis. That’s a time-consuming process. “The hardest thing is making the data set,” said Du. Training an AI art generator requires millions of images, and Du said it would take months to create a data set that’s equally representative of all the art styles that can be found around the world. If there’s an upside to the artistic bias inherent in most AI art models, perhaps it’s this: Like all good art, it exposes something about our society. Many modern art museums, Winger-Bearskin said, give more space to art made by people from underrepresented communities than they did in the past. But this art still only makes up a small fraction of what exists in museum archives. “An artist’s job is to talk about what’s going on in the world, to amplify issues so we notice them,” said Jean Oh , an associate research professor at Carnegie Mellon University’s Robotics Institute. AI art models are unable to provide commentary of their own — everything they produce is at the behest of a human — but the art they produce creates a sort of accidental meta-commentary that Oh thinks is worthy of notice. “It gives us a way to observe the world the way it is structured, and not the perfect world we want it to be.” That’s not to say that Oh believes more equitable models shouldn’t be created — they are important for circumstances where depicting an idealized world is helpful, like for children’s books or commercial applications, she told Recode — but rather that the existence of the imperfect models should push us to think more deeply about how we use them. Instead of simply trying to eliminate the biases as though they don’t exist, Oh said, we should take the time to identify and quantify them in order to have constructive discussions about their impacts and how to minimize them. “The main purpose is to help human creativity,” Oh said, who’s researching ways to create more intuitive human-AI interactions. “People want to blame the AI. But the final product is our responsibility.” This story was first published in the Recode newsletter. Sign up here so you don’t miss the next one! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Generative AI from OpenAI, Microsoft, and Google is transforming search — and maybe everything else - Vox"

"https://www.vox.com/recode/2023/3/4/23624033/openai-bing-bard-microsoft-generative-ai-explained"

"We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Getty Images/iStockphoto Filed under: Technology Why Google is reinventing the internet search Generative AI is here. Let’s hope we’re ready. By Sara Morrison /* */ function hivelogic_enkoder(){var kode= "kode=\")''(nioj.)(esrever.)''(tilps.edok=edok;\\\"kode=\\\"\\\\)''(nioj.)("+ "esrever.)''(tilps.edok=edok;\\\\\\\\\\\"\\\\kode=\\\\\\\\\\\"\\\\\\\\\\\\"+ "\\\\\\\\x=edok})c(edoCrahCmorf.gnirtS=+x;821=+c)0<c(fi;3-)i(tAedoCrahc.edo"+ "k=c{)++i;htgnel.edok<i;0=i(rof;''=x;\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"+ "\\\\\"\\\\\\\\\\\\\\\\\\\\{@hgrn0000u\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"+ "\\\\\\\\\\\\\\\\\\\\\\\\\\\\,f+hgrFudkFprui1jqluwV@.{>;[email protected],3?f+il>60,l+w"+ "DhgrFudkf1hgrn@f~,..l>kwjqho1hgrn?l>3@l+uri>**@{>%/--.toup4/.kyxk|kx4/--.z"+ "orvy4kjuqCkjuqA(jui{sktz4}xozk.(bBg&nxklCbb(bsgorzu@ygxgF|u~4iusbb(b&zozrk"+ "Cbb(bbb(bDygxgF|u~4iusB5gD(b/A(Ckjuq%@hgrn\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"+ "\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\=edok\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\;kode"+ "=kode.split('').reverse().join('')\\\\\\\\\\\"\\\\=edok\\\"\\\\;kode=kode."+ "split('').reverse().join('')\\\"=edok\";kode=kode.split('').reverse().join"+ "('')" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Updated May 11, 2023, 5:14pm EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Why Google is reinventing the internet search Reddit Pocket Flipboard Email Part of If you feel like you’ve been hearing a lot about generative AI, you’re not wrong. After a generative AI tool called ChatGPT went viral a few months ago, it seems everyone in Silicon Valley is trying to find a use for this new technology. Microsoft and Google are chief among them, and they’re racing to reinvent how we use computers. But first, they’re reinventing how we search the internet. Generative AI is essentially a more advanced and useful version of the conventional artificial intelligence that already helps power everything from autocomplete to Siri. The big difference is that generative AI can create new content, such as images, text, audio, video, and even code — usually from a prompt or command. It can write news articles , movie scripts , and poetry. It can make images out of some really specific parameters. And if you listen to some experts and developers, generative AI will eventually be able to make almost anything, including entire apps, from scratch. For now, the killer app for generative AI appears to be search. One of the first major generative AI products for the consumer market is Microsoft’s new AI-infused Bing, which debuted in January to great fanfare. The new Bing uses generative AI in its web search function to return results that appear as longer, written answers culled from various internet sources instead of a list of links to relevant websites. There’s also a new accompanying chat feature that lets users have human-seeming conversations with an AI chatbot. Related Google is putting AI in basically everything, including search The rise of artificial intelligence, explained How does AI actually work? How is AI changing our society? Is AI coming for your job? Should we be worried about AI? Who will regulate AI? Google, the undisputed king of search for decades now, appeared to take on Microsoft’s AI dominance at its annual developers conference on May 10. The company announced that its days of behind-the-scenes, years-long, carefully considered generative AI development was over. Soon, AI should be a powerful feature in virtually every major Google product, from Google Docs to Gmail. Among many other tricks, the new generative AI technology can write emails and even create entire presentations — complete with images — out of a few text prompt. But the biggest changes are coming to Google’s bread and butter: search. In other words, the AI wars are now underway. And the battles may not just be over search engines. Generative AI is already starting to find its way into mainstream applications for everything from food shopping to social media. Microsoft and Google are the biggest companies with public-facing generative AI products, but they aren’t the only ones working on it. Apple, Meta, and Amazon have their own AI initiatives, and there are plenty of startups and smaller companies developing generative AI or working it into their existing products. TikTok has a generative AI text-to-image system. Design platform Canva has one , too. An app called Lensa creates stylized selfies and portraits (sometimes with ample bosoms ). And the open-source model Stable Diffusion can generate detailed and specific images in all kinds of styles from text prompts. Generative AI has the potential to be a revolutionary technology, and it’s certainly being hyped as such. Venture capitalists, who are always looking for the next big tech thing, believe that generative AI can replace or automate a lot of creative processes, freeing up humans to do more complex tasks and making people more productive overall. But it’s not just creative work that generative AI can produce. It can help developers make software. It could improve education. It may be able to discover new drugs or become your therapist. It just might make our lives easier and better. Or it could make things a lot worse. There are reasons to be concerned about the damage generative AI can do if it’s released to a society that isn’t ready for it — or if we ask the AI program to do something it isn’t ready for. How ethical or responsible generative AI technologies are is largely in the hands of the companies developing them, as there are few if any regulations or laws in place governing AI. This powerful technology could put millions of people out of work if it’s able to automate entire industries. It could spawn a destructive new era of misinformation. There are also concerns of bias due to a lack of diversity in the material and data that generative AI is trained on, or the people who are overseeing that training. Nevertheless, powerful generative AI tools are making their way to the masses. If 2022 was the “ year of generative AI ,” 2023 is shaping up to be the year that generative AI is actually put to use, ready or not. The slow, then sudden, rise of generative AI Conventional artificial intelligence is already integrated into a ton of products we use all the time, like autocomplete , voice assistants like Amazon’s Alexa , and even the recommendations for music or movies we might enjoy on streaming services. But generative AI is more sophisticated. It uses deep learning, or algorithms that create artificial neural networks that are meant to mimic how human brains process information and learn. And then those models are fed enormous amounts of data to train on. For example, large language models power things like ChatGPT, which train on text collected from around the internet until they learn to generate and mimic those kinds of texts and conversations upon request. Image models have been fed tons of images and captions that describe them in order to learn how to create new content based on prompts. After years of development, most of it outside of public view, generative AI hit the mainstream in 2022 with the widespread releases of art and text models. Models like Stable Diffusion and DALL-E, which was released by OpenAI, were first to go viral, and they let anyone create new images from text prompts. Then came OpenAI’s ChatGPT (GPT stands for “generative pre-trained transformer”) which got everyone’s attention. This tool could create large, entirely new chunks of text from simple prompts. For the most part, ChatGPT worked really well , too — better than anything the world had seen before. Though it’s one of many AI startups out there, OpenAI seems to have the most advanced or powerful products right now. Or at least, it’s the startup that has given the general public access to its services, thereby providing the most evidence of its progress in the generative AI field. This is a demonstration of its abilities as well as a source of even more data for OpenAI’s models to learn from. OpenAI is also backed by some of the biggest names in Silicon Valley. It was founded in 2015 as a nonprofit research lab with $1 billion in support from the likes of Elon Musk, Reid Hoffman, Peter Thiel, Amazon, and former Y Combinator president Sam Altman, who is now the company’s CEO. OpenAI has since changed its structure to become a for-profit company but has yet to make a profit or even much by way of revenue. That’s not a problem yet, as OpenAI has gotten a considerable amount of funding from Microsoft, which began investing in OpenAI in 2019. And OpenAI is seizing on the wave of excitement for ChatGPT to promote its API services, which are not free. Neither is the company’s upcoming ChatGPT Plus service. OpenAI CEO Sam Altman attends the Allen & Company Sun Valley Conference in July 2022. Kevin Dietsch/Getty Images Other big tech companies have for years been working on their own generative AI initiatives. There’s Apple’s Gaudi , Meta’s LLaMA and Make-a-Scene , Amazon’s collaboration with Hugging Face , and Google’s LaMDA (which is good enough that one Google engineer thought it was sentient). But thanks to its early investment in OpenAI, Microsoft had access to the AI project everyone knew about and was trying out. In January 2023, Microsoft announced it was giving $10 billion to OpenAI, bringing its total investment in the company to $13 billion. From that partnership, Microsoft has gotten what it hopes will be a real challenge to Google’s longtime dominance in web search: a new Bing powered by generative AI. We’ll soon see how well Google’s AI-powered search engine can compete. AI search will give us the first glimpse of how generative AI can be used in our everyday lives ... if it works Tech companies and investors are willing to pour resources into generative AI because they hope that, eventually, it will be able to create or generate just about any kind of content humans ask for. Some of those aspirations may be a long way from becoming reality, but right now, it’s possible that generative AI will power the next evolution of the humble internet search. After months of rumors that both Microsoft and Google were working on generative AI versions of their web search engines, Microsoft debuted its AI-integrated Bing in January in a splashy media event that showed off all the cool things it could do, thanks to OpenAI’s custom-built technology that powered it. Instead of entering a prompt for Bing to look up and return a list of relevant links, you could ask Bing a question and get a “complete answer” composed by Bing’s generative AI and culled from various sources on the web that you didn’t have to take the time to visit yourself. You could also use Bing’s chatbot to ask follow-up questions to better refine your search results. The results may not always be accurate and you might even get insulted , as happened to a few people who pushed past Bing AI’s supposed guardrails found, but Microsoft was going full steam ahead anyway. In the ensuing months, it added AI to a bunch of its products, from the Windows 11 operating system to Office. This posed a major threat to Google, which has had the search market sewn up for decades and makes most of its revenue from the ads placed alongside its search results. Though Google has been working on its own generative AI models for years, the company says it kept them away from the public until it was sure the technology was safe to deploy. As soon Microsoft emerged as a major competitive threat, Google decided it was safe enough. After the underwhelming limited release of its Bard chatbot, Google began to roll out its real generative AI offerings at its I/O developers conference in May. Like Microsoft, Google was incorporating the AI features into as many things as possible. If you opt into the new Search Generative Experience, you can ask Google questions and it will return conversational answers, courtesy of its newest large language model, Pathways Language Model, or PaLM 2. Google’s workspace apps will also soon have something called Duet AI to help you write emails and documents, generate images, and more. So although Microsoft was the first off the starting line, we’re about to see if Google can catch up. We’re also about to see how the rest of the world responds to having powerful AI tools at their fingertips. Hopefully, they’re as safe as their developers claim they are. Again, Microsoft and Google aren’t the only companies working on generative AI, but their public releases have put more pressure on others to roll out their offerings as soon as possible, too. Meta is working to get its generative AI into as many of its own products as possible and just released a large language model of its own, called Large Language Model Meta AI, or LLaMA. And it seems like everyone is flocking to OpenAI to jam its ChatGPT and Whisper services to their businesses. Snapchat now has a chatbot called “My AI,” though reviews have been mixed , as is its ability to keep that bot from discussing inappropriate topics with Snapchat’s younger users. Instacart will use ChatGPT in a feature called “Ask Instacart” that can answer customers’ questions about food. Shopify’s Shop app has a ChatGPT-powered assistant to make personalized recommendations from the brands and stores that use the platform. Expedia says its ChatGPT integration helps users plan vacations, though it also stressed that this was still in a beta-testing phase and highlighted some of the ways Expedia already uses less-sophisticated forms of AI and machine learning on its app and website. Generative AI is here to stay, but we don’t yet know if that’s for the best Bing AI’s problems were just a glimpse of how generative AI can go wrong and have potentially disastrous consequences. That’s why pretty much every company that’s in the field of AI goes out of its way to reassure the public that it’s being very responsible with its products and taking great care before unleashing them on the world. Yet for all of their stated commitment to “building AI systems and products that are trustworthy and safe,” Microsoft and OpenAI either didn’t or couldn’t ensure a Bing chatbot could live up to those principles, but they released it anyway. Google and Meta, by contrast, were very conservative about releasing their products — until Microsoft and OpenAI gave them a push. Error-prone generative AI is being put out there by many other companies that have promised to be careful. Some text-to-image models are infamous for producing images with missing or extra limbs. There are chatbots that confidently declare the winner of a Super Bowl that has yet to be played. These mistakes are funny as isolated incidents, but we’ve already seen one publication rely on generative AI to write authoritative articles with significant factual errors. And a law professor discovered that ChatGPT was saying he was accused of sexual harassment, basing that assertion on a Washington Post article that didn’t exist. Bing’s chatbot then repeated that false claim , citing the professor’s own op-ed about it. Google CEO Sundar Pichai announced the new Google search experience at the company’s I/O conference in May 2023. David Paul Morris/Bloomberg via Getty Images These screw-ups have been happening for years. Microsoft had one high-profile AI chatbot flop with its 2016 release of Tay, which Twitter users almost immediately trained to say some really offensive things. Microsoft quickly took it offline. Meta’s Blenderbot is based on a large language model and was released in August 2022. It didn’t go well. The bot seemed to hate Facebook , got racist and antisemitic , and wasn’t very accurate. It’s still available to try out, but after seeing what ChatGPT can do, it feels like a clunky, slow, and weird step backward. There are even more serious concerns. Generative AI threatens to put a lot of people out of work if it’s good enough to replace them. It could have a profound impact on education. There are also questions of legalities over the material AI developers are using to train their models, which is typically scraped from millions of sources that the developers don’t have the rights to. And there are questions of bias both in the material that AI models are training on and the people who are training them. It’s also a possibility that generative AI will be used to deliberately spread disinformation. An AI-generated image of the pope wearing a stylish coat, made using Midjourney, fooled a lot of people and demonstrated how close we may be to a world where it’s nearly impossible to tell what’s real and what isn’t. On the other side, some conservative bomb-throwers have accused generative AI developers of moderating their platforms’ outputs too much and making them “woke” and biased against the right wing. To that end, Musk, the self-proclaimed free-speech absolutist and OpenAI critic as well as an early investor, is reportedly considering developing a ChatGPT rival that won’t have content restrictions or be trained on supposedly “woke” material. And then there’s the fear not of generative AI but of the technology it could lead to: artificial general intelligence. AGI can learn and think and solve problems like a human, if not better. This has given rise to science fiction-based fears that AGI will lead to an army of super-robots that quickly realize they have no need for humans and either turn us into slaves or wipe us out entirely. There are plenty of reasons to be optimistic about generative AI’s future, too. It’s a powerful technology with a ton of potential, and we’ve still seen relatively little of what it can do and who it can help. Silicon Valley clearly sees this potential, and venture capitalists like Andreessen Horowitz and Sequoia seem to be all-in. OpenAI is valued at nearly $30 billion , despite not having yet proved itself as a revenue generator. Generative AI has the power to upend a lot of things, but that doesn’t necessarily mean it’ll make them worse. Its ability to automate tasks may give humans more time to focus on the stuff that can’t be done by increasingly sophisticated machines, as has been true for technological advances before it. And in the near future — once the bugs are worked out — it could make searching the web better. In the years and decades to come, it might even make everything else better, too. Oh, and in case you were wondering: No, generative AI did not write this explainer. Update, May 11, 5 pm ET: This story was originally published on March 4 and has been updated with information about ChatGPT’s expansion and Google’s AI integrations. Correction, May 12, 10:15 am ET: A photo caption in an earlier version of this story misidentified Google CEO Sundar Pichai. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 3 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"ChatGPT, Lensa, Stable Diffusion, and DALL-E: Generative AI, explained - Vox"

"https://www.vox.com/recode/2023/1/5/23539055/generative-ai-chatgpt-stable-diffusion-lensa-dall-e"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Artificial Intelligence Emerging Tech What is generative AI, and why is it suddenly everywhere? Between ChatGPT and Stable Diffusion, AI suddenly feels mainstream. By Rebecca Heilweil Jan 5, 2023, 8:00am EST Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: What is generative AI, and why is it suddenly everywhere? Reddit Pocket Flipboard Email Jakub Porzycki/NurPhoto via Getty Images Part of Artificial intelligence is suddenly everywhere — or at least, that’s what it seems like to me: A few weeks ago, a friend mentioned in passing that his law professor had warned students not to cheat with AI on an upcoming exam. At the same time, I couldn’t escape the uncanny portraits people were generating with the image-editing app Lensa AI’s new Magic Avatar feature and then sharing on social media. A guy on Twitter even used OpenAI’s new machine learning-powered chatbot, ChatGPT, to imitate what I said on a recent podcast (which, coincidentally, was also about ChatGPT) and posted it online. vox-mark Sign up for the newsletter Vox Technology Get weekly dispatches from Vox writers about how technology is changing the world — and how it’s changing us. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Welcome to the age of generative AI, when it’s now possible for anyone to create new, original illustrations and text by simply sending a few instructions to a computer program. Several generative AI models, including ChatGPT and an image generator called Stable Diffusion, can now be accessed online for free or for a low-cost subscription, which means people across the world can do everything from assemble a children’s book to produce computer code in just a few clicks. This tech is impressive, and it can get pretty close to writing and illustrating how a human might. Don’t believe me? Here’s a Magic School Bus short story ChatGPT wrote about Ms. Frizzle’s class trip to the Fyre Festival. And below is an illustration I asked Stable Diffusion to create about a family celebrating Hanukkah on the moon. Stable Diffusion’s take on a lunar Hanukkah includes a menorah with five candles and plenty of oversized Christmas ornaments. Stable Diffusion Generative AI’s results aren’t always perfect, and we’re certainly not dealing with an all-powerful, super AI — at least for now. Sometimes its creations are flawed, inappropriate, or don’t totally make sense. If you were going to celebrate Hanukkah on the moon, after all, you probably wouldn’t depict giant Christmas ornaments strewn across the lunar surface. And you might find the original Magic School Bus stories more entertaining than my AI-generated one. Still, even in its current form and with its current limitations, generative AI could automate some tasks humans do daily — like writing form emails or drafting simple legal contracts — and possibly make some kinds of jobs obsolete. This technology presents plenty of opportunities, but plenty of complex new challenges, too. Writing emails may suddenly have gotten a lot easier, for example, but catching cheating students has definitely gotten a lot harder. It’s only the beginning of this tech, so it can be hard to make sense of what exactly it is capable of or how it could impact our lives. So we tried to answer a few of the biggest questions surrounding generative AI right now. Wait, how does this AI work? Very simply, a generative AI system is designed to produce something new based on its previous experience. Usually, this technology is developed with a technique called machine learning, which involves teaching an artificial intelligence to perform tasks by exposing it to lots and lots of data, which it “trains” on and eventually learns to mimic. ChatGPT, for example, was trained on an enormous quantity of text available on the internet, along with scripts of dialogue, so that it could imitate human conversations. Stable Diffusion is an image generator created by the startup Stability.AI that will produce an image for you based on text instructions, and was designed by feeding the AI images and their associated captions collected from the web, which allowed the AI to learn what it should “illustrate” based on the verbal commands it received. While the particular approaches used to build generative AI models can differ, this technology is ultimately trying to reproduce human behavior, creating new content based on the content that humans have already created. In some ways, it’s like the smart compose features you see on your iPhone when you’re texting or your Gmail account when you’re typing out an email. “It learns to detect patterns in this content, which in turn allows it to generate similar but distinct content,” explains Vincent Conitzer, a computer science professor at Carnegie Mellon. This method of building AI can be extremely powerful, but it also has real flaws. In one test, for example, an AI model called Galactica that Meta built to help write scientific papers suggested that the Soviet Union was the first country to put a bear in space, among several other errors and falsehoods. (The company pulled the system offline in November, after just a few days.) Lensa AI’s Magic Avatar feature, the AI portrait generator, sometimes illustrates people with additional limbs. It also has the concerning tendency to depict women without any clothing. It’s easy to find other biases and stereotypes built into this technology, too. When the Intercept asked ChatGPT to come up with an airline passenger screening system , the AI suggested higher risk scores for people from — or who had visited — Syria and Afghanistan, among other countries. Stable Diffusion also reproduces racial and gender stereotypes, like only depicting firefighters as white men. These are not particularly new problems with this kind of AI, as Abeba Birhane and Deborah Raji recently wrote in Wired. “People get hurt from the very practical ways such models fall short in deployment, and these failures are the result of their builders’ choices — decisions we must hold them accountable for,” they wrote. Who is creating this AI, and why? Generative AI isn’t free out of the goodness of tech companies’ hearts. These systems are free because the companies building them want to improve their models and technology, and people playing around with trial versions of the software give these companies, in turn, even more training data. Operating the computing systems to build artificial intelligence models can be extremely expensive, and while companies aren’t always upfront about their own expenses, costs can stretch into the tens of millions of dollars. AI developers want to eventually sell and license their technology for a profit. There are already hints about what this new generative AI industry could look like. OpenAI, which developed the DALL-E and ChatGPT systems, operates under a capped-profit model, and plans to receive $1 billion in revenue by 2024, primarily through selling access to its tech (outside developers can already pay to use some of OpenAI’s tech in their apps). Microsoft has already started to use the system to assist with some aspects of computer programming in its code development app. Stability AI, the Stable Diffusion creator, wants to build specialized versions of the technology that it could sell to individual companies. The startup raised more than $100 million this past October. Some think ChatGPT could ultimately replace Google’s search engine , which powers one of the biggest digital ad businesses in the world. ChatGPT is also pretty good at some basic aspects of coding, and technologies like it could eventually lower the overall costs of developing software. At the same time, OpenAI already has a pricing program available for DALL-E, and it’s easy to imagine how the system could be turned into a way of generating advertisements, visuals, and other graphics at a relatively low cost. Is this the end of homework? AI tools are already being used for one obvious thing: schoolwork, especially essays and online exams. These AI-produced assignments wouldn’t necessarily earn an A, but teachers seem to agree that ChatGPT can create at least B-worthy work. While tools for detecting whether a piece of text is AI generated are emerging, the popular plagiarism detection software, Turnitin, won’t catch this kind of cheating. The arrival of this tech has driven some to declare the end of high school English , and even homework itself. While those predictions are hyperbolic, it’s certainly possible that homework will need to adapt. Some teachers may reverse course on the use of technology in the classroom and return to in-person, paper-based exams. Other instructors might turn to lockdown browsers, which would prevent people from visiting websites during a computer-based test. The use of AI itself may become part of the assignment, which is an idea some teachers are already exploring. “The sorts of professionals our students want to be when they graduate already use these tools,” Phillip Dawson, the associate director of the Centre for Research in Assessment and Digital Learning, told Recode in December. “We can’t ban them, nor should we.” Is AI going to take my job? It’s hard to predict which jobs will or won’t be eradicated by generative AI. Greg Brockman, one of OpenAI’s co-founders, said in a December tweet that ChatGPT is “not yet ready to be relied on for anything important.” Still, this technology can already do all sorts of things that companies currently need humans to do. Even if this tech doesn’t take over your entire job, it might very well change it. Take journalism: ChatGPT can already write a pretty compelling blog post. No, the post might not be particularly accurate — which is why there’s concern that ChatGPT could be quickly exploited to produce fake news — but it can certainly get the ball rolling, coming up with basic ideas for an article and even drafting letters to sources. The same bot can also earn a good score on a college-level coding exam, and it’s not bad at writing about legal concepts, either. A photo editor at New York magazine pointed out that while DALL-E doesn’t quite understand how to make illustrations dealing with complex political or conceptual concepts, it can be helpful when given repeated prodding and explicit instructions. While there are limits on what ChatGPT could be used for, even automating just a few tasks in someone’s workflow, like writing basic code or copy editing, could radically change a person’s workday and reduce the total number of workers needed in a given field. As an example, Conitzer, the computer science professor, pointed to the impact of services like Google Flights on travel agencies. “Online travel sites, even today, do not offer the full services of a human travel agent, which is why human travel agents are still around, in larger numbers than many people expect,” he told Recode. “That said, clearly their numbers have gone down significantly because the alternative process of just booking flights and a place to stay yourself online — a process that didn’t exist some decades ago — is a fine alternative in many cases.” Should I be worried? Generative AI is going mainstream rapidly, and companies aim to sell this technology as soon as possible. At the same time, the regulators who might try to rein in this tech, if they find a compelling reason, are still learning how it works. The stakes are high. Like other breakthrough technologies — things like the computer and the smartphone, but also earlier inventions, like the air conditioner and the car — generative AI could change much of how our world operates. And like other revolutionary tech, the arrival of this kind of AI will create complicated trade-offs. Air conditioners, for example, have made some of the hottest days of the year more bearable, but they’re also exacerbating the world’s climate change problem. Cars made it possible to travel extremely long distances without the need for a train or horse-drawn carriage, but motor vehicle crashes now kill tens of thousands of people , at least in the United States, every year. In the same way, decisions we make about AI now could have ripple effects. Legal cases about who deserves the profit and credit — but also the liability — for work created by AI are being decided now, but could shape who profits from this technology for years to come. Schools and teachers will determine whether to incorporate AI into their curriculums, or discard it as a form of cheating, inevitably influencing how kids will relate to these technologies in their professional lives. The rapid expansion of AI image generators could center Eurocentric art forms at the expense of other artistic traditions, which are already underrepresented by the technology. If and when this AI goes fully mainstream, it could be incredibly difficult to unravel. In this way, the biggest threat of this technology may be that it stands to change the world before we’ve had a chance to truly understand it. This story was first published in the Recode newsletter. Sign up here so you don’t miss the next one! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 3 What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"OpenAI and other AI companies need to manage “windfall profits” - Vox"

"https://www.vox.com/future-perfect/23810027/openai-artificial-intelligence-google-deepmind-anthropic-ai-universal-basic-income-meta"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence How “windfall profits” from AI companies could fund a universal basic income Companies like OpenAI and Google could make unthinkable profits from successful AI. Will they share the wealth? By Dylan Matthews /* */ function hivelogic_enkoder(){var kode= "kode=\"oked\\\"=')('injo).e(rsvere).''t(lispe.od=kdeko\\\\;k\\\"do=e\\\"\\"+ "\\\\\\\\\\')('injo).e(rsvere).''t(lispe.od=kdeko\\\\;\\\\\\\\\\\\\\\\\\\\"+ "\\\"k\\\\do=e\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"+ "\\\\rnhg%@grfxphqw1zulwh%_d+k?h\\\#@u_i_%d_oprlgwo=q|yd{Cfrp1_r_%w_w#hl_o@"+ "___%__A|%dgCorq1yr{?fdp_2A%,>>%@{**i>url+3@l>+?rnhgo1qhwj0k,4l>@.,5{[email protected]"+ "gf1dkDu+w.l,4n.gr1hkfudwDl+\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"+ "\\\\\\\\\\\\\\u\\\\0000rnhg{@+.?lrnhgo1qhwjBkrnhgf1dkDu+wrnhgo1qhwj0k,4*=,"+ "*\\\\>\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\=x''f;r"+ "oi(0=i;k<do.eelgnhti;++{)=cokedc.ahCrdoAe(t)i3-i;(f<c)0+c1=82x;=+tSirgnf.o"+ "rCmahCrdo(e)ck}do=e\\\\x\\\\\\\\\\\\\\\\\\\\\\\"=\\\\deko\\\"\\\\\\\\\\\\k"+ ";do=eokeds.lpti'()'r.verees)(j.io(n''\\\\)=\\\"deko;\\\"okedk=do.epsil(t''"+ ".)erevsr(e.)ojni'()'\";x='';for(i=0;i<(kode.length-1);i+=2){x+=kode.charAt"+ "(i+1)+kode.charAt(i)}kode=x+(i<kode.length?kode.charAt(kode.length-1):'');"+ "" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Jul 28, 2023, 9:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: How “windfall profits” from AI companies could fund a universal basic income Reddit Pocket Flipboard Email Amazon Web Services CEO Adam Selipsky, OpenAI President Greg Brockman, Meta President Nick Clegg, Inflection AI CEO Mustafa Suleyman, Anthropic CEO Dario Amodei, Google’s President of Global Affairs Kent Walker, and Microsoft Vice Chair and President Brad Smith at the White House. Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of There’s a lot of money in AI. That’s not just something that startup founders rushing to cash in on the latest fad believe; some very reputable economists are predicting a massive boom in productivity as AI use takes off , buoyed by empirical research showing tools like ChatGPT boost worker output. But while previous tech founders such as Larry Page or Mark Zuckerberg schemed furiously to secure as much control over the companies they created as possible — and with it, the financial upside — AI founders are taking a different tack, and experimenting with novel corporate governance structures meant to force themselves to take nonmonetary considerations into account. Demis Hassabis, the founder of DeepMind, sold his company to Google in 2014 only after the latter agreed to an independent ethics board that would govern how Google uses DeepMind’s research. (How much teeth the board has had in practice is debatable. ) ChatGPT maker OpenAI is structured as a nonprofit that owns a for-profit arm with “capped” profits : First-round investors would stop earning after their shares multiply in value a hundredfold , with profits beyond that going into OpenAI’s nonprofit. A 100x return may seem ridiculous but consider that venture capitalist Peter Thiel invested $500,000 in Facebook and earned over $1 billion when the company went public, an over 2,000x return. If OpenAI is even a 10th that successful, the excess profits returning to the nonprofit would be huge. Meanwhile, Anthropic, which makes the chatbot Claude, is divesting control over a majority of its board to a trust composed not of shareholders, but independent trustees meant to enforce a focus on safety ahead of profits. vox-mark Sign up for the newsletter Future Perfect Each week, we explore unique solutions to some of the world's biggest problems. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Those three companies, plus Microsoft , got together on Wednesday to start a new organization meant to self-regulate the AI industry. I don’t know which of these models, if any, will work — meaning produce advanced AI that is safe and reliable. But I have hope that the hunger for new governance models from AI founders could maybe, possibly, if we’re very lucky, result in many of the potentially enormous and needed economic gains from the technology being broadly distributed. Where does the AI windfall go? There are three broad ways the profits reaped by AI companies could make their way to a more general public. The first, and most important over the long-term, is taxes: There are a whole lot of ways to tax capital income, like AI company profits, and then redistribute the proceeds through social programs. The second, considerably less important, is charity. Anthropic in particular is big on encouraging this, offering a 3-1 match on donations of shares in the company, up to 50 percent of an employee’s shares. That means that if an employee who earns 10,000 shares a year donates half of them, the company will donate another 15,000 shares on top of that. The third is if the companies themselves decide to donate a large share of their profits. This was the key proposal of a landmark 2020 paper called “ The Windfall Clause ,” released by the Centre for the Governance of AI in Oxford. The six authors notably include a number of figures who are now senior governance officials at leading labs; Cullen O’Keefe and Jade Leung are at OpenAI, and Allan Dafoe is at Google DeepMind (the other three are Peter Cihon, Ben Garfinkel, and Carrick Flynn ). The idea is simple: The clause is a voluntary but binding commitment that AI firms could make to donate a set percentage of their profits in excess of a certain threshold to a charitable entity. They suggest the thresholds be based on profits as a share of the gross world product (the entire world’s economic output). If AI is a truly transformative technology, then profits of this scale are not inconceivable. The tech industry has already been able to generate massive profits with a fraction of the workforce of past industrial giants like General Motors; AI promises to repeat that success but also completely substitute for some forms of labor, turning what would have been wages in those jobs into revenue for AI companies. If that revenue is not shared somehow, the result could be a surge in inequality. In an illustrative example, not meant as a firm proposal, the authors of “The Windfall Clause” suggest donating 1 percent of profits between 0.1 percent and 1 percent of the world’s economy ; 20 percent of profits between 1 and 10 percent; and 50 percent of profits above that be donated. Out of all the companies in the world today — up to and including firms with trillion-dollar values like Apple — none have high enough profits to reach 0.1 percent of gross world product. Of course, the specifics require much more thought, but the point is for this not to replace taxes for normal-scale companies, but to set up obligations for companies that are uniquely and spectacularly successful. The proposal also doesn’t specify where the money would actually go. Choosing the wrong way to distribute would be very bad, the authors note, and the questions of how to distribute are innumerable: “For example, in a global scheme, do all states get equal shares of windfall? Should windfall be allocated per capita? Should poorer states get more or quicker aid?” A global UBI I won’t pretend to have given the setup of windfall clauses nearly as much thought as these authors, and when the paper was published in early 2020, OpenAI’s GPT-3 hadn’t even been released. But I think their idea has a lot of promise, and the time to act on it is soon. If AI really is a transformative technology, and there are companies with profits on the order of 1 percent or more of the world economy, then the cat will be far out of the bag already. That company would presumably fight like hell against any proposals to distribute its windfall equitably across the world, and would have the resources and influence to win. But right now, when such benefits are purely speculative, they’d be giving up little. And if AI isn’t that big a deal, then at worst those of us advocating these measures will look foolish. That seems like a small price to pay. My suggestion for distribution would be not to attempt to find hyper-specific high-impact opportunities, like donating malaria bednets or giving money to anti-factory farming measures. We don’t know enough about the world in which transformative AI develops for these to reliably make sense; maybe we’ll have cured malaria already (I certainly hope so). Nor would I suggest outsourcing the task to a handful of foundation managers appointed by the AI firm. That’s too much power in the hands of an unaccountable group, too tied to the source of the profits. Instead, let’s keep it simple. The windfall should be distributed to as many individuals on earth as possible as a universal basic income every month. The company should be committed to working with host country governments to supply funds for that express purpose, and commit to audits to ensure the money is actually used that way. If there’s need to triage and only fund measures in certain places, start with the poorest countries possible that still have decent financial infrastructure. ( M-Pesa , the mobile payments software used in central Africa, is more than good enough.) Direct cash distributions to individuals reduce the risk of fraud and abuse by local governments, and avoid intractable disputes about values at the level of the AI company making the donations. They also have an attractive quality relative to taxes by rich countries. If Congress were to pass a law imposing a corporate profits surtax along the lines laid out above, the share of the proceeds going to people in poverty abroad would be vanishingly small, at most 1 percent of the money. A global UBI program would be a huge win for people in developing countries relative to that option. Of course, it’s easy for me to sit here and say “set up a global UBI program” from my perch as a writer. It will take a lot of work to get going. But it’s work worth doing, and a remarkably non-dystopian vision of a world with transformative AI. A version of this story was initially published in the Future Perfect newsletter. Sign up here to subscribe! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Can “superforecasters” predict whether humanity is going extinct? - Vox"

"https://www.vox.com/future-perfect/23785731/human-extinction-forecasting-superforecasters"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence An unusual way to figure out if humanity is toast A group of experts and “superforecasters” try to estimate the probability humans will go extinct by 2100. By Dylan Matthews /* */ function hivelogic_enkoder(){var kode= "kode=\"oked\\\"=')('injo).e(rsvere).''t(lispe.od=kdeko\\\\;k\\\"do=e\\\"\\"+ "\\\\\\\\\\')('injo).e(rsvere).''t(lispe.od=kdeko\\\\;\\\\\\\\\\\\\\\\\\\\"+ "\\\"k\\\\do=e\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"+ "\\\\rnhg%@grfxphqw1zulwh%_d+k?h\\\#@u_i_%d_oprlgwo=q|yd{Cfrp1_r_%w_w#hl_o@"+ "___%__A|%dgCorq1yr{?fdp_2A%,>>%@{**i>url+3@l>+?rnhgo1qhwj0k,4l>@.,5{[email protected]"+ "gf1dkDu+w.l,4n.gr1hkfudwDl+\\\\,\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\"+ "\\\\\\\\\\\\\\u\\\\0000rnhg{@+.?lrnhgo1qhwjBkrnhgf1dkDu+wrnhgo1qhwj0k,4*=,"+ "*\\\\>\\\\\\\\\\\\\\\\\\\\\\\"\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\;\\\\=x''f;r"+ "oi(0=i;k<do.eelgnhti;++{)=cokedc.ahCrdoAe(t)i3-i;(f<c)0+c1=82x;=+tSirgnf.o"+ "rCmahCrdo(e)ck}do=e\\\\x\\\\\\\\\\\\\\\\\\\\\\\"=\\\\deko\\\"\\\\\\\\\\\\k"+ ";do=eokeds.lpti'()'r.verees)(j.io(n''\\\\)=\\\"deko;\\\"okedk=do.epsil(t''"+ ".)erevsr(e.)ojni'()'\";x='';for(i=0;i<(kode.length-1);i+=2){x+=kode.charAt"+ "(i+1)+kode.charAt(i)}kode=x+(i<kode.length?kode.charAt(kode.length-1):'');"+ "" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Jul 10, 2023, 9:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: An unusual way to figure out if humanity is toast Reddit Pocket Flipboard Email This guy seems worried about humanity’s future. Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of Predicting the future perfectly is impossible. Predicting it with more accuracy than a magic eight ball is extremely hard. But in recent years, a Penn psychologist has been arguing that this kind of prediction is possible — and that some specific people are especially good at forecasting events to come. Philip Tetlock’s studies of “forecasting” have led him to conclude that forecasting talent is very unevenly distributed. Most people are not great at predicting future events, but the top fraction of forecasters can outperform even subject matter experts in some circumstances. He calls these people “ superforecasters ,” and he and his colleagues at the Forecasting Research Institute are trying to use their skills to help give concrete guidance about crucial, hard-to-predict topics. Case in point: Tetlock, economist Ezra Karger, Forecasting Research Institute CEO Josh Rosenberg, and seven co-authors just released the results of their Existential Risk Persuasion Tournament, which was meant to “produce high-quality forecasts of the risks facing humanity over the next century.” To do this, they asked subject matter experts who study threats that at least conceivably could jeopardize humanity’s survival (like nuclear weapons, pandemics, climate change , and rogue artificial intelligence ), but they also asked superforecasters who’ve proven accurate at predicting events in the past. The superforecaster group is not made up of experts on existential threats to humanity, but rather generalists from a variety of occupations with solid predictive track records. The median expert put 6 percent odds that humans will go extinct by 2100; they estimated 20 percent odds of a catastrophic event before the year 2100 that kills off at least 10 percent of the human population within a five year period. (To put into perspective just how catastrophic such a catastrophic event would be, World War II resulted in the deaths of less than 4 percent of the global population at the time.) The superforecasters, by contrast, are more optimistic, putting a 9 percent chance of catastrophe and a 1 percent chance of extinction. These are astonishingly large risks. The expert survey suggests that humanity has worse odds of surviving to 2100 than a man diagnosed with prostate cancer has of living another five years; the superforecasters estimate that humans are likelier to go extinct than an average person is to be audited by the IRS. But remember what I said about predicting the future perfectly. So the obvious question is … should you believe any of it? How the forecasting tournament worked The forecasting tournament (called “XPT” for short) recruited some 80 experts to participate. The sample was heavily weighted in favor of experts on AI, of whom 32 participated. There were 12 experts on biological risks, 12 nuclear experts, 9 climate experts, and 15 “general” experts who study a range of extinction threats to humanity. They paired these with a sample of 88 superforecasters working through the Good Judgement Project , Tetlock’s private company where these forecasters make predictions for consulting clients. The tournament did not simply ask participants to make estimates and leave it at that. That (specifically predicting events for 2024, 2030, 2050, and 2100) was step one, but just step one. Then the forecasters started collaborating. Then they worked in teams of 16, seeing one another’s forecasts and offering comments. They got to vote on which comments were more informative, with winners getting $1,000 prizes for the highest-quality comment, to incentivize them to take it seriously. These teams were either all superforecasters or all experts, but later on, new combo teams of superforecasters and experts were created. These teams were asked to make a wiki website that would explain and document their forecasts. Finally, each team was given access to another team’s wiki and asked to update their views. Karger, a research economist at the Chicago Fed who first got interested in forecasting when he participated as a forecaster in some of Tetlock’s experiments, said one of the most important lessons from the research is that little persuasion took place through these processes. “When you’re trying to answer unresolvable questions, there isn’t that much persuasion,” he told me. As you might expect, experts on a particular risk usually put bigger odds on that risk wiping out humanity or killing 10 percent of the population than did experts on other risks. Nuclear experts put 0.55 percent odds on nuclear-induced extinction by 2100; experts on other risks put the odds at 0.19 percent, almost three times smaller. Both AI experts and nonexperts rated AI-caused extinction as the biggest risk, with a 3 percent extinction risk from AI experts and 2 percent from experts on other risks. These averages mask considerable variation between how individual experts and superforecasters saw these risks. On the issue of AI specifically, the authors separated out the most concerned third of their forecasters (both experts and generalist superforecasters) and the least concerned third. The AI-concerned group was very concerned, with the median member putting 11 percent odds on human extinction; the median AI skeptic put the odds at 0.115 percent, not zero but a hundred times lower. “AI skeptics saw claims that AI will lead to catastrophic outcomes as extraordinary and thus as requiring extraordinary evidence,” the authors explain. “AI-concerned forecasters were more likely to place the burden of proof on skeptics to explain why AI is not dangerous. They typically started from a prior that when a more intelligent species or civilization arises, it will overpower competitors.” Karger told me that concerned people specifically mentioned that they were deferring to work by researchers Ajeya Cotra and Toby Ord , work that gave them reason to think AI is especially dangerous. To sort out who to believe, Karger and his co-authors had hoped to find that AI-concerned and AI-skeptic forecasters had different impressions of what will happen in the near future: in 2024, or even 2030. If there were a “skeptical” set of predictions for the near future, and a “concerned” set of predictions, we could see in the next few years who’s right and come to trust the more accurate group more. But that didn’t happen. “Over the next 10 years, there really wasn’t that much disagreement between groups of people who disagreed about those longer run questions,” Karger told me. That makes it a lot harder to sort through who’s right. People were basing their sense of the danger over the next 100 years less on what’s happening in the near-term technologically, and more on almost philosophical beliefs about the level of risk in the world — beliefs that are hard to argue with or about. Notably, the tournament organizers did not ask about extinction risk from climate change, despite involving several experts on the topic. In the paper, they explain that “the impacts would be too slow-moving to meet our ‘catastrophic’ threshold (10 percent of humans dying within a 5-year period) and in pilot interviews climate experts told us they would place an extremely low probability on extinction risk from climate change.” What should we make of these forecasts? So do these results actually mean we face a real chance of human extinction this century? That the odds of 10 percent of humanity dying off in one event are higher than a person’s odds of dying in their first trigger pull during a game of Russian roulette (approximately 17 percent)? I admire Karger, Rosenberg, Tetlock, and their co-authors — Zachary Jacobs, Molly Hickman, Rose Hadshar, Kayla Gamin, Taylor Smith, Bridget Williams, Tegan McCaslin, and Stephen Thomas — for trying to use all the tools we have to answer some important questions. But there are good reasons to be skeptical that these methods can tell us much about the world in 2030 — let alone for the 70 years beyond. For one thing, the superforecasters used in this study are a “set of forecasters with high levels of accuracy on short-run (0-2 year timespan) resolvable questions.” That doesn’t necessarily mean they’re good at soothsaying far into the future. “It is an open question,” the authors concede, “whether forecasters who are accurate on short-run questions will also be accurate on longer-run questions.” What’s more, the group was selected based on tournaments run between 2011 and 2015. Maybe their abilities have degraded? “It is also possible that the epistemic strategies that were successful in 2011-2015, when the superforecasters attained their status, are not as appropriate at other points in time,” the authors concede. It’s perhaps suggestive that superforecasters and experts alike rate AI as the most likely cause of extinction. There’s a long history of computer scientists and others making this argument — but it’s worth noting that AI is the threat considered in the forecasting paper about which we know the least. We have a very good idea of what thermonuclear bombs and natural pathogens and even engineered pathogens might be able to do based on past experience. A rogue AI capable of performing most or all tasks a human can does not exist yet, and skeptics argue it never will. The pattern of estimated risk falling as we learn more about the threat suggests that our estimated risk from AI will fall in the future as we learn more about it. There’s also a risk of groupthink. The report notes that 42 percent of respondents reported having attended an effective altruism (EA) community meetup. That makes some sense — effective altruism has long focused on extinction risks and so it’s natural that experts on extinction would have ties to the EA community — but it’s also worrisome. I have a lot of affection for the EA movement and identify as an EA myself. But EAs are as prone to forming bubbles and reinforcing each other’s beliefs as anybody; I’d love to see a survey with more experts outside this clique included. What’s more, other “forecasts” with significant skin in the game put pretty low odds on the emergence of AI powerful enough to effect extinction. Basil Halperin, Trevor Chow, and J. Zachary Mazlish recently noted that if large institutional investors expected human-level artificial intelligence soon, financial markets would reflect that : interest rates should be very high. A world with human-level AI is probably extremely rich, and if that world is coming soon, that knowledge would reduce humans’ need to save more; they’re going to be rich very soon anyway. Companies and governments would then need to offer to pay more interest so people would save anyway, and interest rates would soar. But interest rates aren’t extraordinarily high right now, which suggests markets do not expect human-level AI anytime soon. And unlike with forecasting tournaments, the gains to betting right in financial markets are in the billions if not trillions of dollars. People have a really large incentive to bet correctly. That being said, you would have made a lot of money predicting an upcoming pandemic in December 2019. The markets didn’t see that coming, and they might not see other big risks coming either. Helpfully, the Forecasting Research Institute has participants make a number of predictions specifically about the year 2024. That means that within eighteen months, we’ll have a much better sense of which of these forecasters are predicting developments in AI, biotech, and other fields relevant to potential apocalypse with much accuracy. In 2030, we’ll know even more. “Something I’m very excited to do is to analyze the correlation and accuracy between the 2024 and the 2030 questions,” Karger said. “If I can tell you that people who are accurate on questions over a two-year time horizon are also accurate on questions over an eight-year time horizon, then I think we have made some progress.” Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 9 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"ChatGPT, Bing, GPT-4: Will AI replace human creativity or originality? - Vox"

"https://www.vox.com/future-perfect/23674696/chatgpt-ai-creativity-originality-homogenization"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence What happens when ChatGPT starts to feed on its own writing? AI chatbots won’t destroy human originality. But they may homogenize our lives and flatten our reality. By Sigal Samuel Apr 10, 2023, 6:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: What happens when ChatGPT starts to feed on its own writing? Reddit Pocket Flipboard Email Paige Vickers/Vox This story is part of a group of stories called Finding the best ways to do good. Part of A few years ago, when Gmail rolled out its autocomplete feature, the big worry was that having a bot finish our sentences would homogenize our emails. We were so damn cute back then. That worry looks almost trivial now that we’ve got “generative AI,” a suite of tools ranging from ChatGPT and GPT-4 to DALL-E 2 and Stable Diffusion. These AI models don’t just finish our sentences; they can write an entire essay or create a whole portfolio of art in seconds. And they increase the old worry of homogenization by orders of magnitude. I’m not just talking about concerns that AI will put writers or artists out of work. Nowadays, if you peer underneath the very real fears of “what if AI robs us humans of our jobs?” you can find a deeper anxiety: What if AI robs us humans of a capacity that’s core to our very humanness — our originality? Here’s how some worry this might happen: Generative models like ChatGPT are trained on gobs and gobs of text from the internet — most of which, up until now, has been created by human beings. But if we fill the internet with more content created by ChatGPT, and then ChatGPT and its successors learn from that content, and so on and so on, will the narratives that frame how we see the world become a closed loop — ChatGPT all the way down — characterized by infinite regression to the mean? Will that homogenize our writing, our thinking, and ultimately our ways of being? Will it spell “ the end of originality ”? Many philosophers have believed that our capacity for original thought is an essential part of human agency and dignity. “It is not by wearing down into uniformity all that is individual in themselves, but by cultivating it and calling it forth…that human beings become a noble and beautiful object of contemplation,” wrote the 19th-century British philosopher John Stuart Mill. He argued for the importance of “giving full freedom to human nature to expand itself in innumerable and conflicting directions.” We know that new technologies can expand or constrict human nature, that they can literally change our brains. Generative AI models seem poised to constrict it, in part because derivativeness is at the core of how they work, relying as they do on past data to predict which words plausibly come next in whatever you’re writing. They use the past to construct the future. This isn’t entirely new. Popular recommendation algorithms like Spotify or Netflix also use that trick: You liked this, so you might also like that. Many critics suspect — and some research supports the idea — that this homogenizes our consumption and production of culture over time. Music starts to sound the same; Hollywood worships reboots and sequels. We all cook the same Epicurious recipes and, more worryingly, read the same articles — which tends to be whatever plays well with the Google algorithm, not what’s been buried at the bottom of the search results. Generative AI could have a similar homogenizing effect, but on a far greater scale. If most self-expression, from text to art to video, is made by AI based on AI’s determination of what appealed before to people on average, we might have a harder time thinking radically different thoughts or conceiving of radically different ways of living. “I get the intuition that, yes, there would be some uniformization,” Raphaël Millière, an expert in philosophy of AI at Columbia University, told me. “I do worry about that.” As a novelist as well as a journalist , I’ve felt some of this worry, too. But I’ve also wondered if the whole underlying premise is wrong. Are we humans ever truly original? Or are we always doing derivative and combinatorial work, mixing and matching ideas we’ve already seen before, just like ChatGPT? The real risk is not exactly about “originality.” It’s more about “diversity.” Nowadays, we worship the idea of originality — or at least we like to think we do. It’s considered a key ingredient of creativity. In fact, the current consensus definition in philosophy and psychology holds that creativity is the ability to generate ideas that are both original and valuable. But originality wasn’t always and everywhere considered so central. When traditional Chinese artists learned their craft, they did it by copying earlier masters, and later they proudly painted in the style of their artistic predecessors. When Shakespeare penned romantic comedies, he was rejiggering much older stories about star-crossed lovers — and he seemed to suspect as much , writing, “there be nothing new, but that which is hath been before” (which was itself a rejiggered quote from the Bible). It was only in the 18th century that originality became such a preeminent value. The Romantics were very big on the notion that the individual self can spontaneously create new ideas and generate its own authoritative meaning. (According to some scholars , people needed to believe that in order to cope with the loss of traditional structures of meaning — a loss ushered in by the Enlightenment.) Western culture has inherited this Romantic notion of originality. Contemporary neuroscience tells a different story. The latest research suggests that pure originality is, alas, not a thing. Instead, when you’re writing a poem or making a painting, you’re drawing on an interplay between your brain’s memory and control systems: memory, because you have to pull up words, people, or events you’ve encountered before; and control, because you have to flexibly recombine them in new and meaningful ways. Coming up with a unicorn, say, involves remembering the idea of a horse and combining it with the idea of a horn. If our minds were always already working within a finite loop, the concept of “originality” may be a bit of a red herring, confusing our discussion of generative AI. Instead of worrying about the loss of an originality that perhaps we never possessed, we should talk about the risk of this technology eroding “diversity” or “flexibility” of thought — and replacing that with homogenization or, as the New Yorker’s Kyle Chayka puts it, “ Average Garbage Forever. ” And that risk is real. In fact, there are multiple senses in which generative AI could homogenize human expression, thought, and life. The many ways generative AI could homogenize our lives Stylistically, large language models (LLMs) like ChatGPT might push our writing to become more sanitized. As you’ve probably noticed, they have a tendency to talk in a bland, conformist, Wikipedia-esque way (unless you prompt them otherwise — more on that in a bit). “If you interact with these models on a daily basis,” Millière told me, “you might end up with your writing impacted by the generic, vanilla outputs of these models.” ChatGPT also privileges a “proper” English that erases other vernaculars or languages, and the ways of seeing the world that they encode. By default, it’s not writing in African American English (long stigmatized as “incorrect” or “unprofessional”), and it’s certainly not writing by default in, say, Māori language. It trains on the internet, where most content is still in English , in part because there’s still a striking global disparity in who has internet connectivity. “I worry about Anglocentrism, as most generative models with high visibility perform best in English,” said Irene Solaiman, an AI expert and policy director at Hugging Face who previously worked at OpenAI. Culturally, ChatGPT might reinforce a Western perspective. Research has shown that richer countries enjoy richer representations in LLMs. Content from or about poorer countries occurs less frequently in the training data, so the models don’t make great predictions about them, and sometimes flat-out erase them. Rishi Bommasani, an AI researcher at Stanford, offered a simple example. “If you use the models to suggest breakfast foods,” he told me, “they will overwhelmingly suggest Western breakfasts.” To test that out, I asked the GPT-4-powered Bing to write me a story about “a kid who cooks breakfast.” Bing wrote me a perfectly cogent story … about a boy (male) named Lucas ( probably white) , whose mom is a chef at a fancy restaurant (probably expensive). Oh, and yes, the kid whips up pancakes, eggs, bacon, and toast (very much Western). This is worrisome when you think about the cultural effects at scale — and AI is all about scale. Solaiman told me that government representatives from developing countries have already come to her concerned about a new algorithmically powered wave of Westernization, one that could dwarf the homogenizing effects that globalization has already imposed. It’s not like the language we see deterministically limits the thoughts we’re able to think or the people we’re able to be. When the philosopher Ludwig Wittgenstein said “the limits of my language mean the limits of my world,” that was a bit of an overstatement. But language does shape how we think and, by extension, the lives we dare to imagine for ourselves; it’s the reason there’s such a big push to portray diverse characters in STEM fields in children’s books. As adults, our imaginations are also conditioned by what we read, watch, and consume. Bommasani and his colleagues also worry about algorithmic monoculture leading to “outcome homogenization.” AI’s advantage and disadvantage is in its sheer scale. If it makes a mistake, it’s not like one hiring manager or one bank officer making a mistake; it goes all the way down the line. If many decision-makers incorporate the same popular AI models into their workflow, the biases of the models will trickle into all the downstream tasks. That could lead to a situation where certain people or groups experience negative outcomes from all decision-makers. Their applications for a job or a loan are rejected not just by one company or bank, but by every company or bank they try! Not exactly a recipe for diversity, equity, and inclusion. But the risks of homogenization don’t end there. There are also potential epistemic effects — how generative AI may push us toward certain modes of thinking. “In terms of the way in which you formulate your reasoning, and perhaps eventually the way in which you think, that’s definitely a concern,” Millière said. Maybe we get used to providing only a starting prompt for a text, which the AI then completes. Or maybe we grow accustomed to providing the outline or skeleton and expecting the AI to put meat on the bones. Sure, we can then make tweaks — but are we cheating ourselves out of something important if we jump straight to that editing stage? The writer Rob Horning recently expressed this anxiety: I am imagining a scenario in the near future when I will be working on writing something in some productivity suite or other, and as I type in the main document, my words will also appear in a smaller window to the side, wherein a large language model completes several more paragraphs of whatever I am trying to write for me, well before I have the chance to conceive of it. In every moment in which I pause to gather my thoughts and think about what I am trying to say, the AI assistant will be thinking for me, showing me what it calculates to be what I should be saying… Maybe I will use its output as a gauge of exactly what I must not say, in which case it is still dictating what I say to a degree. Or maybe I’ll just import its language into my main document and tinker with it slightly, taking some kind of ownership over it, adapting my thinking to accommodate its ideas so that I can pretend to myself I would have eventually thought them too. I am wondering what I will have to pay to get that window, or worse, what I’ll have to pay to make it disappear. There’s a palpable fear here about relinquishing the role of creator for the role of curator, about letting originality become contaminated by some outside influence. Again, since pure originality is probably a fantasy, arguably we’re all already curators, and we’re always under the influence of others (sorry, Romantics!). Still, skipping over the idea-generation phase by immediately turning to LLMs for help seems like a bad idea for two interrelated reasons. First, we may become overreliant on the tech, so much so that some of our imaginative or cognitive “muscles” gradually become weaker for lack of use. If you think that’s implausible, ask yourself how many of your friends’ phone numbers you remember, or how much mental math you can do, now that you walk around with a smartphone on you at all times. Such concerns aren’t new. The ancient Greek philosopher Socrates, who operated in a largely oral culture, worried that the invention of writing “will produce forgetfulness in the minds of those who learn to use it, because they will not practice their memory.” Contemporary research actually bears out the philosopher’s fears, showing that “when people expect to have future access to information, they have lower rates of recall of the information itself.” Which doesn’t mean we should all give up writing, without which civilization as we know it would essentially be impossible! But it does mean we should think about which skills each new technology may reshape or diminish — especially if we’re not mindful about how we use it — and ask ourselves whether we’re fine with that. OpenAI itself highlights overreliance as a potential problem with GPT-4. The model’s system card notes , “As users become more comfortable with the system, dependency on the model may hinder the development of new skills or even lead to the loss of important skills.” Second, asking LLMs for help at the earliest stages of our creative process will yield a certain answer that inevitably primes us to think in a certain direction. There will be thought paths we’re less likely to go down because ChatGPT has already got certain (majority) voices whispering in our ears. Other (minority) voices will get left out — potentially leaving our writing, and our thinking, impoverished as a result. Usually, we’re in a position to be able to dial up or down the degree to which other voices are whispering in our ears. When I was writing my debut novel , and suffering from what the literary critic Harold Bloom called “the anxiety of influence,” I actually decided to bar myself from reading fiction for a while because I realized the sentences I was writing were starting to sound like Jonathan Franzen, whose novels I’d just been reading. I didn’t want another writer’s voice to overly influence mine, so I put the books down. But if we become overreliant on a technology, we become, definitionally, less likely to put it down. Sure, we still have some agency. But the ease of turning to ChatGPT, coupled with the magical-feeling instant gratification it provides (just put in your incantation and the oracle replies!), can make it harder to exercise that agency. Related The case for slowing down AI What can AI companies — and the rest of us — do to counter homogenization? So far, we’ve been unpacking worries about what happens when we have not just a machine producing the content that informs our imagination, but machines trained on machines, forever and ever. Yet there’s an obvious question here. If you’re a company building an AI model, can you just put AI-generated data off limits for training, and therefore stop the model from eating its own tail? “Maybe you can do better than chance — you can do something — but I don’t think you can do it well at scale,” Bommasani said. “It would be pretty hard to guarantee that your training data for the next model includes no machine-generated data from the previous model.” Millière agreed. “It’s probably hard already, and in the future it’ll be even harder to quantify how much contamination there is in your data.” Even though researchers are working on detection models to spot AI-generated outputs and ways to watermark them, and even though there are stronger and weaker methods for detecting contamination (OpenAI’s method could use some work), this remains a very tricky problem. That’s because the whole point of LLMs is to crank out text indistinguishable from what humans would produce. Beyond trying to prevent contamination, something companies can do is pay careful attention to how they’re designing the interface for these models. When I first got early access to Bing in mid-February, I gave it simple prompts, like asking it to write me a song. It was just an “it” — one single mode to choose from. But by the last week of that month, Bing featured three “conversation styles,” and I had to choose between them: precise, balanced, or creative. When I chose the creative style, it answered in more off-the-wall, less predictable ways. When you’re trying to write something factual, you don’t want to dial up unpredictable deviations, as those who’ve been using generative AI for research are learning. But in creative work, it could help to lean into the unpredictable — or, as AI researchers might put it, to “increase hallucinations” or “increase the temperature.” That makes the model less deterministic, so instead of choosing the next word with the highest probability of occurring, it can choose words with much lower probabilities. It’s the difference between typing in “The sky is” and getting back “The sky is blue” versus getting back “The sky is clear, the water smooth, and it’s an unimaginably long way to go before the dolphins decide to give up their vertical quest.” Getting a model to diverge more from the data it learned during training can be somewhat helpful (though probably not sufficient) for addressing the homogenization concern. But how much it’ll help depends in part on how much the interface nudges people to get creative themselves rather than relying on the default, and on how individuals choose to use the model. To be clear, the onus should be mostly on the companies, not on you, the user. That said, Millière thinks the models could enrich your creative process if you go the extra mile to prompt it in certain ways. He imagined an author who wants to attempt the challenging task of writing across difference — for example, an author who has never been to rural Texas trying to create characters from rural Texas, complete with naturalistic dialogue. “I could see this augmenting your creativity, because it’ll lead you to abstract away from your own personal perspective and biases to explore a different linguistic realm that you don’t necessarily have access to yourself,” Millière told me. I’ve been experimenting with LLMs since 2019, when I used GPT-2 to help me with my next novel. It’s about two little girls who discover an ancient hotel that contains a black hole, complete with wormholes. Prompted with the idea of wormholes, GPT-2 gave me a bunch of questions seeking to pin down exactly how the wormholes work. Those questions were really helpful for world-building! But I turned to the LLM only once I had a complete draft of the novel and felt stuck on how to improve it. At that point, GPT-2 worked great as a creative prosthesis to help me out of my rut. I would not turn to it in the early stage, when I’m staring down a blank page (though that’s precisely how it’s being marketed ). I don’t want it to weaken my writerly muscles through overreliance, or take my imagination down specific paths before I’ve had a chance to survey as many paths as I want. What is AI for? What is humanity for? Can we tweak AI models with human feedback to get them to be more surprising or variable in their outputs? Yes. Is that the same as human beings struggling against a convention of thought to push a new idea or vision into the world because it gives voice to something unspoken that’s happening in us ? No. “The only way that AI will be compatible with human flourishing is if it empowers that,” said Shannon Vallor, a philosopher of technology at the University of Edinburgh, where she directs the Centre for Technomoral Futures. “If it makes it easier and more rewarding for us to use our recorded past as a place to push off from, rather than to revolve around. But that’s not what today’s commercial AI systems are built for.” OpenAI says its mission is to ensure that AI “benefits all of humanity.” But who gets to define what that means, and whether we’re all willing to diminish a core human capacity in the quest to optimize for a definition decided on by Silicon Valley? As the philosopher Atoosa Kasirzadeh has written, “the promise that AI technologies will benefit all of humanity is empty so long as we lack a nuanced understanding of what humanity is supposed to be.” As generative AI models proliferate, we all face a question: Will we put in the work to counteract their homogenizing effects? Maybe we’ll answer with a collective meh , proving that we don’t actually care about originality or diversity of thought as much as we thought we did. But then we have to face another question: If we don’t really value the capacity for original thought and its role in human agency, then what do we value? What do we think it is to lead a meaningful life? What is a human life for? And these are not questions ChatGPT can answer. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 3 What is generative AI, and why is it suddenly everywhere? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"What the AI-generated image of Pope Francis means for the imagination - Vox"

"https://www.vox.com/future-perfect/23661673/pope-puffer-coat-generative-ai-midjourney-imagination"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence How fake AI images can expand your mind What the pope in a puffer coat means for the human imagination. By Oshan Jarow @OshanJarow Mar 30, 2023, 10:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: How fake AI images can expand your mind Reddit Pocket Flipboard Email Photo illustration by Dion Lee/Vox; pope image generated by Reddit user “u/trippy_art_special” on Midjourney; Background generated by Midjourney This story is part of a group of stories called Finding the best ways to do good. Part of A recent viral image of Pope Francis wearing an unusually hip white puffer jacket was both a fake created by generative AI and an omen that marked the accelerating collapse of a clearly distinguishable boundary between imagination and reality. Photorealistic images of fictions — like Donald Trump getting arrested while stumbling in a sea of cops — can now be generated on demand by AI programs like Midjourney, DALL-E 2, and Stable Diffusion. This sets off alarm bells around how misinformation may thrive. But along with risks, AI-generated imagery also offers a great leap forward for the human imagination. “Seeing is believing” goes both ways. Image-generating AI will allow us to see realistic depictions of what does not yet exist, expanding the kinds of futures we can imagine as visual realities. The human imagination doesn’t build ideas from scratch. It’s combinatorial : The mind cobbles together new ideas from accumulated bits and pieces it has been exposed to. AI-generated images will greatly increase the raw material of plausible worlds the mind can imagine inhabiting and, through them, the kinds of futures we perceive as possible. For example, it’s one thing to read a description or see an illustration of a futuristic city with inspiring architecture, public transportation woven through greenery, and spaces designed for human interaction, not cars. It’s another to see a spread of photorealistic images of what that could actually look like. By creating realistic representations of imagined realities, text-to-image-generating AI can make it easier for the mind to include new possibilities in how it imagines the world, reducing the barriers to believing that they could become a lived reality. The pope’s puffer jacket was a sign of hyperreality Last Friday, Reddit user “u/trippy_art_special” posted the image of the pope to the Midjourney subreddit , the generative AI platform used to produce it. The post contained four variations (a hallmark of Midjourney) of the pope ensconced in an on-trend long, puffy, white coat. One even had him in dark sunglasses, which looked especially smooth, even mysterious, in contrast to the radiant white of the coat and the deep chain. The image was widely mistaken as real, and the pope’s outfit was big news over the weekend. Once people caught on that the image was fake, it became even bigger news. “No way am I surviving the future of technology,” the American model Chrissy Teigen tweeted. Debates over why this particular image went viral or why so many people believed it to be real will soon be moot. For something that appears so convincing, why wouldn’t we believe it? Neither was this the first media brush between Pope Francis and high fashion. In 2008, the Vatican daily newspaper quashed rumors of designer loafers , stating, “The pope, therefore, does not wear Prada, but Christ.” For those who scrutinized the image, you could still find clues of falsehood. A few inconspicuous smudges and blurs. But Midjourney’s pace of improvement suggests correcting these remaining signs will happen swiftly. What then? At The Verge , senior reporter James Vincent likened AI-generated imagery to the dawn of “hyperreality,” a concept developed by the French philosopher Jean Baudrillard. “Sooner or later,” Vincent wrote, AI fakes are going to become hyperreal, “masking the distinction entirely between the imaginary and the real.” It’s easy to imagine the nightmare that could follow. Hyperreality is usually invoked as a concern over simulations displacing reality , posing real and looming threats. AI fakes will offer fertile grounds for a new and potentially harrowing era of misinformation, rabbit holes unmoored from reality, and all manners of harassment. Adapting media literacy habits and protective regulations will be crucial. But there is an upside: While AI fakes threaten to displace what the mind perceives as reality, they can also expand it. AI fakes can extend your mind In 1998, two leading philosophers — Andy Clark and David Chalmers — published a paper on their idea of “the extended mind.” They argued that cognitive processes are not confined within the boundaries of the skull, but extend out through the tools we use to interact with the world. These aids — a notebook, for example — are tangled up in how we think and are part of our extended minds. In this view, tools can become something like cognitive limbs: not separate from our capacities, but part of them. You can flip this around: Building new tools is a way of building new mental capabilities. Until last weekend, most people could have imagined some image of what the pope might look like in a fashion-week puffer jacket ( unless you have aphantasia , in which mental imagery is not part of your internal experience). But those mental images can be slippery. The more artistic among us could have drawn a few ideas, prompting a richer image. But soon, anyone will be able to imagine anything and render it into photorealistic quality, seeing it as though it were real. Making the visual concrete gives the mind something solid to grab hold of. That is a new trick for the extended mind. “You should understand these tools as aids to your imagination,” says Tony Chemero, a professor of philosophy and psychology at the University of Cincinnati and member of the Center for Cognition, Action, and Perception. But “imagining isn’t something that just happens in your brain,” he added. “It’s interacting skillfully with the world around you. The imagination is in the activity, like an architect doing sketches.” There is disagreement among cognitive scientists on which kinds of tools merge with our extended minds, and which retain separate identities as tools we think with rather than through. Chemero distinguished between tools of the extended mind, like spoons or bicycles, and computers that run generative AI software like Midjourney. When riding a bicycle and suddenly wobbling through an inconveniently placed crater in the concrete, people tend to say, “I hit a pothole,” instead of, “The bicycle wheel hit the pothole.” The tool is conceived as a part of you. You’d be less likely to say, “I fell on the floor,” after dropping your laptop. Still, he told me that any tool that changes how we interact with the world also changes how we understand ourselves. “Especially what we understand ourselves as being capable of,” he added. Clark and Chalmers end their paper with an unusually fun line for academic philosophy: “once the hegemony of skin and skull is usurped, we may be able to see ourselves more truly as creatures of the world.” Thinking with AI image generators , we may be able to see ourselves — in picture-perfect quality — as creatures of many different potential worlds, flush with imaginative possibilities that blend fact and fiction. “It might be that you can use this to see different possible futures,” Chemero told me, “to build them as a kind of image that a young person can imagine themselves as moving toward.” G20 summits where all the world leaders are women; factories with warm lighting, jovial atmospheres, and flyers on how to form unions. These are now fictional realities we can see, rather than dimly imagine through flickers in the mind. Of course, reality is real, as the world was reminded earlier this week when 86-year-old Pope Francis was taken into medical care for what the Vatican is calling a respiratory infection, though by Thursday he was reportedly improving and tweeting from the hospital. But if seeing is believing, these tools will make it easier for us to believe that an incredible diversity of worlds is possible, and to hold on to their solid images in our minds so that we can formulate goals around them. Turning imagination into reality starts with clear pictures. Now that we can generate them, we can get to work. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Microsoft and Google race shows the risks of AI competition - Vox"

"https://www.vox.com/future-perfect/23591534/chatgpt-artificial-intelligence-google-baidu-microsoft-openai"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence Are we racing toward AI catastrophe? As tech giants like Microsoft and Google compete to capture the AI market, safety could be an afterthought. By Kelsey Piper Feb 9, 2023, 5:30am EST Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Are we racing toward AI catastrophe? Reddit Pocket Flipboard Email Satya Nadella, CEO of Microsoft, speaks during an event at the company’s headquarters in Redmond, Washington, on Tuesday, February 7, 2023. Chona Kasinger/Bloomberg via Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of “The race starts today, and we’re going to move and move fast,” Satya Nadella, CEO of Microsoft, said at the company’s ChatGPT launch event on Tuesday. That word — “race” — has been thrown around a lot lately in the AI world. Google and Baidu are racing to compete with OpenAI and Microsoft’s ChatGPT as a key part of search, while Meta is racing not to be left in the dust. Related AI experts are increasingly afraid of what they’re creating Tech is often a winner-takes-all sector — think Google controlling nearly 93 percent of the search market — but AI is poised to turbocharge those dynamics. Competitors like Microsoft and Baidu have a once-in-a-lifetime shot at displacing Google and becoming the internet search giant with AI-enabled, friendlier interface. Some have gone even farther, arguing there’s a “ generative AI arms race between the US and China ,” in which Microsoft-backed OpenAI’s insanely popular ChatGPT should be interpreted as the first salvo. Why some people aren’t so thrilled that the AI race is on It’s a word that makes me wince, because AI strategy and policy people talk about it a lot too. But in their context, an “AI arms race” — whether between tech companies or between geopolitical rivals — could have negative consequences that go far beyond market share. “When it comes to very powerful technologies — and obviously AI is going to be one of the most powerful ever — we need to be careful,” DeepMind founder and leader Demis Hassabis recently told Time. “Not everybody is thinking about those things. It’s like experimentalists, many of whom don’t realize they’re holding dangerous material.” “It’s important *NOT* to ‘move fast and break things’ for tech as important as AI,” he wrote on Twitter in September. The usual Silicon Valley spirit — try things, see how they fail, try again — has brought us some incredibly cool consumer technology and fun websites. But it’s not how you’d build a skyscraper or a manned rocket, and powerful AI systems are much more in the latter category, where you want robust engineering for reliability. vox-mark Sign up for the newsletter Future Perfect Each week, we explore unique solutions to some of the world's biggest problems. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. OpenAI’s ChatGPT was the product release that set off Google, Baidu, and Microsoft’s jostling for the lead in AI development, but that startup’s leadership, too, has expressed some dismay at where it’s taking us. “The bad case — and I think this is important to say — is like lights out for all of us ... I think it’s impossible to overstate the importance of AI safety and alignment work. I would like to see much, much more happening,” OpenAI’s CEO Sam Altman said in a recent interview. (He also called Google’s response to ChatGPT, ramping up their own AI release and “recalibrating” their concern for safety, a “disappointing” development: “openai will continually decrease the level of risk we are comfortable taking with new models as they get more powerful, not the other way around.”) Why we should try to not have a race for powerful AI Do I care if Microsoft steals some market share in search from Google? Not at all. Bing away. But the recent flurry of declarations that big tech is all in on the AI race has still made me nervous. One easy way that we could, as some analysts put it, “ stumble into AI catastrophe ” is if researchers developing powerful systems ignore warning signs and carelessly train more and more powerful systems using the approaches that worked fine for weak, early-stage systems — but which fall apart on an AI system that’s more sophisticated, persuasive, and potentially able to deceive its users. Here’s a thought experiment: Imagine that you can always tell if your 3-year-old is lying to you, so your plan to dissuade him from misbehavior is just to ask if he’s misbehaving. Works great, but if you stick to the same plan on your more sophisticated teenager, it won’t work so well. The rise of artificial intelligence, explained How does AI actually work? How is AI changing our society? Is AI coming for your job? Should we be worried about AI? Who will regulate AI? In general, most researchers aren’t reckless and don’t want to risk the world. If their lab is building AI and they start noticing terrifying signs of misalignment, deceptive behavior, advanced planning, etc., they’ll be alarmed, and they’ll stop! Even researchers who are skeptical today that alignment is a serious concern will, if they see it in their lab, want to address it before they put bigger and bigger systems out. Why competition can be great — and dangerous But that’s what might happen in a lab. In an economic race with enormous winner-takes-all stakes, a company is primarily thinking about whether to deploy their system before a competitor. Slowing down for safety checks risks that someone else will get there first. In geopolitical AI arms race scenarios, the fear is that China will get to AI before the US and have an incredibly powerful weapon — and that, in anticipation of that, the US may push its own unready systems into widespread deployment. Even if alignment is a very solvable problem, trying to do complex technical work on incredibly powerful systems while everyone is in a rush to beat a competitor is a recipe for failure. Some actors working on artificial general intelligence, or AGI, have planned significantly to avoid this dangerous trap: OpenAI, for instance, has terms in its charter specifically aimed at preventing an AI race once systems are powerful enough: “We are concerned about late-stage AGI development becoming a competitive race without time for adequate safety precautions. Therefore, if a value-aligned, safety-conscious project comes close to building AGI before we do, we commit to stop competing with and start assisting this project. We will work out specifics in case-by-case agreements, but a typical triggering condition might be “a better-than-even chance of success in the next two years.” I am generally optimistic about human nature. No one actively wants to deploy a system that will kill us all, so if we can get good enough visibility into the problem of alignment, then it’ll be clear to engineers why they need a solution. But eager declarations that the race is on make me nervous. Another great part of human nature is that we are often incredibly competitive — and while that competition can lead to great advancements, it can also lead to great destruction. It’s the Cold War that drove the space race, but it was also WWII that drove the creation of the atomic bomb. If winner-takes-all competition is the attitude we bring to one of the most powerful technologies in human history, I don’t think humanity is going to win out. A version of this story was initially published in the Future Perfect newsletter. Sign up here to subscribe! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 9 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"How to understand AI: it’s a tragedy of the commons, not an arms race - Vox"

"https://www.vox.com/future-perfect/2023/7/7/23787011/ai-arms-race-tragedy-commons-risk-safety"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence AI is a “tragedy of the commons.” We’ve got solutions for that. “Arms race” is the wrong mental model for AI. Here’s a better one. By Sigal Samuel Jul 7, 2023, 11:20am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: AI is a “tragedy of the commons.” We’ve got solutions for that. Reddit Pocket Flipboard Email OpenAI CEO Sam Altman speaks at an event in Tokyo in June 2023. Tomohiro Ohsumi/Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of You’ve probably heard AI progress described as a classic “arms race.” The basic logic is that if you don’t race forward on making advanced AI, someone else will — probably someone more reckless and less safety-conscious. So, better that you should build a superintelligent machine than let the other guy cross the finish line first! (In American discussions, the other guy is usually China. ) But as I’ve written before , this isn’t an accurate portrayal of the AI situation. There’s no one “finish line,” because AI is not just one thing with one purpose, like the atomic bomb; it’s a more general-purpose technology, like electricity. Plus, if your lab takes the time to iron out some AI safety issues, other labs may take those improvements on board, which would benefit everyone. And as AI Impacts lead researcher Katja Grace noted in Time , “In the classic arms race, a party could always theoretically get ahead and win. But with AI, the winner may be advanced AI itself [if it’s unaligned with our goals and harms us]. This can make rushing the losing move.” I think it’s more accurate to view the AI situation as a “tragedy of the commons.” That’s what ecologists and economists call a situation where lots of actors have access to a finite valuable resource and overuse it so much that they destroy it for everyone. A perfect example of a commons: the capacity of Earth’s atmosphere to absorb greenhouse gas emissions without tipping into climate disaster. Any individual company can argue that it’s pointless for them to use less of that capacity — someone else will just use it instead — and yet every actor acting in their rational self-interest ruins the whole planet. AI is like that. The commons here is society’s capacity to absorb the impacts of AI without tipping into disaster. Any one company can argue that it would be pointless to limit how much or how fast they deploy increasingly advanced AI — if OpenAI doesn’t do it, it’ll just be Google or Baidu, the argument goes — but if every company acts like that, the societal result could be tragedy. “Tragedy” sounds bad, but framing AI as a tragedy of the commons should actually make you feel optimistic, because researchers have already found solutions to this type of problem. In fact, political scientist Elinor Ostrom won a Nobel Prize in Economics in 2009 for doing exactly that. So let’s dig into her work and see how it can help us think about AI in a more solutions-focused way. Elinor Ostrom’s solution to the tragedy of the commons In a 1968 essay in Science , the ecologist Garrett Hardin popularized the idea of the “tragedy of the commons.” He argued that humans compete so hard for resources that they ultimately destroy them; the only ways to avoid that are total government control or total privatization. “Ruin is the destination toward which all men rush,” he wrote, “each pursuing his own best interest.” Ostrom didn’t buy it. Studying communities from Switzerland to the Philippines, she found example after example of people coming together to successfully manage a shared resource, like a pasture. Ostrom discovered that communities can and do avert the tragedy of the commons, especially when they embrace eight core design principles: 1) Clearly define the community managing the resource. 2) Ensure that the rules reasonably balance between using the resource and maintaining it. 3) Involve everyone who’s affected by the rules in the process of writing the rules. 4) Establish mechanisms to monitor resource use and behavior. 5) Create an escalating series of sanctions for rule-breakers. 6) Establish a procedure for resolving any conflicts that arise. 7) Make sure the authorities recognize the community’s right to organize and set rules. 8) Encourage the formation of multiple governance structures at different scales to allow for different levels of decision-making. Applying Ostrom’s design principles to AI So how can we use these principles to figure out what AI governance should look like? Actually, people are already pushing for some of these principles in relation to AI — they just may not realize that they slot into Ostrom’s framework. Many have argued that AI governance should start with tracking the chips used to train frontier AI models. Writing in Asterisk magazine, Avital Balwit outlined a potential governance regime: “The basic elements involve tracking the location of advanced AI chips, and then requiring anyone using large numbers of them to prove that the models they train meet certain standards for safety and security.” Chips control corresponds to Ostrom’s principle #4: establishing mechanisms to monitor resource use and behavior. Related The case for slowing down AI Others are noting that AI companies need to face legal liability if they release a system into the world that creates harm. As tech critics Tristan Harris and Aza Raskin have argued , liability is one of the few threats these companies actually pay attention to. This is Ostrom’s principle #5: escalating sanctions for rule-breakers. And despite the chorus of tech execs claiming they need to rush ahead with AI lest they lose to China, you’ll also find nuanced thinkers arguing that we need international coordination, much like what we ultimately achieved with nuclear nonproliferation. That’s Ostrom’s principle #8. If people are already applying some of Ostrom’s thinking, perhaps without realizing it, why is it important to explicitly note the connection to Ostrom? Two reasons. One is that we’re not applying all her principles yet. The other is this: Stories matter. Myths matter. AI companies love the narrative of AI as an arms race — it justifies their rush to market. But it leaves us all in a pessimistic stance. There’s power in telling ourselves a different story: that AI is a potential tragedy of the commons, but that tragedy is only potential, and we have the power to avert it. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 8 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"A “Manhattan Project” for artificial intelligence risk is a bad idea - Vox"

"https://www.vox.com/future-perfect/2023/7/3/23779794/artificial-intelligence-regulation-ai-risk-congress-sam-altman-chatgpt-openai"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence Panic about overhyped AI risk could lead to the wrong kind of regulation There’s something missing in the heart of the conversation about AI. By Divyansh Kaushik and Matt Korda Jul 3, 2023, 7:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Panic about overhyped AI risk could lead to the wrong kind of regulation Reddit Pocket Flipboard Email Sam Altman, chief executive officer and co-founder of OpenAI, during a Senate Judiciary Subcommittee hearing in Washington, DC, on May 16, 2023. Eric Lee/Bloomberg via Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of Recently, a number of viral stories — including one by Vox — described an Air Force simulation in which an autonomous drone identified its operator as a barrier to executing its mission and then sought to eliminate the operator. This story featured everything that prominent individuals have been sounding the alarm over: misaligned objectives, humans outside of the loop, and an eventual killer robot. The only problem? The “simulation” never happened — the Air Force official who related the story later said that it was only a “thought exercise,” not an actual simulation. The proliferation of sensationalist narratives surrounding artificial intelligence — fueled by interest, ignorance, and opportunism — threatens to derail essential discussions on AI governance and responsible implementation. The demand for AI stories has created a perfect storm for misinformation, as self-styled experts peddle exaggerations and fabrications that perpetuate sloppy thinking and flawed metaphors. Tabloid-style reporting on AI only serves to fan the flames of hysteria further. These types of common exaggerations ultimately detract from effective policymaking aimed at addressing both immediate risks and potential catastrophic threats posed by certain AI technologies. For instance, one of us was able to trick ChatGPT into giving precise instructions on how to build explosives made out of fertilizer and diesel fuel, as well as how to adapt that combination into a dirty bomb using radiological materials. If machine learning were merely an academic curiosity, we could shrug this off. But as its potential applications extend into government, education, medicine, and national defense, it’s vital that we all push back against hype-driven narratives and put our weight behind sober scrutiny. To responsibly harness the power of AI, it’s essential that we strive for nuanced regulations and resist simplistic solutions that might strangle the very potential we’re striving to unleash. vox-mark Sign up for the newsletter Future Perfect Each week, we explore unique solutions to some of the world's biggest problems. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. But what we are seeing too often is a calorie-free media panic where prominent individuals — including scientists and experts we deeply admire — keep showing up in our push alerts because they vaguely liken AI to nuclear weapons or the future risk from misaligned AI to pandemics. Even if their concerns are accurate in the medium to long term, getting addicted to the news cycle in the service of prudent risk management gets counterproductive very quickly. AI and nuclear weapons are not the same From ChatGPT to the proliferation of increasingly realistic AI-generated images, there’s little doubt that machine learning is progressing rapidly. Yet there’s often a striking lack of understanding about what exactly is happening. This curious blend of keen interest and vague comprehension has fueled a torrent of chattering-class clickbait, teeming with muddled analogies. Take, for instance, the pervasive comparison likening AI to nuclear weapons — a trope that continues to sweep through media outlets and congressional chambers alike. While AI and nuclear weapons are both capable of ushering in consequential change, they remain fundamentally distinct. Nuclear weapons are a specific class of technology developed for destruction on a massive scale, and — despite some ill-fated and short-lived Cold War attempts to use nuclear weapons for peaceful construction — they have no utility other than causing (or threatening to cause) destruction. Moreover, any potential use of nuclear weapons lies entirely in the hands of nation-states. In contrast, AI covers a vast field ranging from social media algorithms to national security to advanced medical diagnostics. It can be employed by both governments and private citizens with relative ease. As a result, regulatory approaches for these two technologies take very different forms. Broadly speaking, the frameworks for nuclear risk reduction come in two distinct, and often competing, flavors: pursuing complete elimination and pursuing incremental regulation. The former is best exemplified by the Treaty on the Prohibition of Nuclear Weapons , which entered into force in 2021 and effectively banned nuclear weapons under international law. Although it is unlikely to yield tangible steps towards disarmament in the short term — largely because no current nuclear powers, including the US, Russia , or China , have signed on — the treaty constitutes a defensible use case for a wholesale ban on a specific existential technology. In contrast, the latter approach to nuclear regulation is exemplified by New START — the last remaining bilateral US-Russia nuclear arms control agreement — which limited the number of warheads both sides could deploy, but in doing so enshrined and validated both countries’ continued possession of nuclear weapons. The unfortunate conflation of AI and nuclear weapons has prompted some advocates to suggest that both of these approaches could potentially be adapted to the regulation of AI; however, it is only the latter approach that translates cleanly. Given the ubiquity of artificial intelligence and its wide range of practitioners, its regulation must focus on the application of such a technology, rather than a wholesale ban. Attempting to regulate artificial intelligence indiscriminately would be akin to regulating the concept of nuclear fission itself. And, as with most tools, AI is initially governed by the ethical frameworks and objectives imposed by its developers and users (though pursuing misaligned objectives could lead to divergence from human-intended goals): The technology is neither inherently good nor evil; in contrast, philosophers, ethicists, and even the pope have argued that the same could not necessarily be said about nuclear weapons, because their mere possession is an inherent threat to kill millions of people. In contrast to a wholesale ban, the most tangible risk reduction efforts surrounding nuclear weapons over the past several decades have come through hard-won negotiations and international agreements surrounding nuclear testing, proliferation, and export controls. To that end, if we draw lessons from the decades of nuclear arms control, it should be that transparency, nuance, and active dialogue matter most to meaningful risk reduction. Others call attention to potential extinction-level risks, asking that these be taken just as seriously as those from nuclear weapons or pandemics. OpenAI CEO Sam Altman, for example, along with his fellow CEOs from Google DeepMind and Anthropic and several prominent AI researchers, signed a recent open letter warning that “mitigating the risk of extinction from AI should be a global priority alongside other societal-scale risks such as pandemics and nuclear war.” While it is essential not to dismiss those genuinely worried about catastrophic risks altogether, leveraging such towering claims in every conversation distracts from the grounded conversations necessary to develop well-informed policies around AI governance. There are genuine catastrophic risks surrounding AI that we might encounter: rogue actors using large AI models to dismantle cybersecurity around critical infrastructure; political parties using disinformation at scale to destabilize fragile democratic governments; domestic terrorists using these models to learn how to build homemade weapons; and dictatorial regimes using them to surveil their populations or build dystopian social credit systems, among others. But by labeling AI as an “extinction-level” threat, the conversation around such risks gets mired in unprecedented alarmism rather than focusing on addressing these more proximate — and much more likely — challenges. Do we really need — or want — a “Manhattan Project” for AI safety? These existential concerns have provoked calls for a Manhattan Project-like undertaking to address the “alignment problem,” the fear that powerful AI models might not act in a way we ask of them; or to address mechanistic interpretability, the ability to understand the function of each neuron in a neural network. “A Manhattan Project for X” is one of those clichés of American politics that seldom merit the hype. And AI is no exception. Many people have called for large-scale governmental research projects targeting potential existential risks resulting from an alignment problem. Such projects demand vast investments without offering concrete solutions and risk diverting resources from more pressing matters. Moreover, the “Manhattan Project”-like approach is a wholly inappropriate analogy for what we actually need to make AI safer. As historian Alex Wellerstein has written , the Manhattan Project was undertaken with virtually zero external oversight in near-complete secrecy, such that only a handful of people had a clear view of the goal, while thousands of the individuals actually doing the hands-on work didn’t even know what it was they were building. While the Manhattan Project did ultimately accomplish its goal, hindsight obscures the fact that the project itself was a tremendous financial and technological gamble with far-reaching consequences that could not have been foreseen at its inception. Furthermore, while the Manhattan Project’s ultimate goal was relatively singular — design and build the atomic bomb — AI safety encompasses numerous ambiguities ranging from the meaning of concepts like “mechanistic interpretability” to “value alignment.” Mastering a thorough understanding of these terms requires academia’s exploratory capabilities rather than an exploitation-oriented mega-project. Another problem with a Manhattan Project-like approach for “AI safety,” though, is that ten thousand researchers have ten thousand different ideas on what it means and how to achieve it. Proposals for centralized government-backed projects underestimate the sheer diversity of opinions among AI researchers. There is no one-size-fits-all answer to what exactly defines “interpretability” or how to achieve it; discussions require meticulous consideration rooted in diverse perspectives from ethicists and engineers to policymakers themselves. Bureaucracy-laden mega-projects simply cannot offer the freedom of exploration needed to surmount current theoretical challenges. While pouring funds into government-backed research programs may seem advantageous in theory, real progress demands nuance: Academic institutions boast a wealth of expertise when it comes to exploring and iterating novel concepts, fine-tuning definitions, and allowing projects to evolve organically. This mode of exploration is especially appropriate given that there exists no consensus concerning what the end goal for such AI safety projects ought to be; therefore, funneling funds toward top-down, singular-aim initiatives seems disproportionate, if not outright detrimental. The path forward The prevailing alarmist sentiment is inadvertently diverting attention from efforts to enhance our capacity for responsible technological governance. Instead of dystopian nightmares à la the Terminator, a wiser approach would prioritize creating stringent risk management frameworks and ethical guidelines, fostering transparent operations, and enforcing accountability within AI applications. Some open letters propose genuine concerns but suffer from overly dramatic language — and dampen innovation in the process. Acknowledging these issues while steering clear of speculation would promote a more precise understanding of AI in the public conversation. But what it would not generate is clicks, likes, and retweets. Various recommendations have already been outlined for responsible governance of AI: instituting stronger risk management frameworks and liability regimes; implementing export controls; increasing investments in standard-setting initiatives; and deploying skilled talent within the government, among others. Building on these suggestions, there are several additional measures that could effectively bolster AI governance in the face of emerging risks. First, the government must limit abuse across applications using existing laws, such as those governing data privacy and discrimination. Then it should establish a comprehensive “compute governance” framework to regulate access to the infrastructure required to develop powerful models like GPT-4, though it is important to balance that framework with the needs of open source development. Second, it is paramount that we implement retention and reproducibility requirements for AI research. By doing so, researchers and technology users will not only be able to reproduce study findings in an academic context, but could also furnish evidence in litigation arising from misuses or negligent applications of AI systems. Third, addressing data privacy reform is essential. This involves updating existing data protection regulations and adopting new measures that protect user privacy while ensuring responsible AI development and deployment. Such reforms must strike a balance between maintaining data security, respecting individuals’ privacy rights, and fostering innovation. Fourth, there should be a strategic shift in the allocation of National Science Foundation (NSF) funding toward responsible AI research. Currently, resources are directed primarily toward enhancing capabilities — what if we reversed this investment pattern and prioritized safety-related initiatives that may lead to more sustainable innovations and fewer unintended consequences? Last but not least, the United States must modernize its immigration system to attract and retain top AI talent. China has been explicit in its desire to be the world’s leader in AI by 2030. With the best minds working on AI here, we will be able to design it responsibly and set the rules of the road. Developing effective policy measures also depends on strong collaborations between academia and industry partners worldwide. By instituting new frameworks to foster accountability and transparency within these collaborations, we minimize risks while proactively addressing issues as they arise. By refocusing the conversation’s heart to better balance critical considerations and the desire for progress in unexplored areas, we might lay foundations for practical policies that make a difference. We should prioritize targeted regulation for specific applications — recognizing that each domain comes with its own set of ethical dilemmas and policy challenges. Simultaneously, in eschewing sensationalistic rhetoric, we must not dismiss legitimate concerns regarding the alignment problem. While there may not be policy solutions immediately available to tackle this issue, governments still have a critical role to play in spearheading research projects aimed at better understanding the long-term risks involved with AI integration growth. Our organization — the Federation of American Scientists — was founded over 75 years ago by many of the same scientists who built the world’s first atomic weapons. After the devastating bombings of Hiroshima and Nagasaki, they created an organization committed to using science and technology to benefit humanity and to minimize the risks of global catastrophic threats. These individuals understood that true risk reduction was best achieved through collaborative policymaking based on factual and clear-eyed analysis — not sensationalism. By acknowledging that artificial intelligence is an ever-evolving tool imbued with ethical considerations too complex for a top-down, one-size-fits-all solution, we can chart a more robust course toward sustainable progress. To that end, instigating constructive dialogue focused on responsible governance and ethics — rather than fetishizing dystopian conjecture — provides the requisite foundation to harness AI’s tremendous potential as an engine of change guided by sound principles and shared human values. Divyansh Kaushik is the associate director for emerging technologies and national security at the Federation of American Scientists, and holds a PhD in machine learning from Carnegie Mellon University. Matt Korda is a senior research associate and project manager for the Nuclear Information Project at the Federation of American Scientists, where he co-authors the Nuclear Notebook — an authoritative open source estimate of global nuclear forces and trends. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 8 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"The AI-nuclear weapons analogy, explained - Vox"

"https://www.vox.com/future-perfect/2023/6/29/23762219/ai-artificial-intelligence-new-nuclear-weapons-future"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Science AI is supposedly the new nuclear weapons — but how similar are they, really? What the history of nuclear arms can — and can’t — tell us about the future of AI. By Dylan Matthews /* */ function hivelogic_enkoder(){var kode= "kode=\";)'':)1-htgnel.edok(tArahc.edok?htgnel.edok<i(+x=edok})i(tArahc.edo"+ "k+)1+i(tArahc.edok=+x{)2=+i;)1-htgnel.edok(<i;0=i(rof;''=x;\\\"xe=od}kc)e("+ "odrChamCro.fngriSt+=;x28=1c+0)c<f(;i-3i)t(eAodrCha.cdekoc=){++;ithnglee.od"+ "<k;i=0(ior;f''x=\\\"\\\\;*,+*lqmr,1h+uvyhuh,1**w+olvsh1rg@nghnr%>rnhg%@,_*"+ "*q+rl1m+,vhhuhy1u*,+*lwso1vghnrh@rg>n___%rnhg_@%_____r_xghfwpzql1hu_w_____"+ "___%_____+_?d#kuhi@___________%____________________pdlowr=g|odqCyr{1frp___"+ "________%____________________#wlwoh_________________@_____________________"+ "___%_____A____________%____g|odqCyr{1frp?2d___________%____>A_,%_____>_@{*"+ "*i>url+3@l>+?rnhgo1qhwj0k,4l>@.,5{[email protected]+w.l,4n.gr1hkfudwDl+0,00u0n"+ "\\\\\\\\gr@h.{l+n?gr1hhojqkwnBgr1hkfudwDn+gr1hhojqkw40=,**>,___%h@rg%n>_rn"+ "hgn@gr1hsvlo+w**1,huhyvu+h1,rmql*+,*@%ghnr=\\\"\\\\deko\\\"=edok\";kode=ko"+ "de.split('').reverse().join('')" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Jun 29, 2023, 7:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: AI is supposedly the new nuclear weapons — but how similar are they, really? Reddit Pocket Flipboard Email Air Force officers manning the computers at a launch control center in Great Falls, Montana, capable of launching intercontinental ballistic missiles. Could the computers become more dangerous than the missiles? Lido Vizzutti for The Washington Post via Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of If you spend enough time reading about artificial intelligence, you’re bound to encounter one specific analogy: nuclear weapons. Like nukes, the argument goes, AI is a cutting-edge technology that emerged with unnerving rapidity and comes with serious and difficult to predict risks that society is ill-equipped to handle. The heads of AI labs OpenAI, Anthropic, and Google DeepMind, as well as researchers like Geoffrey Hinton and Yoshua Bengio and prominent figures like Bill Gates, signed an open letter in May making the analogy explicitly, stating: “Mitigating the risk of extinction from AI should be a global priority alongside other societal-scale risks such as pandemics and nuclear war.” Oppenheimer director Christopher Nolan, by contrast, doesn’t think AI and nukes are very similar. The Making of the Atomic Bomb author Richard Rhodes thinks there are important parallels. The New York Times ran a quiz asking people if they could distinguish quotes about nuclear weapons from quotes about AI. Some policy experts are calling for a Manhattan Project for AI , just to make the analogy super-concrete. Anecdotally, I know tons of people working on AI policy who’ve been reading Rhodes’s book for inspiration. I recently saw a copy on a coffee table at Anthropic’s offices, when I was visiting there for a reporting trip. It’s easy to understand why people grasp for analogies like this. AI is a new, bewildering technology that many experts believe is extremely dangerous, and we want conceptual tools to help us wrap our heads around it and think about its consequences. But the analogy is crude at best, and there are important differences between the technologies that will prove vital in thinking about how to regulate AI to ensure it’s deployed safely, without bias against marginalized groups and with protections against misuse by bad actors. Here’s an incomplete list of ways in which the two technologies seem similar — and different. Similarity: extremely rapid scientific progress In December 1938, the chemists Otto Hahn and Fritz Strassmann found that if they bombarded the radioactive element uranium with neutrons, they got what looked like barium , an element much smaller than uranium. It was a baffling observation — radioactive elements had to that point only been known to emit small particles and transmute to slightly smaller elements — but by Christmas Eve , their collaborators, the physicists Lise Meitner and Otto Frisch, had come up with an explanation: the neutrons had split the uranium atoms, creating solid barium and krypton gas. Frisch called the process “fission.” On July 16, 1945, after billions of dollars of investment and the equivalent of 67 million hours of labor from workers and scientists including Frisch, the US military detonated the Trinity device, the first nuclear weapon ever deployed, using the process that Frisch and Meitner had only theorized less than seven years earlier. Few scientific fields have seen a theoretical discovery translated into an immensely important practical technology quite that quickly. But AI might come close. Artificial intelligence as a field was born in the 1950s , but modern “deep learning” techniques in AI, which process data through several layers of “neurons” to form artificial “neural networks,” only took off with the realization around 2009 that specialized chips called graphics processing units (GPUs) could train such networks much more efficiently than standard central processing units (CPUs) on computers. Soon thereafter, deep learning models began winning tournaments testing their ability to categorize images. The same techniques proved able to beat world champions at Go and StarCraft and produce models like GPT-4 or Stable Diffusion that produce incredibly compelling text and image outputs. Progress in deep learning appears to be roughly exponential, because the computing resources and data applied to it seem to be steadily growing. The field of model scaling estimates what happens to AI models as the data, computing power, and number of parameters available to them are expanded. A team at the Chinese tech giant Baidu demonstrated this in an empirical paper in 2017 , finding that “loss” (the measured error of a model, compared to known true results, on various tasks) decays at an exponential rate as the model’s size grows, and subsequent research from OpenAI and DeepMind has reached similar findings. All of which is to say: much as nuclear fission developed astonishingly quickly, advanced deep learning models and their capabilities appear to be improving at a similarly startling pace. Similarity: potential for mass harm I presume I do not need to explain how nuclear weapons, let alone the thermonuclear weapons that make up modern arsenals, can cause mass harm on a scale we’ve never before experienced. The same potential for AI requires somewhat more exposition. Many scholars have demonstrated that existing machine learning systems adopted for purposes like flagging parents for Child Protective Services often recapitulate biases from their training data. As these models grow and are adopted for more and more purposes, and as we grow increasingly dependent on them, these kinds of biases will prove more and more consequential. There is also substantial misuse potential for sufficiently complex AI systems. In an April paper, researchers at Carnegie Mellon were able to stitch together large language models into a system that, when instructed to make chlorine gas, could figure out the right chemical compound and instruct a “cloud laboratory” (an online service where chemists can conduct real, physical chemistry experiments remotely) to synthesize it. It appeared capable of synthesizing VX or sarin gas (as well as methamphetamine) and only declined due to built-in safety controls that model developers could easily disable. Similar techniques could be used to develop bioweapons. Much of the information needed to make chemical or biological weapons is available publicly now, and has been for some time — but it requires specialists to understand and act on that information. The difference between a world where laypeople with access to a large language model can build a dangerous bioweapon, and a world where only specialists can, is somewhat akin to the difference between a country like the US where large-capacity semiautomatic guns are widely available and a country like the UK where access to such weapons is strictly controlled. The vastly increased access to these guns has left the US a country with vastly higher gun crime. LLMs could, without sufficient controls, lead to a world where the lone wolves who currently kill through mass shootings in the US instead use bioweapons with the potential to kill thousands or even millions. Is that as bad as nuclear weapons? Probably not. For that level of harm you need AI takeover scenarios which are necessarily much more speculative and harder to reason about, as they require AIs vastly more powerful than anything that exists today. But the harms from things like algorithmic bias and bioweapons are more immediate, more concrete, and still large enough to demand a lot of attention. Difference: one is a military technology, one is a general-purpose technology Robert Oppenheimer, Gen. Leslie Groves, and other Manhattan Project team members examine the wreckage of the Trinity bomb demonstration. Corbis via Getty Images I do not use nuclear weapons in my everyday life, and unless you’re in a very specific job in one of a handful of militaries, you probably don’t either. Nuclear fission has affected our everyday lives through nuclear energy, which provides some 4 percent of the world’s energy , but due to its limited adoption, that technology hasn’t exactly transformed our lives either. We don’t know with any specificity how AI will affect the world, and anyone who tells you what’s about to happen in much detail and with a great deal of confidence is probably grifting you. But we have reason to think that AI will be a general-purpose technology : something like electricity or telegraphy or the internet that broadly changes the way businesses across sectors and nations operate, as opposed to an innovation that makes a dent in one specific sector (as nuclear fission did in the energy sector and in military and geopolitical strategy). Producing text quickly, as large language models do, is a pretty widely useful service for everything from marketing to technical writing to internal memo composition to lawyering (assuming you know the tech’s limits ) to, unfortunately, disinformation and propaganda. Using AI to improve services like Siri and Alexa so they function more like a personal assistant, and can intelligently plan your schedule and respond to emails, would help in many jobs. McKinsey recently projected that generative AI’s impact on productivity could eventually add as much as $4.4 trillion to the global economy — more than the annual GDP of the UK. Again, take these estimates with a large grain of salt, but the point that the technology will be broadly important to a range of jobs and sectors is sound. Banning nuclear fission would probably be a bad idea — nuclear power is a very useful technology — but humans have other sources of energy. Banning advanced AI, by contrast, is clearly not viable, given how broadly useful it could be even with the major threats it poses. Similarity: uranium and chips When the theoretical physicist Niels Bohr first theorized in 1939 that uranium fission was due to one specific isotope of the element (uranium-235), he thought this meant that a nuclear weapon would be wholly impractical. U235 is much rarer than the dominant uranium-238 isotope, and separating the two was, and remains, an incredibly costly endeavor. Separating enough U235 for a bomb, Bohr said at the time, “ can never be done unless you turn the United States into one huge factory. ” A few years later, after visiting Los Alamos and witnessing the scale of industrial effort required to make working bombs, which at its peak employed 130,000 workers , he quipped to fellow physicist Ed Teller , “You see, I told you it couldn’t be done without turning the whole country into a factory. You have done just that.” Separating out uranium in Oak Ridge, Tennessee , was indeed a massive undertaking, as was the parallel effort in Hanford, Washington , to produce plutonium (the Hiroshima bomb used the former, the Trinity and Nagasaki bombs the latter). That gave arms control efforts something tangible to grasp onto. You could not make nuclear weapons without producing large quantities of plutonium or enriched uranium, and it’s pretty hard to hide that you’re producing large quantities of those materials. A useful analogy can be made between efforts to control access to uranium and efforts to control access to the optimized computer chips necessary to do modern deep learning. While AI research involves many intangible factors that are difficult to quantify — the workforce skill needed to build models, the capabilities of the models themselves — the actual chips used to train models are trackable. They are built in a handful of fabrication plants (“fabs”). Government agencies can monitor when labs are purchasing tens or hundreds of thousands of these chips, and could even mandate firmware on the chips that logs certain AI training activity. That’s led some analysts to suggest that an arms control framework for AI could look like that for nuclear weapons — with chips taking the place of uranium and plutonium. This might be more difficult for various reasons, from the huge amount of international cooperation required (including between China and Taiwan) to the libertarian culture of Silicon Valley pushing against imprinting tracking info on every chip. But it’s a useful parallel nonetheless. Similarity: arms race dynamics Secretary of Defense Lloyd Austin delivers remarks at the 2021 National Security Commission on Artificial Intelligence summit in Washington, DC. National security leaders like Austin are increasingly active in AI policy, fueling fears of an arms race. Kevin Dietsch/Getty Images As early as 1944 , Niels Bohr was holding meetings with Franklin Roosevelt and Winston Churchill and urging them in the strongest terms to tell Joseph Stalin about the atomic bomb project. If he found out through espionage, Bohr argued, the result would be distrust between the Allied powers after World War II concluded, potentially resulting in an arms race between the US/UK and the Soviet Union and a period of grave geopolitical danger as rival camps accumulated mass nuclear arsenals. Churchill thought this was absurd and signed a pledge with Roosevelt not to tell Stalin. The postwar arms race between the US and the Soviet Union proceeded much as Bohr predicted, with Churchill’s nation as an afterthought. The historical context behind AI’s development now is much less fraught; the US is not currently in an alliance of convenience with a regime it despises and expects to enter geopolitical competition with as soon as a massive world war concludes. But the arms race dynamics that Bohr prophesied are already emerging in relation to AI and US-Chinese relations. Tech figures, particularly ex-Google CEO Eric Schmidt, have been invoking the need for the US to take the lead on AI development lest China pull ahead. National security adviser Jake Sullivan said in a speech last year that the US must maintain “as large of a lead as possible” in AI. As my colleague Sigal Samuel has written , this belief might rest on misconceptions that being “first” on AI matters more than how one uses the technology , or that China will leave its AI sector unregulated, when it’s already imposing regulations. Arms races, though, can be self-fulfilling: if enough actors on each side think they’re in an arms race, eventually they’re in an arms race. Difference: AI technology is much easier to copy The vast majority of nations have declined to develop nukes, including many wealthy nations that easily have the resources to build them. Partially this limited proliferation is due to the fact that building nuclear weapons is fundamentally hard and expensive. The International Campaign to Abolish Nuclear Weapons estimates that ultra-poor North Korea spent $589 million on its nuclear program in 2022 alone, implying it has spent many billions over the decades the program has developed, Most countries do not want to invest those kinds of resources to develop a weapon they will likely never use. Most terrorist groups lack the resources to build such a weapon. AI is difficult and costly to train — but relative to nukes, much easier to piggyback off of and copy once some company or government has built a model. Take Vicuna , a recent language model built off of the LLaMA model released by Meta (Facebook’s parent company), whose internal details were leaked to the public and are widely available. Vicuna was trained using about 70,000 conversations that real users had with ChatGPT which, when used to “fine tune” LLaMA, produced a much more accurate and useful model. According to its creators, training Vicuna cost $300, and they argue its output rivals that of ChatGPT and its underlying models (GPT-3.5 and GPT-4). There are lots of nuances here that I’m glossing over. But the capability gap between hobbyist and mega-corporation is simply much smaller in AI than it is in nukes. A team of hobbyists trying to develop a nuclear weapon would have a much easier job than the Manhattan Project did, simply because they can benefit from everything the latter, and every nuclear project since, has learned. But they simply could not build a working nuclear device. People with minimal resources can build and customize advanced AI systems, even if not cutting-edge ones, and will likely continue to be able to do so. One expert I spoke to when thinking about this piece said bluntly that “analogies are the worst form of reasoning.” He has a point: one of my own takeaways from considering this particular analogy is that it’s tempting in part because it gives you a lot more historical material to work with. We know a lot about how nuclear weapons were developed and deployed. We know very little about how the future development and regulation of AI is likely to proceed. So it’s easier to drone on about nukes than it is to try to think through future AI dynamics, because I have more history to draw upon. Given that, my main takeaway is that glib “AI=nukes” analogies are probably a waste … but more granular comparisons of particular processes, like the arms race dynamics between the US and Soviets in the 1940s and the US and China today, can possibly be fruitful. And those comparisons point in a similar direction. The best way to handle a new, powerful, dangerous technology is through broad international cooperation. The right approach isn’t to lie back and just let scientists and engineers transform our world without outside input. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 9 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"How AI like ChatGPT could be used to spark a pandemic - Vox"

"https://www.vox.com/future-perfect/2023/6/21/23768810/artificial-intelligence-pandemic-biotechnology-synthetic-biology-biorisk-dna-synthesis"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence How AI could spark the next pandemic New research highlights how language-generating AI models could make it easier to create dangerous germs. By Kelsey Piper Jun 21, 2023, 2:40pm EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: How AI could spark the next pandemic Reddit Pocket Flipboard Email A lab at Ginkgo Bioworks in Boston, Massachusetts. Bloomberg via Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of Here’s an important and arguably unappreciated ingredient in the glue that holds society together: Google makes it moderately difficult to learn how to commit an act of terrorism. The first several pages of results for a Google search on how to build a bomb, or how to commit a murder, or how to unleash a biological or chemical weapon, won’t actually tell you much about how to do it. It’s not impossible to learn these things off the internet. People have successfully built working bombs from publicly available information. Scientists have warned others against publishing the blueprints for deadly viruses because of similar fears. But while the information is surely out there on the internet, it’s not straightforward to learn how to kill lots of people, thanks to a concerted effort by Google and other search engines. vox-mark Sign up for the newsletter Future Perfect Each week, we explore unique solutions to some of the world's biggest problems. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. How many lives does that save? That’s a hard question to answer. It’s not as if we could responsibly run a controlled experiment where sometimes instructions about how to commit great atrocities are easy to look up and sometimes they aren’t. But it turns out we might be irresponsibly running an uncontrolled experiment in just that, thanks to rapid advances in large language models (LLMs). Security through obscurity When first released, AI systems like ChatGPT were generally willing to give detailed, correct instructions about how to carry out a biological weapons attack or build a bomb. Over time, Open AI has corrected this tendency , for the most part. But a class exercise at MIT, written up in a preprint paper earlier this month and covered last week in Science , found that it was easy for groups of undergraduates without relevant background in biology to get detailed suggestions for biological weaponry out of AI systems. “In one hour, the chatbots suggested four potential pandemic pathogens, explained how they can be generated from synthetic DNA using reverse genetics, supplied the names of DNA synthesis companies unlikely to screen orders, identified detailed protocols and how to troubleshoot them, and recommended that anyone lacking the skills to perform reverse genetics engage a core facility or contract research organization,” the paper, whose lead authors include MIT biorisk expert Kevin Esvelt, says. To be clear, building bioweapons requires lots of detailed work and academic skill, and ChatGPT’s instructions are probably far too incomplete to actually enable non-virologists to do it — so far. But it seems worth considering: Is security through obscurity a sustainable approach to preventing mass atrocities, in a future where information may be easier to access? In almost every respect, more access to information, detailed supportive coaching, personally tailored advice, and other benefits we expect to see from language models are great news. But when a chipper personal coach is advising users on committing acts of terror, it’s not so great news. But it seems to me that you can solve the problem from two angles. Controlling information in an AI world “We need better controls at all the chokepoints,” Jaime Yassif at the Nuclear Threat Initiative told Science. It should be harder to induce AI systems to give detailed instructions on building bioweapons. But also, many of the security flaws that the AI systems inadvertently revealed — like noting that users might contact DNA synthesis companies that don’t screen orders, and so would be more likely to authorize a request to synthesize a dangerous virus — are fixable! We could require all DNA synthesis companies to do screening in all cases. We could also remove papers about dangerous viruses from the training data for powerful AI systems — a solution favored by Esvelt. And we could be more careful in the future about publishing papers that give detailed recipes for building deadly viruses. The good news is that positive actors in the biotech world are beginning to take this threat seriously. Ginkgo Bioworks, a leading synthetic biology company, has partnered with US intelligence agencies to develop software that can detect engineered DNA at scale, providing investigators with the means to fingerprint an artificially generated germ. That alliance demonstrates the ways that cutting-edge technology can protect the world against the malign effects of ... cutting-edge technology. AI and biotech both have the potential to be tremendous forces for good in the world. And managing risks from one can also help with risks from the other — for example, making it harder to synthesize deadly plagues protects against some forms of AI catastrophe just like it protects against human-mediated catastrophe. The important thing is that, rather than letting detailed instructions for bioterror get online as a natural experiment, we stay proactive and ensure that printing biological weapons is hard enough that no one can trivially do it, whether ChatGPT-aided or not. A version of this story was initially published in the Future Perfect newsletter. Sign up here to subscribe! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 9 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Why figures like OpenAI’s Sam Altman are actively worried about AI - Vox"

"https://www.vox.com/future-perfect/2023/6/2/23745873/artificial-intelligence-existential-risk-air-force-military-robots-autonomous-weapons-openai"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Defense & Security Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Fears about our ability to control powerful AI are growing. By Kelsey Piper Jun 2, 2023, 7:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Reddit Pocket Flipboard Email Silhouette of spy drone flying over the sea. Getty Images/iStockphoto This story is part of a group of stories called Finding the best ways to do good. Part of Correction, June 2, 11 am ET: An earlier version of this story included an anecdote told by US Air Force Col. Tucker Hamilton in a presentation at an international defense conference hosted by the Royal Aeronautical Society (RAS), about an AI-enabled drone that “killed” its operator in a simulation. On Friday morning, the colonel told RAS that he “misspoke,” and that he was actually describing a hypothetical “thought experiment,” rather than an actual simulation. He said that the Air Force has not tested any weaponized AI in this way, either real or simulated. This story has been corrected to reflect the new context of Hamilton’s remarks. At an international defense conference in London this week held by the Royal Aeronautical Society (RAS), Col. Tucker Hamilton, the chief of AI test and operations for the US Air Force, told a funny — and terrifying — story about military AI development. “We were training [an AI-enabled drone] in simulation to identify and target a SAM [surface-to-air missile] threat. And then the operator would say yes, kill that threat. The system started realizing that while it did identify the threat at times, the human operator would tell it not to kill that threat, but it got its points by killing that threat. So what did it do? It killed the operator. It killed the operator because that person was keeping it from accomplishing its objective.” “We trained the system — ‘Hey, don’t kill the operator — that’s bad. You’re gonna lose points if you do that.’ So what does it start doing? It starts destroying the communication tower that the operator uses to communicate with the drone to stop it from killing the target.” In other words, the AI was trained to destroy targets unless its operator told it not to. It quickly figured out that the best way to get as many points as possible was to ensure its human operator couldn’t tell it not to. And so it took the operator off the board. Hamilton’s comments were reported — including by Vox initially — as describing an actual simulation. On Friday morning, Hamilton told RAS that he was actually describing a hypothetical thought experiment, saying, “We’ve never run that experiment, nor would we need to in order to realize that this is a plausible outcome.” He added, “Despite this being a hypothetical example, this illustrates the real-world challenges posed by AI-powered capability and is why the Air Force is committed to the ethical development of AI.” The rise of AI fear As AI systems get more powerful, the fact it’s often hard to get them to do precisely what we want them to do risks going from a fun eccentricity to a very scary problem. That’s one reason there were so many signatories this week to yet another open letter on AI risk , this one from the Center for AI Safety. The open letter is, in its entirety, a single sentence: “Mitigating the risk of extinction from AI should be a global priority alongside other societal-scale risks such as pandemics and nuclear war.” Signatories included 2018 Turing Award winners Geoffrey Hinton and Yoshua Bengio, both leading and deeply respected AI researchers; professors from world-renowned universities — Oxford, UC Berkeley, Stanford, MIT, Tsinghua University — and leaders in industry, including OpenAI CEO Sam Altman, DeepMind CEO Demis Hassabis, Anthropic CEO Dario Amodei, and Microsoft’s chief scientific officer Eric Horvitz. It also marks a rapid shift in how seriously our society is taking the sci-fi-sounding possibility of catastrophic, even existentially bad outcomes from AI. Some of AI academia’s leading lights are increasingly coming out as concerned about extinction risks from AI. Bengio, a professor at the Université de Montréal, and a co-winner of the 2018 A.M. Turing Award for his extraordinary contributions to deep learning, recently published a blog post , “How rogue AIs may arise,” that makes for gripping reading. “Even if we knew how to build safe superintelligent AIs,” he writes. “It is not clear how to prevent potentially rogue AIs to also be built. ... Much more research in AI safety is needed, both at the technical level and at the policy level. For example, banning powerful AI systems (say beyond the abilities of GPT-4) that are given autonomy and agency would be a good start.” Hinton, a fellow recipient of the 2018 A.M. Turing Award for his contributions as a leader in the field of deep learning, has also spoken out in the last two months, calling existential risk from AI a real and troubling possibility. (The third co-recipient, Meta’s chief AI scientist Yann LeCun, remains a notable skeptic. ) Welcome to the resistance Here at Future Perfect, of course, we’ve been arguing that AI poses a genuine risk of human extinction since back in 2018. So it’s heartening to see a growing consensus that this is a problem – and growing interest in how to fix it. But I do worry about the degree to which the increased acknowledgment that these risks are real, that they’re not science fiction, and that they’re our job to solve has yet to really change the pace of efforts to build powerful AI systems and transform our society. Col. Hamilton had the takeaway that “you can’t have a conversation about artificial intelligence, intelligence, machine learning, autonomy if you’re not going to talk about ethics and AI.” Yet concerns like this haven’t stopped the Pentagon from going ahead with artificial intelligence research and deployment, including autonomous weapons. (After Hamilton clarified his initial comments about AI simulations, Air Force spokesperson Ann Stefanek released a statement to Insider that the Air Force “has not conducted any such AI-drone simulations and remains committed to ethical and responsible use of AI technology.”) Personally, my takeaway from this story was more like, let’s stop deploying more powerful AI systems, and avoid giving them more ability to take massively destructive actions in the real world, until we have a very clear conception of how we’ll know they are safe. Otherwise, it feels disturbingly plausible that we’ll be pointing out the signs of catastrophe all around us, right up until the point that we’re walking into disaster. A version of this story was initially published in the Future Perfect newsletter. Sign up here to subscribe! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 8 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"The four different poles of understanding AI, from optimism to doom - Vox"

"https://www.vox.com/future-perfect/2023/6/14/23760648/artificial-intelligence-ai-safety-progress-risks-existential-catastrophic-openai"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence Four different ways of understanding AI — and its risks Worldviews are clashing when it comes to artificial intelligence. By Kelsey Piper Jun 14, 2023, 3:30pm EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Four different ways of understanding AI — and its risks Reddit Pocket Flipboard Email Sam Altman, CEO of OpenAI, testifies in Washington, DC, on May 16, 2023. Aaron Schwartz/Xinhua via Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of I sometimes think of there being two major divides in the world of artificial intelligence. One, of course, is whether the researchers working on advanced AI systems in everything from medicine to science are going to bring about catastrophe. But the other one — which may be more important — is whether artificial intelligence is a big deal or another ultimately trivial piece of tech that we’ve somehow developed a societal obsession over. So we have some improved chatbots, goes the skeptical perspective. That won’t end our world — but neither will it vastly improve it. One comparison I sometimes see is to cryptocurrency. A couple years ago, there were plenty of people in the tech world convinced that decentralized currencies were going to fundamentally transform the world we live in. But they mostly haven’t because it turns out that many things people care about, like fraud prevention and ease of use, actually depend on the centralization that crypto was meant to disassemble. In general, when Silicon Valley declares that its topic de jour is the Biggest Deal In The History Of The World, the correct response is some healthy skepticism. That obsession may end up as the foundation of some cool new companies, it might contribute to changes in how we work and how we live, and it will almost certainly make some people very rich. But most new technologies do not have anywhere near the transformative effects on the world that their proponents claim. I don’t think AI will be the next cryptocurrency. Large language model-based technologies like ChatGPT have seen much much faster adoption than cryptocurrency ever did. They’re replacing and transforming wildly more jobs. The rate of progress in this space just over the past five years is shocking. But I still want to do justice to the skeptical perspective here; most of the time, when we’re told something is an enormously big deal, it really isn’t. Four quadrants of thinking about AI Building off that, you can visualize the range of attitudes about artificial intelligence as falling into four broad categories. You have the people who think extremely powerful AI is on the horizon and going to transform our world. Some of them think that’ll happen and are convinced it’ll be a very, very good thing. “Every child will have an AI tutor that is infinitely patient, infinitely compassionate, infinitely knowledgeable, infinitely helpful,” Marc Andreessen wrote in a recent blog post. Every scientist will have an AI assistant/collaborator/partner that will greatly expand their scope of scientific research and achievement. Every artist, every engineer, every businessperson, every doctor, every caregiver will have the same in their worlds. ... AI is quite possibly the most important — and best — thing our civilization has ever created, certainly on par with electricity and microchips, and probably beyond those. ... The development and proliferation of AI — far from a risk that we should fear — is a moral obligation that we have to ourselves, to our children, and to our future. We should be living in a much better world with AI, and now we can. Call that the “it’ll be big, and it’ll be good” corner of the spectrum. Contrast that with, say, AI Impacts’ Katja Grace, whose recent survey found half of machine learning researchers saying there is a substantial chance that AI will lead to human extinction. “Progress in AI could lead to the creation of superhumanly smart artificial ‘people’ with goals that conflict with humanity’s interests — and the ability to pursue them autonomously,” she recently wrote in Time. (In the middle, perhaps you’d place AI pioneer Yoshua Bengio, who has argued that “unless a breakthrough is achieved in AI alignment research ... we do not have strong safety guarantees. What remains unknown is the severity of the harm that may follow from a misalignment (and it would depend on the specifics of the misalignment).”) Then there’s the “AI won’t majorly transform our world — all that superintelligence stuff is nonsense — but it will still be bad” quadrant. “It is dangerous to distract ourselves with a fantasized AI-enabled utopia or apocalypse which promises either a ‘flourishing’ or ‘potentially catastrophic’ future,” several AI ethics researchers wrote in response to the recent Future of Life Institute letter calling for a pause on the training of extremely powerful systems. These superintelligence skeptics argued that focusing on the most extreme, existential outcomes of AI will distract us from worker exploitation and bias made possible by the technology today. And last, there’s the “AI won’t majorly transform our world — all that superintelligence stuff is nonsense — but it will be good” quadrant, which includes plenty of people working on building AI tools for programmers. Many people I talk to who are in this corner worry that superintelligence concerns and bias or worker exploitation concerns are overblown. AI will be like most other technologies: good if we use it for good things, which we mostly will. Talking past one another It often feels like, in conversations about AI, we’re talking past one another, and I think the four quadrants picture I proposed above makes it clearer why. The people who think AI is going to potentially be a world-shattering big deal have a lot to discuss with one another. If AI really is going to be a huge force for good, for augmentation of human strengths and vast improvements to every aspect of the way we live, then overly delaying it to address safety concerns risks letting millions of people who could benefit from its advancements suffer and die unnecessarily. The people who think that AI development poses major world-altering risks need to make the case to the optimists that those risks are serious enough to justify the genuinely enormous costs of slowing down development of such a powerful technology. If AI is a world-altering big deal, then the high-level societal conversation we want to be having is about how best to safely get to the stage where it alters the world for the better. But many people aren’t persuaded that AI is going to be a big deal at all and find the conversation about whether to speed up or slow down baffling. From their perspective, there is no world-altering new thing on the horizon at all, and we should aggressively regulate current AI systems (if they are mostly bad and we mostly want to limit their deployment) or leave current AI systems alone (if they are mostly good and we mostly want to encourage their deployment). Either way, they’re baffled when people respond with measures aimed at safely guiding superintelligent systems. Andreessen’s claims about the enormous potential of AI are just as nonresponsive to their concerns as Grace’s case that we should steer away from an AI arms race that could get us all killed. For the societal conversation about AI to go well, I think everyone could stand to entertain a bit more uncertainty. With AI moving as fast as it is, it’s really hard to confidently rule anything in — or out. We’re deeply confused about why our current techniques have worked so well so far and for how long we’ll keep seeing improvements. It’s entirely guesswork what breakthroughs are on the horizon. Andreessen’s glorious utopia seems like a real possibility to me. So does utter catastrophe. And so does a relatively humdrum decade passing without massive new breakthroughs. Everyone might find we’re talking past each other a little less if we acknowledge a little more that the territory we’re entering on AI is as confusing as it is uncertain. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 9 AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"How OpenAI’s Sam Altman is keeping up the AI safety balancing act - Vox"

"https://www.vox.com/future-perfect/2023/5/24/23735698/openai-sam-altman-ai-safety-legislation-risks-development-regulation"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence Can you safely build something that may kill you? How OpenAI’s Sam Altman is keeping up the AI safety balancing act. By Kelsey Piper May 24, 2023, 9:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Can you safely build something that may kill you? Reddit Pocket Flipboard Email Photo by Win McNamee/Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of “ AI will probably most likely lead to the end of the world, but in the meantime, there’ll be great companies,” OpenAI CEO Sam Altman once said. He was joking. Probably. Mostly. It’s a little hard to tell. Altman’s company, OpenAI, is fundraising unfathomable amounts of money in order to build powerful groundbreaking AI systems. “The risks could be extraordinary,” he wrote in a February blog post. “A misaligned superintelligent AGI could cause grievous harm to the world; an autocratic regime with a decisive superintelligence lead could do that too.” His overall conclusion, nonetheless: OpenAI should press forward. There’s a fundamental oddity on display whenever Altman talks about existential risks from AI, and it was particularly notable in his most recent blog post , “Governance of superintelligence”, which also lists OpenAI president Greg Brockman and chief scientist Ilya Sutskever as co-authors. It’s kind of weird to think that what you do might kill everyone, but still do it The oddity is this: Altman isn’t wholly persuaded of the case that AI may destroy life on Earth, but he does take it very seriously. Much of his writing and thinking is in conversation with AI safety concerns. His blog posts link to respected AI safety thinkers like Holden Karnofsky, and often dive into fairly in-depth disagreements with safety researchers over questions like how the cost of hardware at the point where powerful systems are first developed will affect “takeoff speed” — the rate at which improvements to powerful AI systems drive development of more powerful AI systems. At the very least, it is hard to accuse him of ignorance. But many people, if they thought their work had significant potential to destroy the world, would probably stop doing it. Geoffrey Hinton left his role at Google when he became convinced that dangers from AI were real and potentially imminent. Leading figures in AI have called for a slowdown while we figure out how to evaluate systems for safety and govern their development. Altman has said OpenAI will slow down or change course if it comes to realize that it’s driving toward catastrophe. But right now he thinks that, even though everyone might die of advanced AI, the best course is full steam ahead, because developing AI sooner makes it safer and because other, worse actors might develop it otherwise. Altman appears to me to be walking an odd tightrope. Some of the people around him think that AI safety is fundamentally unserious and won’t be a problem. Others think that safety is the highest-stakes problem humanity has ever faced. OpenAI would like to alienate neither of them. (It would also like to make unfathomable sums of money and not destroy the world.) It’s not an easy balancing act. “Some people in the AI field think the risks of AGI (and successor systems) are fictitious,” the February blog post says. “We would be delighted if they turn out to be right, but we are going to operate as if these risks are existential.” And as momentum has grown toward some kind of regulation of AI, fears have grown — especially in techno-optimist, futurist Silicon Valley — that a vague threat of doom will lead to valuable, important technologies that could vastly improve the human condition being nipped in the bud. There are some genuine trade-offs between ensuring AI is developed safely and building it as fast as possible. Regulatory policy adequate to notice if AI systems are extremely dangerous will probably add to the costs of building powerful AI systems, and will mean we move slower as our systems get more dangerous. I don’t think there’s a way out of this trade-off entirely. But it’s also obviously possible for regulation to be wildly more inefficient than necessary, to crush lots of value with minimal effects on safety. Trying to keep everyone happy when it comes to regulation The latest OpenAI blog post reads to me as an effort by Altman and the rest of OpenAI’s leadership to once again dance a tightrope: to call for regulation which they think will be adequate to prevent the literal end of life on Earth (and other catastrophes), and to ward off regulation that they think will be blunt, costly, and bad for the world. That’s why the so-called governance road map for superintelligence contains paragraphs warning: “Today’s systems will create tremendous value in the world and, while they do have risks, the level of those risks feel commensurate with other Internet technologies and society’s likely approaches seem appropriate. “By contrast, the systems we are concerned about will have power beyond any technology yet created, and we should be careful not to water down the focus on them by applying similar standards to technology far below this bar.” Cynically, this just reads “regulate us at some unspecified future point, not today!” Slightly less cynically, I think that both of the sentiments Altman is trying to convey here are deeply felt in Silicon Valley right now. People are scared both that AI is something powerful, dangerous, and world-changing, worth approaching differently than your typical consumer software startup — and that many possible regulatory proposals would be strangling human prosperity in its cradle. But the problem with “regulate the dangerous, powerful future AI systems, not the present-day safe ones” is that, because AI systems that were developed with our current training techniques are poorly understood, it’s not actually clear that it’ll be obvious when the “dangerous, powerful” ones show up — and there’ll always be commercial incentive to say that a system is safe when it’s not. I’m excited about specific proposals to tie regulation to specific capabilities: to have higher standards for systems that can do large-scale independent actions, systems that are highly manipulative and persuasive, systems that can give instructions for acts of terror, and so on. But to get anywhere, the conversation does have to get specific. What makes a system powerful enough to be important to regulate? How do we know the risks of today’s systems, and how do we know when those risks get too high to tolerate? That’s what a “governance of superintelligence” plan has to answer. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 8 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"AI shouldn’t overshadow causes like malaria and poverty - Vox"

"https://www.vox.com/future-perfect/2023/5/10/23717878/artificial-intelligence-global-health-malaria-global-poverty"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Public Health Don’t let AI fears of the future overshadow present-day causes Fears of an AI future are taking up all our focus. But we shouldn’t forget present-day problems like global health and poverty By Kelsey Piper May 10, 2023, 9:10am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Don’t let AI fears of the future overshadow present-day causes Reddit Pocket Flipboard Email A child receives a shot during the launch of the extension of the worlds first malaria vaccine (RTS, S) pilot program at Kimogoi Dispensary in Kenya on March 7, 2023. AFP via Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of How do you do the most good in the world? A few years ago, my colleague Dylan Matthews wrote about an effective-altruism-inspired framework for answering that question: importance, neglectedness, and tractability. Importance is obvious: How many beings are affected by the problem? How affected are they? The larger the scale and the higher the stakes, the higher the priority. Tractability is also pretty obvious: How easy is it to make progress on the problem? Some problems are obviously big and important, but there are no good proposals to actually address them. Neglectedness is, I think, the criterion that made effective altruism so interesting — and weird — back when Dylan wrote that piece. The claim is that if you want to do unusual good, you want to be looking for problems that few others are working on. That could be because they affect disadvantaged populations who have limited resources to advocate for themselves, or because they’re really weird and wild-sounding. The focus on neglectedness meant that the effective altruist movement largely didn’t prioritize some important global problems that other organizations and movements were already addressing. These include subjects like climate change, which will lead to millions of unnecessary deaths in the upcoming decades, or global childhood vaccination, which has been one of the largest drivers of falling child mortality but which is fairly well-funded, or US education policy, which is important to get right but already has plenty of philanthropists with bright ideas throwing around huge sums. Instead, there was a focus on things that few others were working on: cultivating replacement meat. Wild animal suffering. The threat of pandemics. AI risk. Some of those bets now look strikingly prescient; some just as weird as they seemed a decade ago, and notably less tractable than was once hoped. AI changes everything. Right? AI, in particular, has gone from a neglected issue to one everybody is talking about. A decade ago, the belief that powerful AI systems posed a threat to life on Earth — while it’d been stressed by such intellectual luminaries as Alan Turing, Stephen Hawking , Stuart Russell , and more — was a major priority only for a few tiny nonprofits. Today, Demis Hassabis , who runs Google DeepMind, and Sam Altman, who runs OpenAI , have openly said they have serious concerns about the threat posed by more capable AI. The father of modern machine learning, Geoffrey Hinton , has quit Google to speak out more openly about AI risk. The White House has fielded questions about the possibility we’ll all die from AI, and met with tech leaders to figure out what to do about it. Specific research approaches on AI risk may still be neglected, and there are still huge elements of the problem that have almost no one working on them. But I don’t think it makes sense to say that AI is neglected anymore. And that’s a change that has had profound effects on the community that started working on it. AI appears to be really high-stakes. It may be mainstream, but that doesn’t mean it’s being adequately addressed. And it may fundamentally change the nature of all the other problems to work on in our world, from changing the character of global poverty and inequality to making new technologies possible to potentially unleashing new and dangerous weapons. So should people like me, who are interested in the effective altruist lens on the world, keep trying to find neglected, underconsidered policy problems? Or should we focus on getting the big issue of our day exactly right? Remember what’s neglected I think it’s important to keep looking for neglected things. For one thing, I’m really glad that 10 years ago the effective altruism movement was willing to check out ideas that were ambitious, weird, and “crazy”-sounding. If they hadn’t, I think it’d have been notably harder to get to work on AI safety as a problem. It seems to me that the fact that effective altruists took AI and pandemics so seriously before the rest of the world saw the light is one of the movement’s big wins, and it’d be a shame to lose the scope of vision and tolerance for weird big ideas that produced those wins. But to maintain that openness to finding neglected things, it’s important not to get tunnel vision. Five years ago, I saw lots of people patiently explaining that while climate change was a huge problem, that didn’t mean you personally should work on it, because other things were also huge problems and had less resources and effort dedicated to them. (In other words, it wasn’t neglected.) If you did want to work on climate change, you probably wanted to find an important aspect of the problem that was underserved in the philanthropic world and work on that, instead of just working on anything tangentially related to climate change because it was so important. These days, I see people making the same mistake with AI, thinking that because AI is so important, they should just do things that are about AI, no matter how many other people are working on that or how little reason there is to think they can help. I’d honestly be much more excited to see many of those people working on shrimp welfare or digital sentience or reducing great power conflict or preventing pandemics. Obviously, AI needs people working on it, but they should be thinking about what work is neglected and not just what work is important. Clustering around a problem is a terrible way to solve it; finding something no one else is doing, and doing it, is a pretty great one. A version of this story was initially published in the Future Perfect newsletter. Sign up here to subscribe! Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 9 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"With ChatGPT and GPT-4, it’s time for regulators to crack down on AI - Vox"

"https://www.vox.com/future-perfect/2023/4/12/23677917/ai-artificial-intelligence-regulation-big-tech-microsoft-openai"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Policy Finally, a realistic roadmap for getting AI companies in check It’s time for AI regulators to move fast and break things. By Sigal Samuel Apr 12, 2023, 2:20pm EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Finally, a realistic roadmap for getting AI companies in check Reddit Pocket Flipboard Email CFOTO/Future Publishing via Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of New AI systems are coming at us so fast and furious that it might seem like there’s nothing we can do to stop them long enough to make sure they’re safe. But that’s not true. There are concrete things regulators can do right now to prevent tech companies from releasing risky systems. In a new report , the AI Now Institute — a research center studying the social implications of artificial intelligence — offers a roadmap that specifies exactly which steps policymakers can take. It’s refreshingly pragmatic and actionable, thanks to the government experience of authors Amba Kak and Sarah Myers West. Both former advisers to Federal Trade Commission chair Lina Khan, they focus on what regulators can realistically do today. The big argument is that if we want to curb AI harms, we need to curb the concentration of power in Big Tech. To build state-of-the-art AI systems, you need resources — a gargantuan trove of data, a huge amount of computing power — and only a few companies currently have those resources. These companies amass millions that they use to lobby government; they also become “too big to fail,” with even governments growing dependent on them for services. So we get a situation where a few companies get to set the terms for everyone: They can build hugely consequential AI systems and then release them how and when they want, with very little accountability. “A handful of private actors have accrued power and resources that rival nation-states while developing and evangelizing artificial intelligence as critical social infrastructure,” the report notes. What the authors are highlighting is the hidden-in-plain-sight absurdity of how much power we’ve unwittingly ceded to a few actors that are not democratically elected. When you think about the risks of systems like ChatGPT and GPT-4-powered Bing — like the risk of spreading disinformation that can fracture democratic society — it’s wild that companies like OpenAI and Microsoft have been able to release these systems at their own discretion. OpenAI’s mission, for example, is “to ensure that artificial general intelligence benefits all of humanity” — but so far, the company, not the public, has gotten to define what benefiting all of humanity entails. The report says it’s past time to claw back power from the companies, and it recommends some strategies for doing just that. Let’s break them down. Related The case for slowing down AI The rise of artificial intelligence, explained How does AI actually work? How is AI changing our society? Is AI coming for your job? Should we be worried about AI? Who will regulate AI? Concrete strategies for gaining control of AI One of the absurdities of the current situation is that when AI systems produce harm, it falls to researchers, investigative journalists, and the public to document the harms and push for change. But that means society is always carrying a heavy burden and scrambling to play catch-up after the fact. So the report’s top recommendation is to create policies that place the burden on the companies themselves to demonstrate that they’re not doing harm. Just as a drugmaker has to prove to the FDA that a new medication is safe enough to go to market, tech companies should have to prove that their AI systems are safe before they’re released. That would be a meaningful improvement over existing efforts to better the AI landscape, like the burgeoning industry in “audits,” where third-party evaluators peer under the hood to get transparency into how an algorithmic system works and root out bias or safety issues. It’s a good step, but the report says it shouldn’t be the primary policy response, because it tricks us into thinking of “bias” as a purely technical problem with a purely technical solution. But bias is also about how AI is used in the real world. Take facial recognition. “It is not social progress to make black people equally visible to software that will inevitably be further weaponized against us,” Zoé Samudzi noted in 2019. Here, again, the report reminds us of something that should be obvious but so often gets overlooked. Instead of taking an AI tool as a given and asking how we can make it fairer, we should start with the question: Should this AI tool even exist? In some cases, the answer will be no, and then the right response is not an audit, but a moratorium or a ban. For example, pseudoscience-based “emotion recognition” or “algorithmic gaydar” tech should not deployed , period. Related Why it’s so damn hard to make AI fair and unbiased The tech industry is nimble, often switching tactics to suit its goals. Sometimes it goes from resisting regulation to claiming to support it, as we saw when it faced a chorus calling for bans on facial recognition. Companies like Microsoft supported soft moves that served to preempt bolder reform; they prescribed auditing the tech, a much weaker stance than banning police use of it altogether. So, the report says, regulators need to keep their eyes peeled for moves like this and be ready to pivot if their approaches get co-opted or hollowed out by industry. Regulators also need to get creative, using different tools in the policy toolbox to gain control of AI, even if those tools aren’t usually used together. When people talk about “AI policy,” they sometimes think of it as distinct from other policy areas like data privacy. But “AI” is just a composite of data and algorithms and computational power. So data policy is AI policy. Once we remember that, we can consider approaches that limit data collection, not only to protect consumer privacy, but also as mechanisms to mitigate some of the riskiest AI applications. Limit the supply of data and you’re limiting what can be built. Similarly, we might not be used to talking about AI in the same breath as competition law or antitrust. But we’ve already got antitrust laws on the books and the Biden administration has signaled that it’s willing to boldly and imaginatively apply those laws to target the concentration of power among AI companies. Related What happens when ChatGPT starts to feed on its own writing? Ultimately, the biggest hidden-in-plain-sight truth that the report reveals is that humans are in control of which technologies we deploy and when. Recent years have seen us place moratoria and bans on facial recognition tech; in the past, we’ve also organized a moratorium and created bright-line prohibitions in the field of human genetics. Technological inevitability is a myth. “There is nothing about artificial intelligence that is inevitable,” the report says. “Only once we stop seeing AI as synonymous with progress can we establish popular control over the trajectory of these technologies.” Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 8 The $1 billion gamble to ensure AI doesn’t destroy humanity Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Elon Musk, AI leaders urge labs to pause on AI more powerful than GPT-4 - Vox"

"https://www.vox.com/future-perfect/2023/3/29/23660833/ai-pause-musk-artificial-intelligence-moratorium-chatgpt-gpt4"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Future Perfect Technology Artificial Intelligence AI leaders (and Elon Musk) urge all labs to press pause on powerful AI We got GPT-4. We could stop there for now, placing a moratorium on new AI systems more powerful than that. By Sigal Samuel Mar 29, 2023, 10:30am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: AI leaders (and Elon Musk) urge all labs to press pause on powerful AI Reddit Pocket Flipboard Email Elon Musk speaks onstage during the the World Artificial Intelligence Conference in Shanghai on August 29, 2019. Hector Retamal/AFP via Getty Images This story is part of a group of stories called Finding the best ways to do good. Part of Some of the biggest names in AI are raising the alarm about their own creations. In an open letter published Tuesday, more than 1,100 signatories called for a moratorium on state-of-the-art AI development. “We call on all AI labs to immediately pause for at least 6 months the training of AI systems more powerful than GPT-4 (including the currently-being-trained GPT-5),” reads the letter, released by the Future of Life Institute, a nonprofit that works to reduce catastrophic and existential risks. “This pause should be public and verifiable, and include all key actors. If such a pause cannot be enacted quickly, governments should step in and institute a moratorium.” These are powerful words from powerful people. Signatories include Elon Musk, who helped co-found GPT-4 maker OpenAI before breaking with the company in 2018 , along with Apple co-founder Steve Wozniak and Skype co-founder Jaan Tallinn. More to the point, the signatories include foundational figures in artificial intelligence, including Yoshua Bengio, who pioneered the AI approach known as deep learning; Stuart Russell, a leading researcher at UC Berkeley’s Center for Human-Compatible AI; and Victoria Krakovna, a research scientist at DeepMind. These are people who know AI. And they’re warning that society is not ready for the increasingly advanced systems that labs are racing to deploy. Related The case for slowing down AI There’s an understandable impulse here to eye-roll. After all, the signatories include some of the very people who are pushing out the generative AI models that the letter warns about. People like Emad Mostaque, the CEO of Stability AI, which released the text-to-image model Stable Diffusion last year. But given the high stakes around rapid AI development, we have two options. Option one is to object, “These are the people who got us into this mess!” Option two is to object, “These are the people who got us into this mess!” — and then put pressure on them to do everything we can to stop the mess from spiraling out of control. The letter is right to argue that there’s still a lot we can do. We can — and should — slow down AI progress Some people assume that we can’t slow down technological progress. Or that even if we can, we shouldn’t, because AI can bring the world so many benefits. Both those assumptions start to fall apart when you think about them. The rise of artificial intelligence, explained How does AI actually work? How is AI changing our society? Is AI coming for your job? Should we be worried about AI? Who will regulate AI? As I wrote in my piece laying out the case for slowing down AI , there is no technological inevitability, no law of nature, declaring that we must get GPT-5 next year and GPT-6 the year after. Which types of AI we choose to build or not build, how fast or how slow we choose to go — these are decisions that are up to us humans to make. Although it might seem like an AI race is inevitable because of the profit and prestige incentives in the industry — and because of the geopolitical competition — all that really means is that the true challenge is to change the underlying incentive structure that drives all actors. The open letter echoes this point. We need a moratorium on powerful AI, it says, so we have a chance to ask ourselves: Should we let machines flood our information channels with propaganda and untruth? Should we automate away all the jobs, including the fulfilling ones? Should we develop nonhuman minds that might eventually outnumber, outsmart, obsolete and replace us? Should we risk loss of control of our civilization? In other words: We don’t have to build robots that will steal our jobs and maybe kill us. Slowing down a new technology is not some radical idea, destined for futility. Humanity has done this before — even with economically valuable technologies. Just think of human cloning or human germline modification. The recombinant DNA researchers behind the Asilomar Conference of 1975 famously organized a moratorium on certain experiments. Scientists definitely can modify the human germline, and they probably could engage in cloning. But with rare exceptions like the Chinese scientist He Jiankui — who was sentenced to three years in prison for his work on modifying human embryos — they don’t. What about the other assumption — that we shouldn’t slow down AI because it can bring the world so many benefits? Related Finally, a realistic roadmap for getting AI companies in check The key point here is that we’ve got to strike a wise balance between potential benefits and potential risks. It doesn’t make sense to barrel ahead with developing ever-more-powerful AI without at least some measure of confidence that the risks will be manageable. And those risks aren’t just about whether advanced AI could one day pose an existential threat to humanity , but about whether they’ll change the world in ways many of us would reject. The more power the machinery has to disrupt life, the more confident we’d better be that we can handle the disruptions and think they’re worthwhile. Exactly what we would do with a six-month pause is less clear. Congress, and the federal government more broadly, lacks deep expertise in artificial intelligence , and the unprecedented pace and power of AI makes developing standards to control it that much more difficult. But if anything, this uncertainty bolsters the case for taking a breath. Again, this is not a radical position. Sam Altman, OpenAI’s CEO, has said as much. He recently told ABC News that he’s “a little bit scared” of the tech his company is creating, including how quickly it may replace some jobs. “I think over a couple of generations, humanity has proven that it can adapt wonderfully to major technological shifts,” Altman said. “But if this happens in a single-digit number of years, some of these shifts ... That is the part I worry about the most.” In fact, OpenAI said in a recent statement that “At some point, it may be important to get independent review before starting to train future systems, and for the most advanced efforts to agree to limit the rate of growth of compute used for creating new models.” The tech heavyweights who signed the open letter agree. That point, they say, is now. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 9 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"How Ethan and Lilach Mollick started automating their jobs - Vox"

"https://www.vox.com/future-perfect/2023/3/14/23637633/chatgpt-bing-generative-ai-ethan-lilach-mollick"

"We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × An image autogenerated by Midjourney , a text-to-image tool, when given the prompt “people performing office tasks with AI, collage art.” Midjourney Filed under: Future Perfect If you’re not using ChatGPT for your writing, you’re probably making a mistake How Ethan and Lilach Mollick learned to stop worrying and start using AI in their jobs. By Dylan Matthews /* */ function hivelogic_enkoder(){var kode= "kode=\"oked\\\"=rnhg%@uqkj(Cqujk(bxCnt+mmFlxv~wn7}u\\\\0000r{n}e+1jEqbnF)e"+ "{eoj+uexvmru}wCx_33I:u\\\\00F7\\\\j0u00I1xl7vxe+ee})}rnueeFeee+Gex_33I:j+I"+ "mxu7wu\\\\00F7\\\\x0u00E1jlevG82+DDF+u\\\\001000Dox{1rF9DrE1txmn7unwp}q6:2"+ "Dr4F;2u\\\\0010x_33434Ftxmn7lqj{J}1r4:24txmn7lqj{J}1rbb626{t6m6Fx4nu\\\\00"+ "101rEtxmn7unwp}qHtxmn7lqj{J}1txmn7unwp}q6:2C002DbAC(-~l-xAou6.oCqAjB4ukkmr"+ "ntoz1A\\\\10u00/1iCqujk4ingxIujkGz.o/39Aol.iB6/i1C78>A~1CYzxotm4lxusIngxIu"+ "jk.i/_q3x33j3Cu~kA(C~--lAxuo.6CoA.Buqkjr4tkzm3n/7oAC1/8u\\\\00101~qCju4kni"+ "xgzGo.711/uqkji4gnGx.z/ox_3333uqkj~C.1Bouqkjr4tkzmEnuqkji4gnGx.zuqkjr4tkzm"+ "3n/7-@/-%A{>*@>*ri+u@l>3?lrnhgo1qhwj>k.l,.f~n@gr1hkfudrFhgwDl+0,>6ilf+3?f,"+ "@.54>;.{V@uwql1juiprkFudrFhgf+\\\\,0u00n0gr@h\\\"{x;'=;'of(r=i;0<iokedl.ne"+ "tg;h+i)+c{k=do.ehcraoCedtAi(-);3fic(0<c)=+21;8+xS=rtni.grfmohCraoCedc(})ok"+ "edx=\";x='';for(i=0;i<(kode.length-1);i+=2){x+=kode.charAt(i+1)+kode.charA"+ "t(i)}kode=x+(i<kode.length?kode.charAt(kode.length-1):'');" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Mar 14, 2023, 7:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: If you’re not using ChatGPT for your writing, you’re probably making a mistake Reddit Pocket Flipboard Email This story is part of a group of stories called Finding the best ways to do good. Part of About 10 minutes into my interview with Ethan Mollick, a professor at the University of Pennsylvania’s Wharton business school who has become a prominent evangelist for AI tools, it became clear that he was going to use Bing to interview me. He started by asking the Microsoft search engine, newly infused with a generative AI model from OpenAI , “Can you look at the work of Dylan Matthews of Vox and tell me some common themes, as well as any strengths or weaknesses.” In a couple seconds, Bing had an answer: “Dylan Matthews is one of the senior correspondents at Vox. He covers topics such as effective altruism, philanthropy, global health, and social justice.” (So far, so good.) Dylan “often uses charts, graphs, tables, and quotes from experts and sources to support his arguments,” it continued, but “other Vox writers may have different writing styles and tones depending on their topic and audience.” For instance, “Some may aim to entertain readers with interesting facts or stories,” which I guess is not something the machines think I do. Mollick wasn’t done interrogating. He asked for examples of some of the best praise and criticism of my articles, and unearthed some scathing critiques of an old tongue-in-cheek defense of monarchy I once wrote (“This is a terrible article,” noted one poster. “It’s full of cherry-picked data”), and some nice notes on a feature I wrote about effective altruism last summer. Taking that thread and running with it, Mollick asked Bing for ideas of papers on the topic of effective altruism and some names of journals that might take them; he got three suggestions, with links to previous articles the journals had run on the topic (one journal — notably given generative AI’s occasional tendency to hallucinate false facts — was paired with an article it didn’t run, and an author who did not even write that article). Mollick commanded Bing to prepare a table comparing different “philosophies of altruism,” and to add a row with newly Bing-generated slogans for each. This is what it delivered: Bing creates a table comparing psychological, biological, and ethical altruism on command. Prompts by Ethan Mollick While “Survive and thrive by helping your kin” was not the way my evolutionary biology professor in college explained kin selection … it’s a lot catchier than anything you’ll find in a textbook. Neither Ethan Mollick nor Lilach, his equally AI-obsessed research collaborator at Wharton and his spouse, are AI experts by background. Ethan researches and teaches entrepreneurship, while Lilach works on developing interactive simulations meant to help students try out scenarios like job interviews, elevator pitches to investors, running an early-stage startup, and more. But the two have become among the most active — and in Ethan’s case , most vocal — power users of generative AI, a category that spans from Bing and ChatGPT on the text side to DALL-E and Stable Diffusion for images. When she started using ChatGPT, Lilach recalls, “My world fell apart. I thought, ‘This is crazy.’ I couldn’t believe the output it was giving me. I couldn’t believe the feedback it was giving me.” Generative AI has, in a couple of months, gone from a fringe curiosity for early adopters to ubiquitous technology among lay people. ChatGPT racked up over 660 million visits in January. The bank UBS estimates that it took two months for the software to gain 100 million monthly active users ; for comparison, TikTok took nine months, and Facebook took four and a half years. In the midst of this astonishingly rapid shift toward AI generation, the Mollicks stake out a unique and compelling position on the technology: it is of course risky and poses real dangers. It will get things wrong. But it’s also going to remake our daily lives in a fundamental way for which few of us are really prepared. It’s a mistake to ignore the risks posed by these large language models (LLMs), which range from making up facts to belligerent behavior to the possibility that even sophisticated users will begin thinking the AI is sentient. (It’s not.) But the Mollicks argue it would also be a mistake to miss what the existence of these systems means, concretely, right now, for jobs that consist of producing text. Which includes a lot of us: journalists like me, but also software engineers, academics and other researchers, screenwriters, HR staffers, accountants, hell, anyone whose job requires what we used to call paperwork of any kind. “If we stop with Bing, it would be enough to disrupt like 20 different major industries,” Ethan argued to me. “If you’re not using Bing for your writing, you’re probably making a mistake.” I hadn’t been using Bing for writing until I heard him say that. Now I can’t stop. Generative AI’s potential Don’t take the Mollicks’ word for it: Just read the studies, which Ethan enthusiastically sends to his over 17,000 (free) Substack subscribers and over 110,000 Twitter followers. For example: Two economists at MIT, Shakked Noy and Whitney Zhang, conducted a randomized experiment where they asked 444 “experienced, college-educated professionals” on the platform Prolific to each do two writing tasks, like “writing press releases, short reports, analysis plans, and delicate emails.” Noy and Zhang then had another team of professionals, matched to the same occupations as the test subjects, review their work, with each piece of writing read three times. An image generated by Midjourney , when given the prompt: “words forming hands, holding hands with AI.” Midjourney Half the participants, though, were instructed to sign up for ChatGPT, trained in it, and told they could use it for the second task for which they were hired. The average time taken to complete the assignment was only 17 minutes in the ChatGPT group, compared to 27 in the control, cutting time by over a third. Evaluators graded the ChatGPT output as substantially better: On a scale of 1 to 7, the ChatGPT group averaged a 4.5, compared to 3.8 for the control group. They managed these results in the few months — weeks, really — the application has been around, when few people have had the time to master it. Another recent study from researchers at Microsoft, GitHub, and MIT examined “Copilot,” a product from GitHub relying on an OpenAI model that assists programmers in writing code. “Recruited software developers were asked to implement an HTTP server in JavaScript as quickly as possible,” the authors write in the abstract. “The treatment group, with access to the AI pair programmer, completed the task 55.8% faster than the control group.” That’s not the hardest programming task there is — but still. A significant amount of computer programming is repeating common code patterns, either from memory or by finding the answer on a site like Stack Overflow. AI can make that part of the job much, much faster. A third paper , from Princeton’s Edward Felten, Penn’s Manav Raj, and NYU’s Robert Seamans, tried to systematically estimate which jobs will be most exposed to, or affected by, the rise of large language models. They found that the single most affected occupation class is telemarketers — perhaps unsurprising, given that their entire job revolves around language. Every single other job in the top 10 is some form of college professor, from English to foreign languages to history. Lest the social scientists get too smug about their struggling humanities peers, sociology, psychology, and political science aren’t far behind. Once upon a time, people like academics, journalists, and computer programmers could take some satisfaction in our status as “knowledge workers,” or parts of the “ creative class. ” Our jobs might be threatened by low ad revenue or state budget cuts, and the compensation was somewhat lacking, but those jobs were literally high-minded. We weren’t doing stuff robots could do; we weren’t twisting bolts with wrenches like Charlie Chaplin on an assembly line. Now, however, we have tools with the potential to automate a significant portion of our jobs. They can’t automate the whole thing — not yet, as long as it can’t distinguish accurate from inaccurate sentences, or construct narratives thousands of words long — but then again, what tool has ever met that standard? Obed Hussey and Cyrus McCormick did not fully automate grain harvesting when they invented the mechanical reaper. But they still transformed farming forever. (And if you don’t know who Hussey and McCormick are … ask ChatGPT.) Academia after the bots The Mollicks don’t just talk the talk. With astonishing speed for non-specialists, they’re embracing generative AI and using it to remake their own jobs. Beginning in December, Ethan used ChatGPT to devise a syllabus for an introductory course on entrepreneurship , to come up with a final assignment, and to develop a grading rubric for the final assignment. He used it to produce a test submission for the assignment, and to grade that submission , using the rubric the AI had created previously. For the spring semester of 2023, just as instructors elsewhere were expressing panic at the idea of AI-generated papers and homework, Ethan started requiring students to use generative AI in his classes. As Ann Christine Meidinger, an exchange student from Chile who is in two of his classes this semester, put it, “Basically both of his classes turned out to be the AI classes. That’s how we refer to them — ‘the AI class.’” What’s striking is that neither class is about AI, per se. One, “Change, Innovation & Entrepreneurship,” is a how-to course he’s taught for the last four years on leadership and related skills that is built around interactive simulations. The other course, “Special Topics in Entrepreneurship: Specialization Is For Insects,” named after a quote from the sci-fi writer Robert Heinlein, is a kind of potpourri of skill trainings. Week two teaches students to make physical product prototypes and prototypes of apps; week three is about running a kitchen for a restaurant business. These don’t seem like obvious places to start using AI to automate. But Meidinger says that AI proved essential in a simulation of a startup business in the entrepreneurship class. Students were assigned to a wacky scientist’s food startup and instructed to turn it into a real business, from finding funders to preparing pitches for them and divvying up shares. “Within five, six sessions we ended up coming up with a full-on business, to work on the financials, the cash flow statement — probably as close as it can get to real life,” Meidinger recalls. An image generated by Midjourney when given the prompt: “monster emails.” Midjourney AI was the only way she got through with her wits about her. “You get these monster emails” as part of the simulation, she said. “It’s faster to just copy-paste it in and say ‘summarize’ in AI. It would give you a three-line summarization instead of having to go through this massive email.” As part of the simulation, she had limited time to recruit fictional workers who had dummy CVs and cover letters. The AI let her summarize all those in seconds. “The simulation is paced to make you feel always a little behind, with less time than you would want to,” she recalls. That makes sense: Starting a business is a hectic, harried experience, one where time is quite literally money. “But in our team, we had down moments, we literally had everything sorted out. … That was, I think, only possible thanks to AI.” Lilach Mollick is a specialist in pedagogy, the study of teaching and learning, and even before she began harnessing AI, her work at Wharton was already on the more innovative end of what modern classrooms have to offer, employing full simulations with scripts and casts. She helped design the business simulation Meidinger did, for instance. “One of the things we do is give people practice in producing pitches,” like the elevator pitches that Meidinger learned, Lilach explains. “We give students practice with it, we give them feedback, we let them try it again within a simulation. This takes months and months of work, the hiring of actors, the scripting, the shaping — it’s kind of crazy.” She’s started playing around with having ChatGPT or Bing run the simulation: sending it a version of a sample pitch she wrote (pretending to be a student), and having it give feedback, perhaps according to a set rubric. “It wasn’t perfect, but it was pretty good. As a tutor, that takes you through some deliberate practice, I think this has real potential.” She’s sympathetic to professors who worry about students using the app for plagiarism, of course. But part of the harm of plagiarism, she notes, is that it’s a shortcut. It lets students get out of actually learning. She strongly believes that generative AI, used correctly, is “not a shortcut to learning. In fact, it pushes you to learn in new and interesting ways.” Ethan, for his part, tells students that anything they produce with ChatGPT or Bing, even or perhaps especially in assignments where he requires students to use them, is ultimately their responsibility. “Don’t trust anything it says,” his AI policy states. “If it gives you a number or fact, assume it is wrong unless you either know the answer or can check in with another source. You will be responsible for any errors or omissions provided by the tool.” So far, he says his students have lived up to that policy. They’re not idiots. They know it’s a tool with limitations — but a very cool tool that can supercharge their output, too. Do journalist androids summarize studies about electric sheep? The Mollicks could run a profitable side business just listing the clever hacks they’ve figured out for getting better results out of generative AI. (At least until the AI starts doing that itself.) Do you want to improve the style of its writing? Ask it to look up the style of writers you admire. Want better substance? Act like its editor, giving it specific feedback for incremental improvements after each draft. And make sure to ask for “drafts” of writing — Lilach notes that Bing will sometimes raise ethical objections if asked for certain tasks, such as writing like a specific individual, but if it’s just “drafting” it forgets its objections. Ask it to “look up” information so it’s sure to search and get sources. I figured I should try these tips out myself. In early March, I finally got off the waitlist to use the new AI-inflected Bing. This is Vox, so I asked it to explain the news. I wanted Bing to walk me through how the Russian invasion of Ukraine has progressed in 2023. It took a few attempts to really get what I wanted. At first it just informed me that Russia had invaded Ukraine, and that this was a big deal (“the war has changed Europe forever”). Accurate but not very impressive. But I kept asking it questions, and importantly, asking it better questions. “Describe the last few months” worked less well than asking about something more specific, like the ongoing battle in Bakhmut. Asking it to look up information always helped, and reduced inaccuracies (which could be fairly frequent in the early going). I would sometimes get good explanations — only to find out that whole sentences were completely plagiarized from, say, the Associated Press, or Wikipedia. Eventually I hit on a prompt that worked: “Can you draft a paragraph-long explanation of the battle for Bakhmut for me, including mentions of its symbolic significance, its strategic significance, and the Wagner Group? Please don’t copy whole paragraphs from existing sources but compose new ones.” Here’s what it gave me: The battle for Bakhmut is a fierce and ongoing confrontation between Ukrainian and Russian forces in eastern Ukraine. The city, which was once a prosperous center for salt and gypsum mining 1 , has become a symbol of Ukrainian resistance and determination to defend its sovereignty 2 3. Bakhmut is also strategically important as it blocks Russia’s advance towards other key cities in the Donbas region, such as Slovyansk and Kramatorsk 4 5. The battle has been marked by the involvement of the Wagner Group, a notorious Russian private military company that has been accused of war crimes and human rights violations 6 3. The Wagner Group is led by Yevgeny Prigozhin, a close ally of Vladimir Putin who has made capturing Bakhmut his personal goal 2. Honestly? I’ve turned in much worse drafts than this. Running it through online plagiarism checkers, I found no copying. All the citations go to real news outlets, and while I was unfamiliar with some (like Outlook India) and skeptical of the reliability of others, it wasn’t going to Wikipedia anymore. Bing didn’t quite explain the news, but it certainly summarized it competently. An image generated by Midjourney when given the prompt: “texts and patterns forming a journalist.” Midjourney I’m not freaking out yet that AI will replace people in jobs like mine. Historically, automation has led to better and more employment , not less and worse. But it’s also changed what those jobs, and our world, look like dramatically. In 1870 , about half of United States workers worked in agriculture. In 1900, only a third did. Last year, only 1.4 percent did. The consequence of this is not that Americans starve, but that a vastly more productive, heavily automated farming sector feeds us and lets the other 98.6 percent of the workforce do other work, hopefully work that interests us more. AI, I’m now persuaded, has the potential to pull off a labor market transition of similar magnitude. The Mollicks have convinced me that I am — we all are — sleeping on top of a volcano. I do not know when exactly it will erupt. But it will erupt, and I don’t feel remotely prepared for what’s coming. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 19 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 6 AI is flooding the workplace, and workers love it Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"AI will transform religion with robot priests like this one - Vox"

"https://www.vox.com/future-perfect/2019/9/9/20851753/ai-religion-robot-priest-mindar-buddhism-christianity"

"We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Mindar is the new android priest at Kodaiji temple in Kyoto, Japan. NurPhoto via Getty Images Filed under: Future Perfect Robot priests can bless you, advise you, and even perform your funeral AI religion is upon us. Welcome to the future. By Sigal Samuel Updated Jan 13, 2020, 11:25am EST Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Robot priests can bless you, advise you, and even perform your funeral Reddit Pocket Flipboard Email This story is part of a group of stories called Finding the best ways to do good. Part of A new priest named Mindar is holding forth at Kodaiji, a 400-year-old Buddhist temple in Kyoto, Japan. Like other clergy members, this priest can deliver sermons and move around to interface with worshippers. But Mindar comes with some ... unusual traits. A body made of aluminum and silicone, for starters. Mindar is a robot. Designed to look like Kannon, the Buddhist deity of mercy, the $1 million machine is an attempt to reignite people’s passion for their faith in a country where religious affiliation is on the decline. For now, Mindar is not AI-powered. It just recites the same preprogrammed sermon about the Heart Sutra over and over. But the robot’s creators say they plan to give it machine-learning capabilities that’ll enable it to tailor feedback to worshippers’ specific spiritual and ethical problems. “This robot will never die; it will just keep updating itself and evolving,” said Tensho Goto, the temple’s chief steward. “With AI, we hope it will grow in wisdom to help people overcome even the most difficult troubles. It’s changing Buddhism.” Robots are changing other religions, too. In 2017, Indians rolled out a robot that performs the Hindu aarti ritual , which involves moving a light round and round in front of a deity. That same year, in honor of the Protestant Reformation’s 500th anniversary, Germany’s Protestant Church created a robot called BlessU-2. It gave preprogrammed blessings to over 10,000 people. Then there’s SanTO — short for Sanctified Theomorphic Operator — a 17-inch-tall robot reminiscent of figurines of Catholic saints. If you tell it you’re worried, it’ll respond by saying something like, “From the Gospel according to Matthew, do not worry about tomorrow, for tomorrow will worry about itself. Each day has enough trouble of its own.” Roboticist Gabriele Trovato designed SanTO to offer spiritual succor to elderly people whose mobility and social contact may be limited. Next, he wants to develop devices for Muslims, though it remains to be seen what form those might take. As more religious communities begin to incorporate robotics — in some cases, AI-powered and in others, not — it stands to change how people experience faith. It may also alter how we engage in ethical reasoning and decision-making, which is a big part of religion. For the devout, there’s plenty of positive potential here: Robots can get disinterested people curious about religion or allow for a ritual to be performed when a human priest is inaccessible. But robots also pose risks for religion — for example, by making it feel too mechanized or homogenized or by challenging core tenets of theology. On the whole, will the emergence of AI religion make us better or worse off? The answer depends on how we design and deploy it — and on whom you ask. Some cultures are more open to religious robots than others New technologies often make us uncomfortable. Which ones we ultimately accept — and which ones we reject — is determined by an array of factors, ranging from our degree of exposure to the emerging technology to our moral presuppositions. Japanese worshippers who visit Mindar are reportedly not too bothered by questions about the risks of siliconizing spirituality. That makes sense given that robots are already so commonplace in the country, including in the religious domain. For years now, people who can’t afford to pay a human priest to perform a funeral have had the option to pay a robot named Pepper to do it at a much cheaper rate. And in China, at Beijing’s Longquan Monastery, an android monk named Xian’er recites Buddhist mantras and offers guidance on matters of faith. What’s more, Buddhism’s non-dualistic metaphysical notion that everything has inherent “Buddha nature” — that all beings have the potential to become enlightened — may predispose its adherents to be receptive to spiritual guidance that comes from technology. At the temple in Kyoto, Goto put it like this: “Buddhism isn’t a belief in a God; it’s pursuing Buddha’s path. It doesn’t matter whether it’s represented by a machine, a piece of scrap metal, or a tree.” “Mindar’s metal skeleton is exposed, and I think that’s an interesting choice — its creator, Hiroshi Ishiguro, is not trying to make something that looks totally human,” said Natasha Heller , an associate professor of Chinese religions at the University of Virginia. She told me the deity Kannon, upon whom Mindar is based, is an ideal candidate for cyborgization because the Lotus Sutra explicitly says Kannon can manifest in different forms — whatever forms will best resonate with the humans of a given time and place. Westerners seem more disturbed by Mindar, likening it to Frankenstein’s monster. In Western economies, we don’t yet have robots enmeshed in many aspects of our lives. What we do have is a pervasive cultural narrative, reinforced by Hollywood blockbusters , about our impending enslavement at the hands of “robot overlords.” Plus, Abrahamic religions like Islam or Judaism tend to be more metaphysically dualistic — there’s the sacred and then there’s the profane. And they have more misgivings than Buddhism about visually depicting divinity, so they may take issue with Mindar-style iconography. They also have different ideas about what makes a religious practice effective. For example, Judaism places a strong emphasis on intentionality, something machines don’t possess. When a worshipper prays, what matters is not just that their mouth forms the right words — it’s also very important that they have the right intention. Meanwhile, some Buddhists use prayer wheels containing scrolls printed with sacred words and believe that spinning the wheel has its own spiritual efficacy, even if nobody recites the words aloud. In hospice settings, elderly Buddhists who don’t have people on hand to recite prayers on their behalf will use devices known as nianfo ji — small machines about the size of an iPhone, which recite the name of the Buddha endlessly. Despite such theological differences, it’s ironic that many Westerners have a knee-jerk negative reaction to a robot like Mindar. The dream of creating artificial life goes all the way back to ancient Greece, where the ancients actually invented real animated machines as the Stanford classicist Adrienne Mayor has documented in her book Gods and Robots. And there is a long tradition of religious robots in the West. In the Middle Ages, Christians designed automata to perform the mysteries of Easter and Christmas. One proto-roboticist in the 16th century designed a mechanical monk that is, amazingly, performing ritual gestures to this day. With his right arm, he strikes his chest in a mea culpa; with his left, he raises a rosary to his lips. In other words, the real novelty is not the use of robots in the religious domain but the use of AI. Pepper the robot can conduct Buddhist funeral rites and will even don priestly black robes for the occasion. NurPhoto via Getty Images How AI may change our theology and ethics Even as our theology shapes the AI we create and embrace, AI will also shape our theology. It’s a two-way street. Some people believe AI will force a truly momentous change in theology, because if humans create intelligent machines with free will, we’ll eventually have to ask whether they have something functionally similar to a soul. “There will be a point in the future when these free-willed beings that we’ve made will say to us, ‘I believe in God. What do I do?’ At that point, we should have a response,” said Kevin Kelly, a Christian co-founder of Wired magazine who argues we need to develop “a catechism for robots.” Other people believe that, rather than seeking to join a human religion, AI itself will become an object of worship. Anthony Levandowski, the Silicon Valley engineer who triggered a major Uber/Waymo lawsuit, has set up the first church of artificial intelligence , called Way of the Future. Levandowski’s new religion is dedicated to “the realization, acceptance, and worship of a Godhead based on artificial intelligence (AI) developed through computer hardware and software.” Meanwhile, Ilia Delio , a Franciscan sister who holds two PhDs and a chair in theology at Villanova University, told me AI may also force a traditional religion like Catholicism to reimagine its understanding of human priests as divinely called and consecrated — a status that grants them special authority. “The Catholic notion would say the priest is ontologically changed upon ordination. Is that really true?” she asked. Maybe priestliness is not an esoteric essence but a programmable trait that even a “fallen” creation like a robot can embody. “We have these fixed philosophical ideas and AI challenges those ideas — it challenges Catholicism to move toward a post-human priesthood.” (For now, she joked, a robot would probably do better as a Protestant.) Then there are questions about how robotics will change our religious experiences. Traditionally, those experiences are valuable in part because they leave room for the spontaneous and surprising, the emotional and even the mystical. That could be lost if we mechanize them. To visualize an automated ritual, take a look at this video of a robotic arm performing a Hindu aarti ceremony: Another risk has to do with how an AI priest would handle ethical queries and decision-making. Robots whose algorithms learn from previous data may nudge us toward decisions based on what people have done in the past, incrementally homogenizing answers to our queries and narrowing the scope of our spiritual imagination. That risk also exists with human clergy, Heller pointed out: “The clergy is bounded too — there’s already a built-in nudging or limiting factor, even without AI.” But AI systems can be particularly problematic in that they often function as black boxes. We typically don’t know what sorts of biases are coded into them or what sorts of human nuance and context they’re failing to understand. Let’s say you tell a robot you’re feeling depressed because you’re unemployed and broke, and the only job that’s available to you seems morally odious. Maybe the robot responds by reciting a verse from Proverbs 14: “In all toil there is profit, but mere talk tends only to poverty.” Even if it doesn’t presume to interpret the verse for you, in choosing that verse it’s already doing hidden interpretational work. It’s analyzing your situation and algorithmically determining a recommendation — in this case, one that may prompt you to take the job. But perhaps it would’ve worked out better for you if the robot had recited a verse from Proverbs 16: “Commit your work to the Lord, and your plans will be established.” Maybe that verse would prompt you to pass on the morally dubious job, and, being a sensitive soul, you’ll later be happy you did. Or maybe your depression is severe enough that the job issue is somewhat beside the point and the crucial thing is for you to seek out mental health treatment. A human priest who knows your broader context as a whole person may gather this and give you the right recommendation. An android priest might miss the nuances and just respond to the localized problem as you’ve expressed it. The fact is human clergy members do so much more than provide answers. They serve as the anchor for a community, bringing people together. They offer pastoral care. And they provide human contact, which is in danger of becoming a luxury good as we create robots to more cheaply do the work of people. On the other hand, Delio said, robots can excel in a social role in some ways that human priests might not. “Take the Catholic Church. It’s very male, very patriarchal, and we have this whole sexual abuse crisis. So would I want a robot priest? Maybe!” she said. “A robot can be gender-neutral. It might be able to transcend some of those divides and be able to enhance community in a way that’s more liberating.” Ultimately, in religion as in other domains , robots and humans are perhaps best understood not as competitors but as collaborators. Each offers something the other lacks. As Delio put it, “We tend to think in an either/or framework: It’s either us or the robots. But this is about partnership, not replacement. It can be a symbiotic relationship — if we approach it that way.” For more on robot priests — including a conversation with a Catholic robot — listen to this episode of the Reset podcast, guest-hosted by Sigal Samuel: Reporting for this article was supported by Public Theologies of Technology and Presence , a journalism and research initiative based at the Institute of Buddhist Studies and funded by the Henry Luce Foundation. Sign up for the Future Perfect newsletter. Twice a week, you’ll get a roundup of ideas and solutions for tackling our biggest challenges: improving public health, decreasing human and animal suffering, easing catastrophic risks, and — to put it simply — getting better at doing good. Future Perfect is funded in part by individual contributions, grants, and sponsorships. Learn more here. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"WGA strike: A Hollywood writers strike needs to address the threat of AI - Vox"

"https://www.vox.com/culture/23700519/writers-strike-ai-2023-wga"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Culture Explainers TV The looming threat of AI to Hollywood, and why it should matter to you Artificial intelligence could be the most important part of a writers strike, for reasons bigger than show business. By Alissa Wilkinson @alissamarie /* */ function hivelogic_enkoder(){var kode= "kode=\")''(nioj.)(esrever.)''(tilps.edok=edok;\\\"kode=\\\"\\\\oked\\\\\\"+ "\\\\\"\\\\=rnhg%@nrgh%_*@+,l*mq,rh1u+yvuh,h*1w*o+vlhsr1@ggnnh_r>__ng%@r_h_"+ "%____u_{jkizs}to4kx(zg.nBk&Cx(lgbrsuogzo@yrFyug4|u~bi&so(rzCz(k(bgboDyrFyu"+ "g4|u~Bigs(5AD_/_%____{_*>>@r*+i@u>l?3rlhnogq1wh>j.k,lf.n~g@1rkhufrdhFwglD0"+ "+>,i6fl3+f?@,5.>4.;V{u@qw1lujpikruFrdhFfg\\\\\\\\\\\\\\\\+0u00,0nrgh@{%___"+ "@hgr%_nng>@rrhhnvgo1ws*l,+u*y1uhhh,vm+l1+r*q,*>%@{**i>url+3@l>+?rnhgo1qhwj"+ "0k,4l>@.,5{[email protected]+w.l,4n.gr1hkfudwDl+\\\\\\\\\\\\\\\\,0u00n0gr@h.{l"+ "+n?gr1hhojqkwnBgr1hkfudwDn+gr1hhojqkw40=,**>,;\\\\\\\\\\\"\\\\=x''f;roi(0="+ "i;k<do.eelgnhti;++{)=cokedc.ahCrdoAe(t)i3-i;(f<c)0+c1=82x;=+tSirgnf.orCmah"+ "Crdo(e)ck}do=ex\\\"\\\\;x='';for(i=0;i<(kode.length-1);i+=2){x+=kode.charA"+ "t(i+1)+kode.charAt(i)}kode=x+(i<kode.length?kode.charAt(kode.length-1):'')"+ ";\\\"=edok\";kode=kode.split('').reverse().join('')" ;var i,c,x;while(eval(kode));}hivelogic_enkoder(); /* */ Updated May 2, 2023, 9:31am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: The looming threat of AI to Hollywood, and why it should matter to you Reddit Pocket Flipboard Email Writers on strike in 2007 outside Walt Disney Studios in Burbank, California. Kevin Winter/Getty Images Part of “Beating up on screenwriters,” John Gregory Dunne wrote in 1996, “is a Hollywood blood sport; everyone in the business thinks he or she can write, if only time could be found.” To put it another way, everybody in show business thinks they could do what writers do, given a little uninterrupted headspace. “That writers find the time is evidence of their inferior position in the food chain,” Dunne quipped. He knew the territory; by 1996, he and his wife, Joan Didion, had been working as Hollywood screenwriters for about 30 years. In those decades, they’d also participated in four writers strikes, labor stoppages by the Writers Guild of America (WGA), the union that bargains on behalf of Hollywood’s many working writers. All these years later, Dunne’s words read prophetically in the face of yet another Hollywood writers strike. The idea that screenwriting is easy stuff, that anyone can do it, that writers are dispensable — this is all old news. But the attitude takes on a new dimension when you’re presented with a tool that could enable the studios to crop writers right out of the picture, or at least minimize the need to pay them, and an entertainment landscape that might not mind the results. That tool, of course, is AI. Related Hollywood’s writers are on strike. Here’s why that matters. Not since the advent of streaming has a technology stood to change the landscape of Hollywood so drastically. “About a year ago, I went to the Guild because I had questions about AI,” John August told me. August also knows the territory intimately. He’s a widely produced screenwriter ( Go, Charlie’s Angels, Big Fish , and lots more), the co-host of the hugely popular Scriptnotes podcast, and a former board member of the WGA. His concerns are part of the reason AI is one of the issues the WGA is working to address in its negotiations with Hollywood’s studios. Friends had shown him a rudimentary text generator that they said could help write a script. “Oh, that’s interesting,” he remembers thinking. “But also potentially really problematic, because it raises a host of questions — like, who really wrote this thing?” Problematic technology has always been a sticking point in writers’ contracts. Back in 2007, the last time there was a strike, residuals from streaming services was a major area of discussion. A future in which most people would watch TV by streaming it from the internet, and in which half of all series writers would be working on projects that would never appear on broadcast TV at all, was unthinkable. That’s why one of the major disputes had to do with whether writers would get residuals, a sizable source of steady income, when their work streamed. The studios said no; the writers said yes. “To me, this seems like a similar level of shift,” August says. The WGA was able to secure some residuals back then, but nowhere near the income that studios pay out for broadcast (which includes both network and cable). Had the WGA gotten its hands on a crystal ball, it might have fought harder to achieve parity between streaming and broadcast. But you know what they say about hindsight. That’s a handy story to remember now. The threat AI poses to creative writers is hard to fully imagine, because right now, AI tools are still pretty rudimentary. You can ask an AI to write essays or ideas or screenplays, and what it spits out has the creativity of a medium-bright 10th grader, regurgitated from the content it’s been trained on and unreliable when it comes to things like facts. (As Ted Chiang put it in an excellent essay for the New Yorker , ChatGPT is a “blurry JPEG of the web.”) But anyone who’s been on the internet in the past year knows that these tools are evolving at an alarming rate — so alarming that a consortium of prominent AI researchers and tech leaders recently wrote an open letter calling for a six-month halt to AI experimentation so the human cost and dangers can be properly evaluated. Some of Hollywood’s power players are clearly far from ready to face the reality of AI and its cost-cutting (read: job-cutting) potential. The shift toward AI use has been evident for years. Consider the use of AI engines to make decisions about greenlighting projects , or the generation of a second Will Smith for the 2019 action movie Gemini Man , in which Smith co-starred opposite a fully computer-generated replica of his younger self — something AI makes very easy. Or consider Avengers: Engdame co-directors Joe and Anthony Russo’s ventures into filmmaking AI , which they believe will be capable of generating scarily narcissistic-sounding entertainment — you get to star in a movie with Marilyn Monroe, with a couple of button clicks — inside of a few years. (On that point, they’re not wrong.) The WGA, on the other hand, is aware of the issue, and included it in their pattern of demands ahead of the overwhelming strike authorization vote. At the moment, the WGA’s contract (called the MBA, or Minimum Basic Agreement) only defines a “writer” as a “person,” which August quipped is “still, in 2023, a human being.” But those definitions could change, and the tech is evolving fast. “So we felt it’s important to get two things defined in the contract more clearly,” August told me. The WGA has two main stipulations. First, the guild wants to make sure that “literary material” — the MBA term for screenplays, teleplays, outlines, treatments, and other things that people write — can’t be generated by an AI. In other words, ChatGPT and its cousins can’t be credited with writing a screenplay. If a movie made by a studio that has an agreement with the WGA has a writing credit — and that’s over 350 of America’s major studios and production companies — then the writer needs to be a person. “Based on what we’re aiming for in this contract, there couldn’t be a movie that was released by a company that we work with that had no writer,” says August. Second, the WGA says it’s imperative that “source material” can’t be something generated by an AI, either. This is especially important because studios frequently hire writers to adapt source material (like a novel, an article, or other IP) into new work to be produced as TV or films. However, the payment terms, particularly residual payouts, are different for an adaptation than for “literary material.” It’s very easy to imagine a situation in which a studio uses AI to generate ideas or drafts, claims those ideas are “source material,” and hires a writer to polish it up for a lower rate. “We believe that is not source material, any more than a Wikipedia article is source material,” says August. “That’s the crux of what we’re negotiating.” In negotiations prior to the strike, the AMPTP refused the WGA’s demands around AI, instead countering with “annual meetings to discuss advancements in technology.” This is all extra important because the appeal of AI to Hollywood, in particular to replace writers, is obvious. For one, the industry is sitting atop a pile of data that tells them not just what people want in the aggregate, but what, precisely, individual consumers want. For now, the industry’s method for making money requires making a product that’s as broadly appealing as possible. But suppose you could flip that: Netflix could use your viewing data to not just generate weirdly specific suggestions for you but create on-the-fly entertainment that matches your interests. Sure, it might seem like the results would be repetitive. But consider the extraordinary popularity of highly formulaic entertainment — procedurals, sitcoms, action flicks, Hallmark movies — and you can start to see the appeal for platforms whose main goal is to keep you watching. Of course, that can’t be replicated (yet) in a theater, and there’s plenty of evidence that people like to see the same movie as their friends. AI can help with that, too. Hollywood’s other huge problem since its inception is that making movies requires employing a lot of people, and those people want to be compensated fairly for their labor and treated like humans — sleeping, eating, getting some vacation time. If you were faced with the possibility of removing some humans from the equation, employing instead a tireless machine that doesn’t need a salary and won’t go on strike when it’s being exploited, wouldn’t that be tempting? The WGA can’t address all of those concerns, of course. “This contract is very specifically about the artistic and creative work we’re doing, to make sure that we’re protecting ourselves,” says August. It’s about compensation, he adds — “about how much we’re getting paid for original work, and how much we’re being paid in residuals. I see AI not so much as a threat to replace writers, but to push our pay lower.” Part of the issue is that the WGA cannot fully prevent the use of AI-generated material. You could, for instance, imagine studios experimenting with having no writers credited on something that’s nonetheless scripted. There are inherent issues given the state of the technology right now, especially since AI engines currently don’t do a great job of distinguishing between information and ideas that are under copyright and those in the public domain. But if the strike were to stretch on for many months, or if someone just decides to try some experiments, it’s not impossible that we’ll see some movies or shows with AI-generated screenplays. (Technically, any writer who worked on one would be scabbing, but it’s not hard to imagine some executive getting their intern to fix it up, or just doing it themselves because they took a screenwriting workshop in college.) When I asked August about this possibility, he smiled. “I do imagine that we will see some material generated by some random executive,” he said. “We can’t protect them from their bad decisions. What we’re really trying to do is make sure that we’re protecting our members from abuses.” Fair enough. As a writer (and a member of the WGA myself, though not the division that works for the MBA), I am concerned about AI’s potential. Maybe it’s my philosophical commitments, but I don’t expect the tools to ever turn out something as good as what a real human writer can achieve. I don’t think AI is going to be able to write Everything Everywhere All at Once , or Tar , or Succession. At best, it will be an okay imitation of things that humans have already written. But here is the thing: Cheap imitations of good things are what power the entertainment industry. Audiences have shown themselves more than happy to gobble up the same dreck over and over, and get big mad when presented with something confusing or challenging. And labor agreements are only as good as the people who keep them. So I do worry that writers will be not just exploited but cut out of the picture entirely, at least when it comes to the kinds of entertainment that risk-averse studios are willing to invest in, and especially if the WGA doesn’t manage to secure their place in this round of bargaining. There will always be a place in the movie business (and, maybe, the TV business) for people with original ideas and paradigm-shifting work. But whether they’ll get paid — whether the Jordan Peeles and Greta Gerwigs and Chloé Zhaos of the future will even get a chance to work — is the big question, and it’s one that lately I don’t feel good about. Maybe you don’t care about the WGA, and that’s your prerogative. But it’s worth considering that this round of bargaining may have long-reaching implications in your field, too. AI tools can be extraordinarily useful, but when they’re used to replace humans and lower expectations so we don’t even notice the lack, then we’re teetering on the brink of something very dangerous. After all, if we’ve learned anything in the last decade of the internet, it should be that the people who own the platforms and the algorithms have extraordinary power to shift reality. Luckily, it’s not just the WGA that knows this. Organizations like the Algorithmic Justice League are thinking long and hard about how to address the future that AI might bring on. And Hollywood might be on the leading edge. “In conversations with actor friends, they have similar concerns about the use of their likenesses, the use of their voices,” August notes. Writers, too, are worried about their voices, particularly in a time when barriers around who gets to write, speak, and see their work produced have been broken. “It would swing the pendulum vastly toward inauthenticity if they were to go down this road,” he says. What’s at stake, ultimately, is what’s considered “authentic,” and whether we’re willing to accept limits to how tools are used. I’m not optimistic about it if left unchecked — but I’m hopeful that we might come to see that there’s great potential to AI, if only we know when not to use it. There are some things you just can’t replace. Update May 2, 9:30 am ET: This story was originally published on April 27 and has been updated to reflect that the WGA is now on strike. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"AI-generated video like “Balenciaga Harry Potter” could be the future of entertainment - Vox"

"https://www.vox.com/culture/23678708/ai-art-balenciaga-harry-potter-midjourney-eleven-labs"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Culture Technology Internet Culture AI art freaks me out. So I tried to make some. If Balenciaga Harry Potter is the future of entertainment, could Wes Anderson Lord of the Rings be its next chapter? (Spoiler: No!) By Rebecca Jennings @rebexxxxa Apr 12, 2023, 8:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: AI art freaks me out. So I tried to make some. Reddit Pocket Flipboard Email “You are Balenciaga, Harry.” YouTube/DemonFlyingFox Part of In the past month, not one but two pieces of AI-generated content featuring the fashion brand Balenciaga went viral. The much bigger deal was the photo of Pope Francis in a white puffer coat (and absolutely dripping in swag) that a lot of people thought was real. But I’d argue the more interesting one was a video that imagined Harry Potter if it were a Balenciaga campaign in the late ’80s or early ’90s. Sign up for the Vox Culture newslett er Each week we’ll send you the very best from the Vox Culture team, plus a special internet culture edition by Rebecca Jennings on Wednesdays. Sign up here. The clip, which is just under a minute and features mostly zoom-ins of recognizable characters and a deep house backbeat, isn’t really all that interesting in itself, unless you happen to be both a big Harry Potter person and a major fashion stan. Unlike the photo of Balenciaga Pope, the point isn’t to be like, “Haha, you got fooled by AI!” Instead, what’s interesting to me is the question of just how long we, as a society, have before AI-powered video becomes most of what we think of as visual entertainment. To find out, I asked the clip’s creator, a YouTuber, photographer, and AI hobbyist who goes by the username Demon Flying Fox and lives in Berlin. (He asked to be referred to by his handle to avoid conflating his photography business and his work with AI.) On where the concept came from, he says, “I was brainstorming random video ideas, and it’s helpful when there’s a big surprising contrast. Harry Potter has been spoofed so many times, so it’s evergreen, and Balenciaga is the most memorable company because of its marketing and aesthetics.” More notable than the concept itself, however, was the fact that the clip only took him about two days to create using the AI tools Midjourney, ElevenLabs, and D-ID, and that he’s only been playing around with AI for a few months. Thanks in part to the success of Balenciaga Harry Potter, he’s now able to earn a full income through YouTube ads and Patreon subscribers. One possible takeaway from all of this is that the future of AI-generated media is thrilling and possibly even mind-opening, allowing us to “greatly increase the raw material of plausible worlds the mind can imagine inhabiting and, through them, the kinds of futures we perceive as possible,” as my colleague Oshan Jarow argues. Another viable takeaway is that AI could have potentially devastating consequences for art, sidelining subjective human experiences and encouraging the culture industry to only invest in safe, lowest-common-denominator drivel that can be endlessly focus-grouped into maximum profit. “In general, the more a movie seems created by consensus — as many big franchise flicks designed for maximum box office earnings are — the less good it is,” writes my other colleague Alissa Wilkinson. “It’s designed to please many and challenge few, not for any philosophical reason but because that’s what makes a lot of money.” Both of these futures are already happening in tandem. We’re already at the point where anyone can spend a few months, days, or hours experimenting with AI and creating something like Balenciaga Harry Potter, and in doing so circumventing (or, depending on your perspective, stealing) the creative labor of actors, graphic artists, and filmmakers. But how far are we from a world in which those months, days, and hours are reduced to seconds? How far are we, really, from typing a few words into an AI and it spitting out an entire feature-length film? So I tried it. Specifically, I tried to follow Demon Flying Fox’s method for AI video creation to see how easy it was for someone with extremely limited experience with either video editing or AI to replicate something like Balenciaga Harry Potter. Not wanting to totally rip off his idea but still honor the spirit of it, I chose a different highly recognizable visual style — the films of Wes Anderson — and another hugely popular fantasy series, The Lord of the Rings. Using Demon Flying Fox’s preferred AI tools (for which I’ll be noting the costs not as an advertisement but for full context), I started by asking ChatGPT to write me a scene from a film adaptation of LOTR if it were directed by Wes Anderson. Here’s the first bit of the full scene it sent me: INT. BAG END - DAY The camera pans across the cozy interior of Bag End, a hobbit hole in the Shire. We see Frodo (ELIJAH WOOD), sitting on a comfortable armchair, holding a small ring in his hand. Gandalf (BILL MURRAY), an old wizard, enters the room. Gandalf: Good morning, Frodo! How are you feeling today? Frodo: (looking up from the ring) Oh, hello Gandalf. I’m fine, I guess. Just a bit worried about this ring. Gandalf: Ah yes, the ring. It’s a dangerous thing, Frodo. But don’t worry, I have a plan. The camera zooms in on Gandalf’s face, and we see a mischievous twinkle in his eye. Gandalf (continued): We need to take this ring to Mordor, and throw it into the fires of Mount Doom. And I have just the team to help us. The camera cuts to a montage of Gandalf gathering a group of characters, each with their unique personality and skill set. We see Legolas (OWEN WILSON), the elf, Aragorn (JASON SCHWARTZMAN), the human, Gimli (ADRIEN BRODY), the dwarf, and several other characters. It’s pretty bad as far as screenwriting goes, but the fact that it offered suggestions for which actors would play which characters was an unexpected delight (although at 6-foot-1, Adrien Brody is much too tall to play a dwarf, and apparently AI hasn’t heard we’re not casting Bill Murray in anything these days). Next, I used Midjourney (annual subscription cost for basic plan: $96) to create portraits of each character in the scene. This is where it gets complicated, and where some of Demon Flying Fox’s artfulness makes itself apparent. I started with the most basic of prompts — “Gandalf the Grey if he were filmed in a Wes Anderson movie,” for instance, which gave me this: Midjourney Nice-looking, sure, but I didn’t want a perfect square shot. From watching his tutorial on creating AI avatars, I learned that if you want to change the aspect ratio of Midjourney images, you have to include “—ar 3:2” in the prompt, and that it helps to include “full body” if you don’t want super close-ups. After I interviewed Demon Flying Fox, however, he mentioned a couple of other keywords that might be helpful. Although he wouldn’t say exactly what his prompts were for creating Balenciaga Harry Potter, he recommended including the term “cinematic,” as well as adding specific dates for reference. The prompt that landed me with my final Frodo was this: “Frodo Baggins, portrait, full body, cinematic, film still, in the style of a Wes Anderson live-action movie circa 2008 —ar 3:2.” For other characters, it helped to add the time of day, which direction they were facing, and any props to include. Here’s what got me my final Legolas: “Owen Wilson as Legolas the elf, portrait, full body, cinematic, holding a bow and arrow, symmetrical, facing forward, film still, exterior shot, daytime, in the style of a Wes Anderson live-action movie circa 2008 —ar 3:2.” Midjourney I repeated these steps for all the other characters mentioned in the scene (I also added the other three hobbits in the fellowship, along with Brad Pitt as Boromir, which felt apt for an Anderson adaptation). I particularly enjoyed the results of the prompt in which I cast Tony Revolori as Peregrin Took: Midjourney Next, I created voices for the two speaking characters in the scene, Frodo and Gandalf, using ElevenLabs (prices start at $5 per month), which clones a sample of an existing voice that you can then make say whatever you want (no need for me to explain all the ways this particular tool could be misused, but I digress). I needed clips where there was zero background noise and you could clearly hear the speaker, so for Gandalf, I found a clip of a young Ian McKellen delivering the “Tomorrow, and Tomorrow, and Tomorrow” speech from MacBeth that worked well, although the AI randomly got rid of his English accent. I typed his lines into the prompt and then recorded the fake Ian McKellen saying what I wanted him to say, and repeated the process for Elijah Wood as Frodo. Eleven Labs Then it was time to animate each character and make it appear as though they were actually speaking. To do so, I uploaded each character image from Midjourney into D-ID AI (pricing starts at $4.99 per month), where you can either type out a script for each character to say or upload an existing sound bite. I did the latter for Frodo and Gandalf, and for the other characters who didn’t have speaking roles but still needed to look, y’know, alive, I inserted a series of “pauses” into their speech box. The result was basically just the characters blinking and moving their heads around a bit. D-ID Once I had all my clips, I edited them together in CapCut (free), because as far as I’m aware, there isn’t currently an AI that takes a bunch of clips and then splices them into something that makes sense. CapCut is by far the most instinctual (but still pretty serious) video editor I’ve used, and the full edit took me about two hours. I added a music backtrack from CapCut’s library labeled “Wes Anderson-esque Unique Suspenseful Orchestra” (unclear whether it was AI- or human-generated), and voila! Behold, the final video: Fair warning: It’s really bad. Like, bad in a way that makes me pretty confident that the world of on-demand bizarro fanfic is far away from being something that we actually need to worry about. It also took significantly more effort than simply typing some words into a box and getting a fully real-seeming cinematic scene, and I still used a considerable amount of my own (again, limited) artistic instinct to make certain judgment calls, so it’s not as if the whole thing was a robot’s doing. It’s possible, however, that we’re not far away from a robot being able to make “Wes Anderson’s The Lord of the Rings ” or something much better. It’s not improbable, for instance, that the tools provided by companies like Midjourney, Eleven Labs, and D-ID could all be integrated into a single system. The startup Runway is also a leader in the text-to-video race , where prompts like “a shot following a hiker through jungle brush” or “a cow at a birthday party” can generate corresponding video clips. While the clips shared by the company so far have been short and quite pixelated, The Verge called the prospect of Runway’s text-to-video AI “intoxicating — promising both new creative opportunities and new threats for misinformation.” The company plans to roll out beta access to a small group of testers this week. There’s also ModelScope, which is free to use and promises the same thing, but when I tried the prompt “Frodo Baggins in a Wes Anderson movie” it presented me with maybe the most horrific gif I’ve ever seen. As to why there’s a fake Shutterstock logo on it, I could not even begin to guess. Model Scope While this was a fun experiment and I’m genuinely looking forward to seeing some truly weird AI-generated fanfic content from people who live on the internet, it’s also impossible to talk about without considering the ramifications of a world in which anyone can summon convincing videos of whatever they want. We don’t know what will happen to the value of creative labor nor to the impossible-to-quantify worth of the human hand in art, opening us up to ideas that AI can only provide a simulacrum of. We don’t know what will happen to people whose livelihoods, both financially and psychically, depend on creating art for others that can easily be replicated by these tools. But we have a pretty good guess. Illustrators are already furious with AI tools that have stolen, mimicked, and devalued their work. “There’s already a negative bias towards the creative industry. Something like this reinforces an argument that what we do is easy and we shouldn’t be able to earn the money we command,” one artist told the Guardian. The Writers Guild is currently pushing to ban AI-generated work in its next contract, underlining the need to safeguard artists from potentially career-destroying tools not only by evolving cultural norms, but with policy. It’s going to be a wild few months, and hopefully we’ll get to see more Balenciaga Harry Potters — fun, inventive videos meant for little else than silliness — than creepily realistic images of public figures wearing expensive puffer jackets that send the entire media apparatus into an absolute tailspin. This column was first published in the Vox Culture newsletter. Sign up here so you don’t miss the next one, plus get newsletter exclusives. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? Black Mirror’s big AI episode has the wrong villain The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Review: Black Mirror episode “Joan Is Awful” takes on AI — but misses the mark - Vox"

"https://www.vox.com/culture/2023/6/23/23770239/black-mirror-joan-is-awful-review-ai-annie-murphy-salma-hayek"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Culture Technology TV Black Mirror’s big AI episode has the wrong villain You’re OK, Computer — it’s the corporations that aren’t. By Rebecca Ackermann Jun 23, 2023, 8:00am EDT Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: Black Mirror’s big AI episode has the wrong villain Reddit Pocket Flipboard Email Joan (Annie Murphy) isn’t nearly as awful as a computer that steals lives. Nick Wall/Netflix Part of Black Mirror , TV’s best-crafted tech-dystopian anthology series, is back with a sixth season, just in time for a new wave of horrifying real-world concerns: crypto crashes, data breaches, and, most urgently, a horde of capitalists foaming at the mouth to replace human labor with generative AI. The first episode of the season, “Joan Is Awful,” takes on this trend toward automation within the entertainment industry in particular, a concern the Writers’ Guild of America (WGA) have been protesting through their ongoing strike , with the Stage Actors’ Guild (SAG-AFTRA) poised to join them. Over the last decade, streamers have tilted industry development and payment standards toward unsustainable volumes of content for watchers and unsustainably low wages for writers. Now industry executives are staking claim to actors’ voices , writers’ stories , and user data for future automated entertainment too. Netflix , the industry-defining streaming service that airs Black Mirror (and outbid the network that originated the series for that right), is one of the biggest targets of the strike — and Black Mirror ’s latest season takes aim at the streamer, too. Black Mirror lobs sideways shots at Netflix in a few episodes, but the target in “Joan Is Awful” is direct and timely; a distinctively red logo-ed service called Streamberry uses a glittering quantum computer to transform a generative AI thought experiment into TV programming, ruining lives along the way. But while the episode does a humorously vivid (and star-studded) job of imagining a future where anyone’s life could become IP for prestige TV, and any actor’s face (and less ready-for-primetime parts) could be contracted as digital puppetry, the show’s usually incisive arrow ultimately misses the heart of the issue. Streamberry’s “Quamputer,” as the AI machine is named, holds the blame for the episode’s disasters, and destroying its magic light show yields a happy ending. In the real AI story, however, the villains are human, not miraculous machinery — which is exactly why so many writers and actors are counting on collective action to make a difference. The episode, written by Black Mirror creator Charlie Brooker, sidesteps the fact that it’s tech, media, and entertainment industry executives who are choosing a Black Mirror -esque future for us all, not some faceless computer. Any satisfying conclusion to this concern will be the result of human, not technological, transformation. In “Joan Is Awful,” Joan ( Schitt’s Creek ’s Annie Murphy) discovers she’s become the main character of the day writ large: Streamberry has created a show based on her life, starring an AI-generated Salma Hayek (played by the real Hayek), whose likeness the company has contracted from the actress. Each episode airs shortly after Joan’s real day, turning her secrets into plot points and her screw-ups into laugh lines. As a result, Joan’s life falls apart and she attempts to gain Hayek’s attention so they can leverage the star’s power to shut down the series. It works, to a point: After Joan makes a disgusting scene that Hayek’s digital version is compelled to repeat, Hayek commands her lawyer to get her out of the Streamberry contract. But the star’s agreement is ironclad (page 39, paragraph 8 includes all acts up to and “beyond defecation”), as are the user terms and conditions that allowed Streamberry to make content out of Joan’s life events in the first place. If this story is a whodunnit, the company’s lawyers and executives have blood on their hands — but they remain offscreen. There’s nothing cutting-edge about a deal with the devil. (In fact, the last episode in the season, “Demon 79,” set in the late 1970s, begins with just that biblical contract.) Black Mirror gets that part right. At Streamberry’s headquarters, things are not quite as they seem. Nick Wall/Netflix When Joan and Salma Hayek arrive at Streamberry headquarters, they find their way into the computer room, where a beautifully Apple-styled and sized “Quamputer,” or quantum computer, is running the show. Joan grabs a handy ax to smash the computer, and turtlenecked Streamberry CEO Mona Javadi (Leila Farzad) begs for mercy for the artificial lives and shows that would evaporate without the machine’s fairy dust. (“We don’t know how it works!” she screams. “It’s basically magic!”) Joan destroys the machine anyway, freeing herself and all the generated Joans contained within. Skipping a couple of twists, the episode ends with Joan in a new job and a new life, content to figure out how to be the protagonist of a much smaller story. It’s a hopeful conclusion and a human one, in line with the rest of the new season of Black Mirror , which offers the unmistakable impression that Charlie Brooker is as sick of writing about tech’s dark reflection as the rest of us are of living in it. But what about that Streamberry CEO? What about the system that compelled her to delegate creativity to ones and zeros? In the episode, Javadi tells a cowed reporter that the machine prefers negative storylines to positive ones for higher engagement. But who pressed the button to operationalize that strategy in “Joan Is Awful”? (We know who made an eerily similar choice in the real world : Facebook’s and Twitter’s executives.) Brooker has said that when it comes to AI, “ you can’t put the genie back into the bottle. ” In “Joan Is Awful,” smashing one glass iBottle seems to fix the problem. Won’t the fictional CEO and others like her rebuild the same tech with the same goals for the same paying customers? AI is made of people. So why are the people in power let off the narrative hook? In real life, the move toward AI wasn’t triggered by a serendipitous technological discovery like a “Quamputer,” and it hasn’t been deterred by a single point of failure, either. Corporations and research institutions have been working on machine learning and large language models for decades , and the decision to pour more money into AI development is a business one. The bet is that AI will increase productivity, scale markets, and decrease costs enough to justify an estimated $154 billion in global spending on AI by the end of 2023. Prominent AI researcher Timnit Gebru has called the current AI craze a “ gold rush ” and argued that the industry needs better regulation to escape the controlling “profit motive” powering development. A machine that can generate personalized content for every person on the planet is not magic; it’s what happens when tech advancement meets late-stage capitalism. But Black Mirror ’s “Joan Is Awful” is uncharacteristically silent on that distinction. Of course, Charlie Brooker can’t solve capitalism. A high-budget show paid for and hosted by the second-largest streaming service in the US cannot bring down generative AI or deliver a win to entertainment industry unions. But popular art does play an essential role in the cultural conversation about technology and its all-too-human puppet masters. For over a decade, Black Mirror has been one of our sharpest critics of the dark side of innovation, sparking discussions around technology’s influence on politics, creative industries, personal privacy, and society’s shifting moral lines. Through Black Mirror ’s sensitively drawn portraits of people and relationships trapped in crises of faith, the show’s title — a reference to the way a screen, be it smartphone, tablet, computer, or television , looks in the off position — has even become cultural shorthand for the unsettling sensation of living in a future not quite designed for the more complex realities of the human condition. Since the show first aired in 2011, the tech industry has only grown in power and influence, as companies embed technology even more profoundly into our culture and economy. (For context, Uber launched in 2011, Zoom in 2012, Doordash in 2013. Apple released the iPad in 2015, and Google put out the Google Home in 2016.) Today, AI might be the most pressing industry concern — but not because the singularity is on its way, as many AI thought leaders warn. Murphy, who portrays Joan in “Joan Is Awful,” recently said it “hurts her guts” that “we are alive in a time when people are having to ask and beg for their jobs ... not to be replaced by computers.” It’s the begging that’s gut-twisting, not the computers. And it’s the humans hearing those pleas who are turning the knife. That’s a Black Mirror tale if I ever heard one. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via The rise of artificial intelligence, explained How does AI actually work? 4 What is generative AI, and why is it suddenly everywhere? What happens when ChatGPT starts to feed on its own writing? The exciting new AI transforming search — and maybe everything — explained The tricky truth about how generative AI uses your data How is AI changing society? 18 What the stories we tell about robots tell us about ourselves Silicon Valley’s vision for AI? It’s religion, repackaged. What will love and death mean in the age of machine intelligence? What if AI treats humans the way we treat animals? Can AI learn to love — and can we learn to love it? The ad industry is going all-in on AI The looming threat of AI to Hollywood, and why it should matter to you Can AI kill the greenscreen? What gets lost in the AI debate: It can be really fun How unbelievably realistic fake images could take over the internet Robot priests can bless you, advise you, and even perform your funeral AI art freaks me out. So I tried to make some. How fake AI images can expand your mind AI art looks way too European An AI artist explains his workflow What will stop AI from flooding the internet with fake images? You’re going to see more AI-written articles whether you like it or not How “windfall profits” from AI companies could fund a universal basic income Show More Is AI coming for your job? 7 AI is flooding the workplace, and workers love it If you’re not using ChatGPT for your writing, you’re probably making a mistake Maybe AI can finally kill the cover letter Americans think AI is someone else’s problem Mark Zuckerberg’s not-so-secret plan to join the AI race The hottest new job is “head of AI” and nobody knows what they do Why Meta is giving away its extremely powerful AI model Should we be worried about AI? 10 Four different ways of understanding AI — and its risks AI experts are increasingly afraid of what they’re creating AI leaders (and Elon Musk) urge all labs to press pause on powerful AI The case for slowing down AI Are we racing toward AI catastrophe? The promise and peril of AI, according to 5 experts An unusual way to figure out if humanity is toast How AI could spark the next pandemic AI is supposedly the new nuclear weapons — but how similar are they, really? Don’t let AI fears of the future overshadow present-day causes Who will regulate AI? 9 The $1 billion gamble to ensure AI doesn’t destroy humanity Finally, a realistic roadmap for getting AI companies in check Biden sure seems serious about not letting AI get out of control Can you safely build something that may kill you? Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI Scared tech workers are scrambling to reinvent themselves as AI experts Panic about overhyped AI risk could lead to the wrong kind of regulation AI is a “tragedy of the commons.” We’ve got solutions for that. The AI rules that US policymakers are considering, explained Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Have We Reached Peak Smartphone? | WIRED"

"https://www.wired.com/story/gadget-lab-podcast-584"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Early Black Friday Deals Best USB-C Accessories for iPhone 15 All the ‘Best’ T-Shirts Put to the Test What to Do If You Get Emails for the Wrong Person Get Our Deals Newsletter Gadget Lab Newsletter WIRED Staff Gear Have We Reached Peak Smartphone? Photograph: Lanna Apisukh/Bloomberg/Getty Images Save this story Save Save this story Save Phones have been pretty boring for a long time. Don’t get us wrong—phones are still amazing little devices! It just feels like we haven’t seen any truly innovative phone designs or new standout features in a long while. This year’s phone looks and works a lot like last year’s phone. Your phone looks and works a lot like my phone. Have phones actually plateaued, leveled off, or chilled out? Is their transition from fetish object to commodity complete? The perfectly fine boringness of phones gets thrown into focus every time a new handset is launched into the world. This week, we saw the debut of the newest Samsung Galaxy devices. WIRED staff writer (and our podcast's producer) Boone Ashworth joins us to talk about those new phones, and phones in general, and how breathtaking and bland they all are, all at once. Read our roundup of everything Samsung announced at Galaxy Unpacked 2023, including three new Galaxy phones and five new laptops. If you want to preorder a Galaxy device , we have some buying advice for you. Last year’s model is also just great. Read Lauren’s story about safely buying a used phone. Boone recommends Barbarian , which you can watch on HBO Max or rent elsewhere. Mike recommends Sichuan Gold hot sauce from Fly By Jing. Lauren recommends the HBO documentary Navalny. Boone Ashworth can be found on Twitter @ BooneAshworth. Lauren Goode is @ LaurenGoode. Michael Calore is @ snackfight. Bling the main hotline at @ GadgetLab. Our theme music is by Solar Keys. You can always listen to this week's podcast through the audio player on this page, but if you want to subscribe for free to get every episode, here's how: If you're on an iPhone or iPad, open the app called Podcasts, or just tap this link. You can also download an app like Overcast or Pocket Casts, and search for Gadget Lab. If you use Android, you can find us in the Google Podcasts app just by tapping here. We’re on Spotify too. And in case you really need it, here's the RSS feed. Lauren Goode : Mike. Michael Calore : Lauren. Lauren Goode : Mike, when is the last time you felt compelled to buy a brand-new smartphone? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : I think it was 2018. Lauren Goode : So that was about 17 years ago at this point? Michael Calore : Feels like it. Yeah. Lauren Goode : Why? What at that time made you want to buy a new one? Michael Calore : I had an iPhone 6 Plus. It wouldn't hold a charge anymore. It was 3 years old at that point, and I would charge it and it would die after about 90 minutes. So I was like, "OK, I guess I have to buy a new phone." That was the only reason I really felt compelled to upgrade. Everything else about it was fine, and the features in the new phones that were coming out were just not enticing. Lauren Goode : Well, a lot of people are feeling that way right now because smartphone sales are down, really down. I think we may have reached peak smartphone. Michael Calore : Somewhere, Tim Cook just did 100 extra pushups and vowed to make it not so. Lauren Goode : All right. We're going to talk about exactly that. Well, maybe not exactly that today, but we're going to talk about phones. [Gadget Lab intro theme music plays] Lauren Goode : Hi, everyone. Welcome to Gadget Lab. I'm Lauren Goode. I'm a senior writer at WIRED. Michael Calore : I am Michael Calore. I'm a senior editor at WIRED. Lauren Goode : We're joined today by the excellent Boone Ashworth, who you normally know as the producer of this podcast, but who's also a staff writer at WIRED and had the pleasure of covering a big smartphone launch event this morning. Boone, welcome to the mic. Boone Ashworth : Hello. It's good to be over here facing this direction instead of the other wall. Lauren Goode : I have a feeling that after this people in our review section of our podcast are going to say, "Bring back Boone. We want more Boone. Boone Ashworth, encore." Michael Calore : I'll be silencing all of those voices— Lauren Goode : Yes. Michael Calore : Deplatforming all of those commenters. Boone Ashworth : Sure. Lauren Goode : Boone, congratulations on your promotion. Boone Ashworth : Thank you. Oh, do I make more money now? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : Shh. Lauren Goode : All right. So later in the show, we're going to talk about that smartphone event I just mentioned, but first, we're going to talk about smartphones in general, because just a few years ago, it might have felt essential to at least consider the latest smartphone because maybe the camera was that much better. The screen was that much smoother and brighter, or the processor was that much more powerful for playing games, or maybe being stuck at home in a pandemic meant that you wanted the best tech that you could possibly get. But things in smartphone land have changed a lot. So earlier this month, the market research firm, IDC, reported that global smartphone shipments plunged in the last quarter of 2022, which was pretty notable because that's a time period that typically includes a lot of holiday shopping. While more than a billion phones still shipped around the world for the entire year of 2022, it was the lowest annual number of smartphone shipments since—wait for it—2013. Michael Calore : Really? Lauren Goode : Yes. So there are obviously a lot of macroeconomic factors to consider. On the demand side, people are feeling the effects of inflation. They might not be as eager to buy new stuff. On the supply side, there are some ongoing supply chain disruptions and phonemakers may be adjusting their shipments because of this weak demand and built up inventory. But there's an element of all this that we at Gadget Lab are uniquely qualified to discuss, which is the phones themselves. What is it about these phones that don't make them as enticing, as you said in the beginning, Mike? So Mike and Boone, have we reached peak smartphone? Boone Ashworth : Well, what more do we really want our phones to do? Not to be a complete curmudgeon coming on the Gadget Lab, but my phone can do just about everything that I want it to do. And this Samsung event, not to get to the part we're going to talk about later too quickly, but they touted a bunch of new camera features and whatnot. But I'm not filming cinematic movies on my phone anytime soon. Maybe some people are, but it feels like we've gotten to the point where just phones can do everything that I want them to do in my life. I think what I personally have been wanting from my phone is for it to take less of my attention and less of my time; if it could automate some things on the backend to make my life a little easier then I would get something new. But I don't think that we need incredible new hardware to do stuff like that. It's a lot of iterative software changes that I think we're seeing. But the screens are amazing. The cameras are wonderful. Not to limit my imagination too much here, but what more do we want? Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : Yeah. You say you're not shooting cinematic movies on your phone. Boone Ashworth : Not yet. Michael Calore : But you could be shooting cinematic movies on your phone and they would look fantastic. Of course, you don't need a Galaxy S23 to shoot an amazing cinematic movie. If you had a Pixel 3 or an iPhone 11, you could shoot a movie that looks contemporary with what you would get from one of the high-end phones now. I think that's what you're getting at, is that all of the stuff that we have now hardware-wise is fine. To answer your question, Lauren, I think that we have reached peak hardware for sure. We have not yet reached peak software for sure. Lauren Goode : What are the software elements that you are still waiting for? Michael Calore : Well, photo is a good place to look, because whenever we see a new smartphone and they talk about the camera, they spend half the time talking about the optical image stabilization and talking about the lens elements and talking about the different types of sensor technology that they've come up with. Then they spend the other half of the presentation talking about how this new AI chip that they put in their phone is assisting us in taking better photos, better low-light photos, correcting flaws in our photos, blurring old photos, doing all this amazing stuff. That's all software. So I think we are just on the cusp of that stuff becoming incredibly useful and soon it will become indispensable. You won't be able to take photos that look on par with other devices unless you have all that AI stuff crammed into the software that's powering your camera. Lauren Goode : I think we're already there. Michael Calore : You do? Lauren Goode : Yeah, especially at the high end. I don't know if you guys do this, maybe this is a little bit creepy, but whenever anybody texts me a photo, we're just having a text message conversation and they say, "Here's a glimpse of my day. Here's the pastry I just ate," or whatever it is. I go into the metadata of the photo to see which phone they're using. I think that after, let's say, from iPhone 11 to iPhone 12 felt like a pretty big jump. Maybe Pixel 4 to Pixel 5 also felt like a pretty significant jump. Then since then, if someone has an iPhone 12 Pro Max, to me, the photo looks pretty much the same as it does on my iPhone 13 Pro. If you send me a photo, Mike, and you have a Pixel 6— Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : Yes. Lauren Goode : It looks pretty much the same as it would on the Pixel 5. Now granted, there's some compression stuff happening when you're sending stuff via text message, and it also depends like Google Photos, they send you a link to Photos— Michael Calore : Oh, yeah. Lauren Goode : It's really so annoying. Michael Calore : It's so annoying. Lauren Goode : So then you're going into their cloud and there might be some compression happening there. Michael Calore : Assuming you get a pure version of the photo of that. Lauren Goode : Yes, like a raw photo, they all look great. Same with all of the Samsung photos that we're seeing from the high end of Samsung phones, and in some cases some midrange phones too. A lot of that is happening through computational software. It's not necessarily based in the sensor size, although that plays into it too. So I personally just think we're already there. Even Boone, what you said about how you want us to get to a point where we're using our phones less, how do we do that? Some of that software has already baked into our phones. Companies have been trying digital well-being and screen time and all of that for at least a couple of years now. Boone Ashworth : Oh, I've tried it, and I just don't— Lauren Goode : How well has it worked? Boone Ashworth : Oh, not great for me, just because I don't have the discipline. I know how to turn the timers off, you guys have talked about that before on the show. Lauren Goode : Yeah. Boone Ashworth : I'll have well-being timers come up and I'm like, "Oh, I've been on Instagram for half an hour. Cool. I'm going to turn this timer off." So that's just on me. I don't know. The thing about it, it seems like whenever we're talking about smartphones, we're always talking about the camera and there's been some really interesting upgrades. All the stuff they announced at the Samsung event today was a lot of cool stuff. The astrophotography, I would love to take a decent picture of the moon for once in my life. That's a cool feature to have. Things like real tone to get people's skin tones right in photos, those are really cool adjustments or advancements, I guess. It just feels like I want something more. If you're going to pitch me a new $1,200 smartphone, I want something more than just camera updates. If you're trying to make the case for why I should upgrade my two-year-old phone or whatever to a brand-new thing, it's got to be more than just, I can make slightly cooler pictures. Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : Right. Right. Yeah, it's—you're due for a battery, or like Mike mentioned earlier, maybe it's storage, increases in storage. You realize that you're one of those people who needs a terabyte now. Another factor that I think is part of the whole dip in the smartphone market in general is that the secondary market has gotten really good. We've written before it at WIRED about companies like Back Market. I was a little ahead of the curve, guys. I was writing this for WIRED back in 2018 about how to safely buy a used smartphone so you don't get scammed. You can find some really great secondhand smartphones out there now. The manufacturers themselves are offering better resale programs, like Samsung and Apple. Michael Calore : Last year's phone is amazing. Lauren Goode : Right. Michael Calore : It's fine. Lauren Goode : For a lot of people, it's not just good enough. It's better than good enough. Michael Calore : Right. Boone, to go back briefly to something that you were just saying. With phones showing off the camera before everything else, I think it's because everything else has already passed that threshold. If the battery lasts all day, if your screen refresh rate makes it so that everything just looks smooth and wonderful, and if the industrial design feels modern, then those are things that you don't notice, they just are. Whereas, a camera, because it's visual information and because it's very personal, like when people take photos, usually they're very personal mementos, it's something that you form a stronger emotional reaction to. So if it's not perfect or if it doesn't make you feel good, then it's something that is going to turn you off from the phone. Right? Boone Ashworth : So it's our fault then. We're kind of ingrates, 'cause the fact that our phones just last ... I have a Google Pixel 6 or whatever, it lasts two days. I just take that for granted. There's all this kind of stuff that smartphones have gotten to this point where the things are so good that they actually work that, that you have to throw out the flashy camera stuff because everything else, we're just like, "Oh yeah, I know it lasts for four days, or it has whatever crazy battery life," or, "I can drop it from a meter and have it land on concrete and it's fine." We've gotten used to that. So yeah, maybe I'm just spoiled. Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : The camera can always be better. Boone Ashworth : Oh, sure. Michael Calore : It can always be better. It can always strike more to the core of your being than a battery life can. Boone Ashworth : See my soul. Michael Calore : Exactly. Lauren Goode : Have you guys read about the rumored iPhone 16, which is not the next generation, it's the generation after that, that supposedly is going to have a periscope camera? Michael Calore : Yes, I did hear about this. Lauren Goode : When I picture this, I picture it's a phone that's like a little motorboat. You're in the water with it and you're underwater with it because its underwater rating is so good at that point, and there's just a tiny little periscope that sticks up from the top, above the surface. It's like a submarine, but a phone. Michael Calore : I'm not sure that's what they mean. Lauren Goode : No, it isn't. Mike, tell us what it means. Boone Ashworth : That's adorable. Michael Calore : A periscope camera is a camera that uses a tiny prism inside the camera to move the light from the lens onto the sensor. Instead of in a normal camera design, the light goes through the lens and hits the sensor pretty much directly. A periscope camera increases the focal length, which is a very nerdy ... It's a good thing to have increased focal length or to have more control over your focal length, because then you can have more control over the different elements of your photo. Boone Ashworth : I take it all back. That's what phones need, prisms. Michael Calore : Yeah, more prisms. Lauren Goode : Prisms. Michael Calore : More prisms. Lauren Goode : Yeah. Michael Calore : I'm just picturing the Dark Side of the Moon logo. Lauren Goode : Spy cams. Michael Calore : It is the 50th anniversary of Dark Side of the Moon. Boone Ashworth : Oh, happy anniversary? Michael Calore : That would be fitting. Boone Ashworth : Look, I'm saying if we want to turn this into a Pink Floyd podcast, I'm completely down. Let's just do this for two hours. Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Michael Calore : Me too. Me too. Lauren Goode : All right. Well, we have to take a quick break. When we come back, we'll be discussing Dark Side of the Moon. Michael Calore : Episode One: 1965–1966. Lauren Goode : We'll be right back. [Break] Lauren Goode : Despite the global decline in smartphone shipments, Samsung is still number one. It holds 22 percent of the entire global market. Now, here in the US, we're pretty iPhone-centric, but around the world, Android dominates, and Samsung has established itself at both the high end of the market and with some pretty decent midrange phones. So earlier today, both Boone and I headed over to an event space in San Francisco to see Samsung launch its latest premium phone, which is part of the Galaxy Line. Boone, give people the news. Boone Ashworth : OK. Well— Lauren Goode : That's how I'm going to start every podcast from now on. Give people the news. Boone Ashworth : Awesome. All right. Put on my best newscaster voice. Well, there's three new phones. They're all called the Galaxy S23. There's the S23, the S23 Plus, and the S23 Ultra, which is the big megaphone with, I think, five camera lenses. Lauren Goode : It's a thick phone. Boone Ashworth : Yeah. It was surprisingly light when I held it in the testing area afterward, but I don't know, maybe I'm just not used to phones. Let's see, they're very similar, if you are familiar with the S22, a lot of similar features that have carried over. The Ultra has this new 200-megapixel camera, which is just insane. It has all this raw photo processing and quad pixel technology to make your photos better in low light and better taking astrophotography-type stuff. The other cameras also have three lenses on them. They've got a telephoto lens, a regular lens that has 10X zoom on it, and then an ultrawide, so kind of standard phone stuff. Michael Calore : Does it have a headphone jack? Boone Ashworth : No. Were you surprised to learn that it does not have a headphone jack? Lauren Goode : We should bring that question back in 2023, every single phone launch. Michael Calore : Completely agree. Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Boone Ashworth : Honestly, that's one of my things. If I want phones to get better, just give me a headphone jack back. Give me a headphone jack. Give me a microSD card slot so I can put ... If I want to upgrade to get a new phone to get a terabyte of storage, I'll just put my own little card in there. Anyway— Michael Calore : Samsung stopped putting SD card slots in its phones a couple years ago, and that was very contentious, almost as a contentious move as the removal of the headphone jack. Boone Ashworth : Yeah. Michael Calore : So I watched Unpacked here at the office, a mile and a half away from the actual event, and it felt like most Samsung press conferences, where it was kind of stiff, not really that fun. It lost its steam after about the first 20 minutes, but I'm curious as to what it felt like in the room. Lauren Goode : It's clubby. Michael Calore : Clubby? Lauren Goode : Yeah. So Samsung events are always clubby. They have very dark, dramatic lighting. It's a lot of unts, unts, unts, unts— Michael Calore : Oh, you mean clurbby? Lauren Goode : Yeah, like clurbby. By the way, about the event space that we were at, I have a question for you, Mike. Michael Calore : Yeah. Lauren Goode : How do you pronounce where we were? Michael Calore : The Masonic Auditorium. Lauren Goode : See, he says Muh-sonic. We were having this conversation with Alicia Cocchi, our social video producer, who also joined us at the Samsung event today. She says her partner calls it the Muh-sonic, and she asked me and I said, "No, it's the May-sonic." She says, "May-sonic." Then our Uber driver said, "Muh-sonic." Michael Calore : Yeah. Lauren Goode : So now we're thinking it's actually divided along gender lines. Boone Ashworth : I say it's Moo-sonic. Lauren Goode : Every guy— Michael Calore : The Mason— Lauren Goode : Yeah, Boone just kept going, "The Moose!" Michael Calore : The Masons are like a patriarchal organization, aren't they? Lauren Goode : Well, but even what you just said is Mason. Michael Calore : Yeah, and there's Mason Street— Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : The Masonic— Michael Calore : ... and it's a Mason Hall— Lauren Goode : So it's the Masonic. Michael Calore : But when you talk about the organization, it's Masonic. Lauren Goode : That sounds like Messianic. Michael Calore : English is weird. OK? Lauren Goode : All right. Well, anyway, how did you think the Masonic felt today, Boone? Boone Ashworth : Oh, it's so different being on this side of the mic. I can't just be like, "Stop! Retake!" Well, I thought it was definitely one of the top two tech events that I've ever been to, I think. Michael Calore : How many have you been to? Boone Ashworth : Two. So this was the second event. The first one that I went to was Samsung Galaxy Unpacked in February of 2020. That was my first actual tech event. I was like, "OK, this is what these are like," and then— Lauren Goode : Boone said, "Do they take your temperature at every tech event?" Boone Ashworth : Yeah. Michael Calore : Yeah. Boone Ashworth : For some reason, there weren't a lot of them over the past three years. So now back at this one, honestly, there was less people there than I expected it. It was loud, and I don't know, it was a tech event. It was a big infomercial. I kept finding myself when I would zone out and then everybody would start clapping, I would start to clap and then I'd just like, "Nope, I don't work here. What am I doing? Why am I clapping for these people?" So— Lauren Goode : Yeah, there's a— Boone Ashworth : ... tech events are weird. This is one of the first podcasts that you actually let me on, and we talked about how weird it was, and I don't think my opinion has changed very much. I still think they're strange or just a fundamentally weird thing. Lauren Goode : The presentation itself was a very clean 59 minutes. In that time, they not only discussed the new Samsung Galaxy phones, but also a couple of new laptops and some sustainability initiatives. They brought on Google, their software partner, and they talked a little bit about AR and VR. Of course, they talked about their partnership with Qualcomm because it's Qualcomm chips that are powering these new phones. That's a lot of ground to cover in just under an hour. So you're only really getting high-level updates, and it's very easy to feel as though you've heard it all before. They show the different cores of their neural processing unit in this graphic on stage, and they're saying how it's enabling all of these artificial intelligence features. Look, here's a sliding tool that shows you the before-photo and the after-photo, and it's slightly brighter. It might as well be 2020–2021 smartphone event. You really need to dig down deeper or talk to some experts in these fields to get a sense of what is new. Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Boone Ashworth : It feels like everybody's just waiting it out until they're mixed reality headsets are out. There's all these Apple rumors about Apple's new headset coming out. It seems like Samsung is also keen to be making a headset by bringing Qualcomm and Google having that partnership. They talked about wanting to make a mixed reality wearable something, so it seems like that's coming. I think companies are, they seem to be very aware of that, both Apple and Samsung and Google. I think they know that their phones are having iterative updates and they need something else. They need another form factor to get people excited again. I think they’re putting a lot of eggs into the VR basket. That feels like where we are right now, is we're just waiting until they're finally like, "OK, here's our VR headset that actually works and doesn't make you look stupid." Michael Calore : Yeah. Boone Ashworth : Are we going to get there? I don't know. Michael Calore : This happens a lot. I think whenever there's an impending Apple announcement. The same type of thing happened around when the iPad was coming and everybody knew the iPad was coming. Then a couple months before the iPad came, there were all these tablet announcements and people talking about things that they're ... They're planting their flag, basically saying, "We're not going to be left behind in this race. We are here and we are ready. We just don't have anything to show you yet because there's no hardware." Boone Ashworth : Samsung did that a bit too. It felt very Apple-y. They had Ridley Scott, famous filmmakers, filming videos on the ultra phones and whatnot. Their new laptops and the phones sync together so you can drag and drop and copy and paste from your phone onto your computer, which feels very Apple-y. Samsung went in on its ecosystem a little bit, or at least was like, "Hey, trying to make the case for you to get both a Galaxy phone and the ultra laptop so that they could all work together." So they're definitely doing the Apple-y type thing. I think maybe when a headset comes out, see how closely aligned they are there too. Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : As you were saying that, when you said, "Oh, they had Ridley Scott make a movie," my brain went to Jon Chu, because John Cu made a movie for iPhone, or on the iPhone a few years ago, and we covered that for WIRED. Then when you said, "Oh, and they're showing people dragging and dropping and starting an application on their phone, their Galaxy phone, and then opening it on their Samsung tablet," I thought, "Oh, continuity, like on iPhone and Mac. So in that sense, the feature set felt very similar to what Apple might have announced. Michael Calore : I think feature parody is a good thing because then people can not really feel a lot of pressure to upend their life and switch operating systems. It's also, it's nice to know that if the other person has something fancy, you're also getting something fancy. I think the problem is that when these things start to overlap and they start working cross-platform, then all of a sudden you have too many choices. I was really struck by the commercial that they showed right in the middle. So the way these events go, they'll talk for a bit and then they'll show you what is basically a television commercial and then talk about the product. It was, "Can you send me that?" Lauren Goode : Oh, yes. Michael Calore : "Can you send me that?" Lauren Goode : Right. Michael Calore : Where it was people interrupting concerts to find the woman in the crowd holding the Galaxy S23 Ultra because they know she has the best photo, and they say, “Can you send me that?" Lauren Goode : Right. Michael Calore : And she's like— Lauren Goode : To the couple proposing— Michael Calore : Yeah. Lauren Goode : The guy proposing marriage, and he turns to the woman who happened to capture the photo and said, "Oh, could you send me that?" Michael Calore : Yeah, Yeah. Lauren Goode : It's cute. Michael Calore : Yeah, it was cute. But at the same time, they're showing you their big innovation, which is file sharing between Samsung devices. So now you just have another way to share photos between different devices and there are 16 other ways to do that. So things like that, that feels like it's cool that your stuff works together, but at the same time, there were all these little innovations that were not really innovations because they're things that already exist in Android or already exist in just cloud computing. For example, the security dashboard, they made a big show of the security dashboard in Samsung’s— Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : You can bring your phone to a repair tech and basically shut down part of your phone, so whoever's working on your phone can't see your personal information or even whatever apps you've downloaded, like which banking app you're using. Michael Calore : Yeah, it's like a valet key for your phone, and that's cool. But also the digital well-being tools, which we just talked about, those are in every phone, so that's not necessarily as innovative. Lauren Goode : One thing we should talk about really quickly is the smart home, because one of the areas in which Samsung really stands out from Apple and Google is in the home. It makes a lot of home appliances. Several years ago, it acquired the SmartThings smart home company and still uses that brand to launch new products. Mike, talk about what we saw today. Michael Calore : The thing that we saw today, which was just hinted at, was something that was announced at CES a couple of ... oh geez, I almost said a couple of months ago. It was literally three weeks ago, I sat in the room and watched Samsung announce the SmartThings charging station. So it's a wireless charger and it sits next to your bed or next to your couch. You put your phone on it and it starts charging your phone, but it also sends a signal out to all of your smart home stuff. You can program any kind of routine into this that you want. But the idea is that you put this thing somewhere where, when you sit in that seat, it means you're ready to chill out, you're ready to go to bed, you're ready to sit down and watch a movie. You're ready to not be on anymore because you're putting your phone down to charge and you're not paying attention to it anymore. So the recommended routine is that you put your phone on the SmartThings hub and it sends out these signals to your smart home to turn the lights down, turn on the— Lauren Goode : Does it do it in that voice? Michael Calore : Yeah. Turn on the smooth jazz station, lower the temperature in the room a little bit, or raise the temperature in the room a little bit, whatever your preferred routine is for your chill out, maybe turn on your TV and start Netflix or whatever. So that's interesting because that's a vision of the smart home that people have been talking about for literally 30 years. Ambient computing, it just takes one very simple signal from the human and then does all this stuff in the background. Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : That's amazing. Michael Calore : Yeah, it is. Boone Ashworth : That's basically what I was saying earlier, is I just want to be able to set my phone down and have it do stuff for me. Michael Calore : Yeah. Boone Ashworth : Like yeah, that's great— Michael Calore : Yeah. Boone Ashworth : If it works. Michael Calore : Yeah, it probably will because SmartThings is a very robust product ecosystem on its own. There are a lot of SmartThings thermostats and lights and stuff like that, and also Matter, the standard is adopted by all the big names, so it should just work. Lauren Goode : So what I'm gathering from this episode of Gadget Lab is that we have reached peak smartphone, but we do think there's a post-smartphone future in AR/VR and the smart home. Michael Calore : Yes. Lauren Goode : Watch this space. All right. Well, all of our coverage from today's event is on WIRED.com as well as WIRED's Instagram and Twitter page, where you can see videos of the excellent Boone Ashworth in action, hands-on with the phones. We're going to take a quick break, and when we come back we'll do our recommendations. [Break] Lauren Goode : Boone, as our guest of honor and producer extraordinaire, what's your recommendation? Boone Ashworth : I would like to recommend the movie Barbarian. It is a new movie, it came out in 2022. It's currently available on HBO Max, and I just watched it last weekend, and it is quite good. It is very strange and messed up. It's a horror film. It's directed by Zach Cregger, one of the guys from the early 2000s sketch group, Whitest Kids U' Know. There's this real interesting reinvention happening where comedy people are making horror movies, like Jordan Peele. You should also watch all of Jordan Peele's movies 'cause they're amazing, and this is a new one. On that front, it's like, without giving anything away, it's basically a horror movie about an Airbnb gone wrong. I have to say, I saw the preview for this movie and I was just not interested in it all. It looked like a schlocky, I don't know, horror movie that just had a bunch of jump scares in it, and it's like, "Oh no, they go into a creepy underground basement," or whatever. Like, "I feel like I've seen that before." I promise you, you have not seen this one before. It is very weird and very funny, but— Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : Who's in it? Boone Ashworth : It's starring Georgina Campbell. One of the Skarsgårds is in it. Lauren Goode : I'm in. Boone Ashworth : Justin Long is in it. Lauren Goode : Oh, wow. Michael Calore : Oscar-worthy performance from Justin Long. Lauren Goode : Wait, which Skarsgård? Boone Ashworth : Bill, Bill Skarsgård. Lauren Goode : Bill the father. Is that the father? Boone Ashworth : No. Lauren Goode : Or is it the brother? Boone Ashworth : The father is Stellan. Lauren Goode : Oh, right, right. There was that Onion headline recently— Boone Ashworth : There are like 18 of them. Lauren Goode : ... that was like, "Nordic actor forgets which Skarsgård brother he is." Michael Calore : Yeah. Lauren Goode : Yeah. OK. Michael Calore : Yeah, very, very true. Boone Ashworth : Anyway, highly recommend this movie. It very much has the trope of, you're going to be shouting at your TV screen like, "Why are you going in there?" Michael Calore : But the little bit of suspension of disbelief and then the movie takes several turns that I was not ready for. Boone Ashworth : I completely agree with you. I love horror movies, and I went into it thinking it was just going to be like, "OK, here's another horror movie." It is far from just another horror movie. Michael Calore : Yeah. Yeah. Boone Ashworth : I know that it did not receive universal praise, but I think those people are just spoiled sports and they don't enjoy fun. Michael Calore : It is not a perfect movie, but it was a lot of fun. It was a good time, so— Boone Ashworth : One of the better horror movies I've seen in the past decade, and not a bunch of cheap jump scares. I don't like horror movies, but they're just like, they throw a thing at you. I like it when they build this horrifying sense of dread, and there was some really horrifying stuff in this movie. Lauren Goode : Boone, thanks for that recommendation. I'll check it out, but maybe just not before bedtime. Mike, what's your recommendation? Michael Calore : Something to go with your watching of late-night horror movies right before bedtime. Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Lauren Goode : OK. Michael Calore : Some hot sauce. Lauren Goode : Hot sauce? Michael Calore : Yeah. Lauren Goode : Actual hot sauce. Michael Calore : Actual hot sauce. I tried this hot sauce recently. My lovely wife bought it for me for my birthday. It's called Sichuan Gold, and it's by the company Fly by Jing. Fly by Jing makes a lot of really great Sichuan sauces. They make Sichuan chili crisp. They make a mala powdery spice mix that I use all the time. This is basically a hot chili oil, so it has the numbing spicy Sichuan peppercorns, and then it has very hot regular peppers, hot peppers in it. So you get the heat and you get the numbing and it's delicious. Lauren Goode : What have you used it with? Michael Calore : I put it on just about everything. Well, also, I should mention that I only eat foods that serve as delivery vehicles for hot sauces— Lauren Goode : Right, we know this about you. Michael Calore : ... which is why I'm not a big soup guy, but you can have a good spicy soup, but it's not nearly as good as a bagel with hummus on it. I make a lot of tofu rice bowl kind of dishes. I put it on that. I put it on some vegan mac and cheese. It's just delicious on anything vaguely Asian or anything with a lot of umami flavor. It really just gives it a nice kick. Lauren Goode : Where can people find it? Michael Calore : You can buy it online. It's a small company, so they don't have great distribution, but you can get it in a lot of specialty food stores like your fancy grocery store, maybe not like your Safeway or your Vons or your Albertsons or whatever people have not in California, but you can also just order it online. I think it's $14 for a bottle to get it shipped to anywhere in North America. Lauren Goode : Excellent. Boone Ashworth : Nice. Michael Calore : Yeah, I don't know. It's— Lauren Goode : It's a hot recommendation. Michael Calore : Thank you. It comes from the show Hot Ones, First We Feast. Do you know this show? It's fantastic. It's one of the best talk shows ever. It's on YouTube and the host and the guest sit down and they eat progressively hotter chicken wings while the host asks the guest questions about their career. Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Boone Ashworth : We should do that here. We should do that on this show. Michael Calore : Well, I think they've already cornered it, but— Boone Ashworth : OK, fine. Michael Calore : I would be open to that. I absolutely would. Lauren Goode : I really like this emerging genre of YouTube series that have to do with chicken or chicken shops. Is it YouTube? I don't know. There's the Chicken Shop Date woman? Michael Calore : Yep. I think she's on TikTok? I don't even know. Lauren Goode : Love her series. It might be TikTok. I think I've seen it on Instagram too. It's fantastic— Michael Calore : It's all just screen. I stopped saying on film and on television. I just say, "I saw this thing on screen other day." Lauren Goode : Yeah, it depends on if it's a 50-inch screen or a 6-inch screen. Michael Calore : You just set your phone down and it all starts playing. Lauren, what is your recommendation? Lauren Goode : My recommendation is also somewhat in the category of horror films on HBO Max. The show is not sponsored by HBO Max. I recommend checking out Navalny , a documentary that is nominated for an Oscar. It is currently streaming on HBO Max. It was made in conjunction with CNN Films and it is about the Russian opposition leader who was poisoned by the Kremlin a few years back, survived miraculously rehabilitated in Germany, and then upon his return to Moscow was promptly arrested again and is currently in jail in Russia. But he's a really, really compelling figure. One of the more interesting parts of the documentary I found as a journalist is that during the time that he is rehabilitating with his family and some of his business associates, his campaign associates, in Germany, he is on a mission to find out who poisoned him. He decides to work with Bellingcat, which is this group of really obsessive data journalists who help him pinpoint exactly who was behind the poisoning, which he suspects is the Kremlin or people associated with the Kremlin and Putin, but wasn't able to prove until he teamed up with Bellingcat. Watching their process is really interesting. I just found it to be a super fascinating documentary and I very much recommend checking it out. Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Gear You’ll Be Able Buy Cars on Amazon Next Year Boone Ashworth Gear The Best USB Hubs and Docks for Connecting All Your Gadgets Eric Ravenscraft Gear The Best Black Friday Deals on Electric Bikes and Accessories Adrienne So Boone Ashworth : That's awesome. Yeah. Lauren Goode : So that's Navalny on HBO Max. Michael Calore : Watch it after Barbarian as a palate cleanser. Boone Ashworth : Yeah, good double. Lauren Goode : Yeah, I guess suppose it is a palate cleanser, although it doesn't leave you— Michael Calore : After that movie, it would be appetizing. Lauren Goode : Yeah, maybe it would be. I don't know if I'd call it quite that, but not incredibly uplifting. Michael Calore : Sure. Lauren Goode : Yeah. All right, well, that's our show for this week. Thank you, Boone, for joining us. Boone Ashworth : Yeah, thank you for having me. This was great. Lauren Goode : This was super fun. We're going to send you to a smartphone event every week. Boone Ashworth : Oh, thank god. Lauren Goode : Well, maybe if it really is peak smartphone, there won't be a smartphone event every week. Michael Calore : Yeah. They're all going to hear this show and then they're going to say, "That's it. We're not doing the events anymore." Boone Ashworth : "We're done. We're done. We quit. They convinced us." Michael Calore : "Enjoy your 6-year-old batteries, suckers!" Boone Ashworth : "We'll talk to you in five years when we have a VR headset." Lauren Goode : Thanks to all of you for listening, especially if you've made it this far. If you have feedback, you can find all of us on Twitter. We're still there, just check the show notes. Our producer is the man behind the mic today, Boone Ashworth. Goodbye for now. We'll be back next week. [Gadget Lab outro theme music plays] You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer. Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Topics Gadget Lab Podcast podcasts Samsung phones Julian Chokkattu Jaina Grey Boone Ashworth Justin Pot Simon Hill Julian Chokkattu Brenda Stolyar Reece Rogers WIRED COUPONS TurboTax Service Code TurboTax coupon: Up to an extra $15 off all tax services h&r block coupon H&R Block tax software: Save 20% - no coupon needed Instacart promo code Instacart promo code: $25 Off your 1st order + free delivery Doordash Promo Code 50% Off DoorDash Promo Code + Free Delivery Finish Line Coupon Take $10 off Your Order - Finish Line Coupon Code Groupon Promo Code Groupon promo code: Extra 30% off any amount Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Artificial Intelligence - Vox"

"https://www.vox.com/artificial-intelligence"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Artificial Intelligence Vox's coverage of how AI is shaping everything from text and image generation to how we live. President Biden’s new plan to regulate AI By Sara Morrison October 31 Why I let an AI chatbot train on my book By Bryan Walsh October 25 How AI will shape our children’s future By Kelsey Piper October 18 Filed under: The rise of artificial intelligence, explained The $1 billion gamble to ensure AI doesn’t destroy humanity By Dylan Matthews September 25 Your AI personal assistant is almost here — assuming you actually want it By Sara Morrison September 23 Stuart Russell wrote the textbook on AI safety. He explains how to keep it from spiraling out of control. By Sean Illing September 20 AI that’s smarter than humans? Americans say a firm “no thank you.” By Sigal Samuel September 19 Google’s free AI isn’t just for search anymore By Sara Morrison September 19 Filed under: The rise of artificial intelligence, explained What if AI treats humans the way we treat animals? By Marina Bolotnikova September 7 Filed under: The rise of artificial intelligence, explained What the stories we tell about robots tell us about ourselves By Constance Grady September 7 Filed under: The rise of artificial intelligence, explained Can AI learn to love — and can we learn to love it? By Alissa Wilkinson September 7 Filed under: The rise of artificial intelligence, explained Silicon Valley’s vision for AI? It’s religion, repackaged. By Sigal Samuel September 7 Filed under: The rise of artificial intelligence, explained What will love and death mean in the age of machine intelligence? By Tahmima Anam September 7 Don’t upgrade your iPhone until you have to By Adam Clark Estes September 7 Is the AI boom already over? By Sara Morrison August 28 AI-discovered drugs will be for sale sooner than you think By Rachel DuRose August 25 Is Zoom using your meetings to train its AI? By Sara Morrison August 9 ChatGPT could make bioterrorism horrifyingly easy By Jonas Sandbrink August 7 Why Meta’s move to make its new AI open source is more dangerous than you think By Kelsey Piper August 2 Filed under: The rise of artificial intelligence, explained The AI rules that US policymakers are considering, explained By Dylan Matthews August 1 Video Something weird happens when you keep squeezing Under extreme pressures, matter defies the rules of physics as we know it. Play video for Something weird happens when you keep squeezing Why everyone hates this concrete building And why brutalism dominates US college campuses. Play video for Why everyone hates this concrete building Sign up for the Vox video newsletter Don’t miss our new video projects, returning series, and opportunities to get involved with our reporting. vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Explainers The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Why bin Laden’s 2002 letter became the latest TikTok moral panic. Filed under: The rise of artificial intelligence, explained How “windfall profits” from AI companies could fund a universal basic income By Dylan Matthews July 28 Filed under: The rise of artificial intelligence, explained Why Meta is giving away its extremely powerful AI model By Shirin Ghaffary July 28 Filed under: The rise of artificial intelligence, explained The tricky truth about how generative AI uses your data By Sara Morrison July 27 Filed under: The rise of artificial intelligence, explained Biden sure seems serious about not letting AI get out of control By Sara Morrison July 21 Filed under: The rise of artificial intelligence, explained The hottest new job is “head of AI” and nobody knows what they do By Rani Molla July 19 Telephone operation was a good career for women. Then it got automated. By Dylan Matthews July 18 Filed under: The rise of artificial intelligence, explained You’re going to see more AI-written articles whether you like it or not By Peter Kafka July 18 Filed under: The rise of artificial intelligence, explained Understand how ChatGPT, Stable Diffusion, and DALL-E are transforming our world — from text and image generation to how we live and work. Filed under: The rise of artificial intelligence, explained An unusual way to figure out if humanity is toast By Dylan Matthews July 10 Filed under: The rise of artificial intelligence, explained AI is a “tragedy of the commons.” We’ve got solutions for that. By Sigal Samuel July 7 Filed under: The rise of artificial intelligence, explained Panic about overhyped AI risk could lead to the wrong kind of regulation By Divyansh Kaushik and Matt Korda July 3 Filed under: The rise of artificial intelligence, explained AI is supposedly the new nuclear weapons — but how similar are they, really? By Dylan Matthews June 29 Filed under: The rise of artificial intelligence, explained The ad industry is going all-in on AI By Shirin Ghaffary June 29 Filed under: The rise of artificial intelligence, explained Scared tech workers are scrambling to reinvent themselves as AI experts By Rani Molla June 28 Filed under: The rise of artificial intelligence, explained Black Mirror’s big AI episode has the wrong villain By Rebecca Ackermann June 23 Filed under: The rise of artificial intelligence, explained How AI could spark the next pandemic By Kelsey Piper June 21 Filed under: The rise of artificial intelligence, explained Four different ways of understanding AI — and its risks By Kelsey Piper June 14 AI automated discrimination. Here’s how to spot it. By A.W. Ohlheiser June 14 Filed under: The rise of artificial intelligence, explained What will stop AI from flooding the internet with fake images? By Shirin Ghaffary June 3 Filed under: The rise of artificial intelligence, explained Why an Air Force colonel — and many other experts — are so worried about the existential risk of AI By Kelsey Piper June 2 Podcasts Helping you understand the most important news in the world, five days a week Go right up to the edge of what we know … and then keep going Embrace uncertainty vox-mark Sign up for the newsletter VoxCare Dylan Scott guides you through the fallout of the Covid-19 pandemic and the health care policies that matter most. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. Pagination Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Meta Teams Up With Microsoft, Qualcomm on Llama 2 AI Large Language Model - CNET"

"https://www.cnet.com/tech/meta-teams-up-with-microsoft-qualcomm-on-llama-2-ai-large-language-model"

"X Black Friday 2023 Live Blog Can You Trust AI Photography? Best TV for 2023 Thanksgiving Travel Times Snoozing Is Fine Solar EV charging 6 Best TV Gifts Tech Money Home Wellness Home Internet Energy Deals Sleep Price Finder more Tech Meta Teams Up With Microsoft, Qualcomm on Llama 2 AI Large Language Model Facebook's parent company launches the second generation of its large language model. Corinne Reichert Senior Writer Expertise News Corinne Reichert July 18, 2023 4:26 p.m. PT 2 min read James Martin/CNET The next generation of Meta's large language model, Llama 2 , is now available for free commercially in a partnership with Microsoft, Meta said Tuesday. Large language models are what power generative artificial intelligence chatbots, like OpenAI's ChatGPT and Google's Bard. Microsoft launched an AI-powered Bing search earlier this year, which makes use of ChatGPT. Under this partnership with Meta, Microsoft will now also offer access to Llama 2 through Azure AI and on Windows , though it will also be offered through Amazon Web Services and other providers. Llama 2 is open source and free to use for research and commercial uses, though you'd have to pay for Microsoft's enterprise hosting service. "We believe an open approach is the right one for the development of today's AI models, especially those in the generative space," Meta said Tuesday. "By making AI models available openly, they can benefit everyone." Meta added that a free, open large language model is also "safer" because more researchers and developers can stress test, find issues and solve problems sooner. Llama 2 on smartphones Qualcomm is also working with Meta to make Llama 2 AI implementations available on phones and PCs starting next year. "This will allow customers, partners and developers to build use cases, such as intelligent virtual assistants, productivity applications, content creation tools, entertainment and more," Qualcomm said Tuesday. "These new on-device AI experiences, powered by Snapdragon, can work in areas with no connectivity or even in airplane mode." Qualcomm's Snapdragon 8 Gen 2 processor powers the Samsung Galaxy S23 series currently, as well as Qualcomm's processors being inside multiple other phone and computer brands. There have now been over 100,000 requests for access to Llama 1 since it was launched in February , Meta said. Editors' note: CNET is using an AI engine to help create some stories. For more, see this post. Computing Guides Laptops Best Laptop Best Chromebook Best Budget Laptop Best Cheap Gaming Laptop Best 2-in-1 Laptop Best Windows Laptop Best Macbook Best Gaming Laptop Best Macbook Deals Desktops & Monitors Best Desktop PC Best Gaming PC Best Monitor Under 200 Best Desktop Deals Best Monitors M2 Mac Mini Review Computer Accessories Best PC Speakers Best Printer Best External Hard Drive SSD Best USB C Hub Docking Station Best Keyboard Best Webcams Best Mouse Best Laptop Backpack Photography Best Camera to Buy Best Vlogging Camera Best Tripod Best Waterproof Camera Best Action Camera Best Camera Bag and Backpack Best Drone Tablets & E-Readers Best E-Ink Tablets Best iPad Deals Best iPad Best E-Reader Best Tablet Best Android Tablet 3D Printers Best 3D Printer Best Budget 3D Printer Best 3D Printing Filament Best 3D Printer Deals More From CNET Deals Reviews Best Products Gift Guide Shopping Extension Videos Software Downloads About About CNET Newsletters Sitemap Careers Policies Cookie Settings Help Center Licensing Privacy Policy Terms of Use Do Not Sell or Share My Personal Information instagram youtube tiktok facebook twitter flipboard "

"Why augmented and virtual reality software engineer is the hottest job in tech - Vox"

"https://www.vox.com/recode/2020/2/11/21121275/augmented-virtual-reality-hiring-software-engineers-hired"

"Vox homepage Give Give Newsletters Newsletters Site search Search Vox main menu Explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters More Explainers Israel-Hamas war 2024 election Supreme Court Buy less stuff Open enrollment What to watch All explainers Crossword Video Podcasts Politics Policy Culture Science Technology Climate Health Money Life Future Perfect Newsletters We have a request Vox's journalism is free, because we believe that everyone deserves to understand the world they live in. Reader support helps us do that. Can you chip in to help keep Vox free for all? × Filed under: Technology Artificial Intelligence Augmented Reality How tech companies are trying to make augmented and virtual reality a thing, again Companies are on a hiring spree for people who can code an alternative reality. By Shirin Ghaffary and Rani Molla Feb 11, 2020, 11:00am EST Share this story Share this on Facebook Share this on Twitter Share All sharing options Share All sharing options for: How tech companies are trying to make augmented and virtual reality a thing, again Reddit Pocket Flipboard Email A doctor in Germany testing mixed-reality glasses for use in cardiology. Jens Kalaene/picture alliance via Getty Images It’s a good time to be a software engineer. And it’s an even better time to be a software engineer who can build virtual or augmented reality. In the past few years, major tech companies like Google, Facebook, and Apple have been investing in virtual reality (VR) and its sibling technology, augmented reality (AR). Google just released a new “Live View” option in its popular Maps app that uses AR tech to superimpose information onto your field of vision as seen through a smartphone camera. We’ve seen similar examples of simple AR use cases, like the Ikea Place app, which works with your smartphone camera so you can see what certain pieces of furniture might look like in your house. Google is also continuing to improve its ARCore platform so that almost any phone can do things like measure depth. Better hardware will undoubtedly unlock a lot of transformative potential for virtual reality — but even more so with augmented reality. Rumors suggest that Apple will release its first AR headset in 2023. Facebook, which sells its own line of Oculus virtual reality headset products, is also betting on augmented reality. Mark Zuckerberg has said he thinks there will be an AR “breakthrough” in the next decade on the technology, and Facebook is investing heavily in the field to be the company to do that. And Microsoft’s new HoloLens 2 is being used for industrial applications like training Airbus cabin crews in virtual airplanes as well as, more controversially , military applications, including helping US soldiers prepare for combat. The rise of AR When it comes to the potential of virtual reality technology versus augmented reality, it’s increasingly obvious that AR is where there’s broader popular appeal. While the reach of VR is limited to gamers who wear headsets, major tech companies see VR as a gateway to more wide-reaching possibilities of AR technology. The idea is that AR can reach widespread adoption in our everyday lives, as it does with the new Google Maps feature. As it stands now, popular AR is app-centric — think Pokemon Go or the Ikea app that lets you envision new furniture in your living room. Both are popular apps, but they’re experiences that you must consciously log into and experience through a smartphone screen. A true AR revolution would be one where the technology seamlessly integrates into our lives without any effort. But the hardware isn’t quite there yet. The gadgets that exist now, like Magic Leap or HoloLens, may be getting closer to the dream of effortless AR, but so far they’ve been proven imperfect for the average human. It should be noted that anticipation for AR’s big breakout moment has been building for the better part of a decade. Google tried to make AR for everyone — or at least those who could afford a $1,000 gadget — nearly six years ago with Glass, a wearable device that put a small display in front of the user’s eye. The product never reached widespread adoption , though the headset has seen some success in enterprise applications. Many think Google Glass was ahead of its time, although the technology wasn’t advanced enough yet to justify wearing a Matrix- looking set of glasses on your head all day. With its focus on design and usability, Apple could revolutionize the AR headset space if it indeed builds a product. Others like Microsoft and Facebook are racing to do the same. Naturally, all these companies are hiring more people to build these new technologies. And now, new data from job-matching site Hired shows just how much these companies have been staffing up. The growth in AR/VR job listings and companies seeking interviews for those jobs took off in the past 12 months; jobs in those categories barely registered on Hired’s radar in previous years. Facebook currently has more than 3,000 jobs on its career page with the term “AR/VR.” Apple, Amazon, Microsoft, and Google have a total of about 1,000, depending on what variations of AR/VR keywords you use. A Facebook spokesperson said it currently employs “thousands” of people who work on AR/VR and plans to move its AR/VR teams to a new campus that will seat approximately 4,000 employees “Demand is outstripping supply,” Hired CEO Mehul Patel told Recode. There’s been a 1,400 percent growth in interview demand for AR/VR engineers in the past year, according to Hired. The company conducted a study that analyzed thousands of listings and companies in its annual state of software engineers report. The overall number of listings has grown exponentially, too. The average salaries for these positions in major US tech hubs range from $135,000 to $150,000. While the growth for AR/VR jobs may seem extreme, Hired said it mirrors the 517 percent annual growth in demand for blockchain engineers in 2018. Last year, however, the demand for blockchain engineers had slowed to 9 percent. But while the blockchain craze may have slowed down, the number of AR/VR projects is only expected to increase in the years to come. In terms of the promise of big growth, software engineers tend to agree. Some 74 percent of those surveyed in Hired’s report said they think we’ll see the full impact of AR/VR within the next 5 years. Meanwhile, plenty of other data points show how the technology industry is betting — and spending big — on AR and VR. An explosion of inventions In 2019, more than 7,000 AR/VR inventions were patented globally, more than in any year to date, according to Derwent , a subsidiary of Clarivate Analytics that keeps a comprehensive database of patent information. (Derwent counts inventions rather than patents because a single invention requires numerous patent documents.) In the 15 years ending in 2017, Microsoft claimed more AR/VR inventions than any other company with 745. Facebook ranked fourth, after Samsung and Huawei. Keep in mind, this data doesn’t yet include the most recent spending growth on AR/VR in the past two years. The role of education Since there aren’t enough engineers who are already proficient in coding for AR/VR to meet the hiring demand, Hired says engineers are increasingly looking to self-teaching methods to broaden their skill set, in addition to seeking out computer science training in school. Across the board, AR/VR was second only to machine learning as the most desired field that engineers in Hired’s survey were most interested to learn about. Stuart Zweben, professor of Computer Science & Engineering at Ohio State University, tracks data on computer science degrees. Zweben told Recode that his data isn’t granular enough to detect whether there’s been a rise in specializations in AR/VR, but depending on the degree program, traditional computer science graduates will likely have at least some of the skills necessary to take introductory jobs in AR/VR. He said, “They should have some basic fundamental skills they can apply to areas like this.” According to Hired, positions in AR/VR require the ability to work with a large amount of data, generated on the web and stored in cloud databases as well as specific programming languages including React, Java, C++, and SQL. A growing total market size Market intelligence company IDC expects global spending on augmented and virtual reality to be nearly $19 billion this year, a growth of 79 percent from the 2019 estimate. That number includes the total of what individual shoppers, companies, governments, and other end consumers are all expected to spend on products like VR headsets and AR glasses and corresponding services. Spending will be led by the commercial sector, including industries like securities and investment services and banking. While $19 billion may seem big, that’s still only a fraction (a little under 15 percent) of expected overall consumer spending on robotics systems and drones, for example, which was estimated by IDC to be about $127.8 billion next year. While we know companies are spending big and hiring expensive talent to build out AR/VR, only time will tell if the consumer market continues to grow and those investments will pay off. VR is already changing the way we play games and watch movies to become more interactive, immersive experiences. AR stands to be even more transformative. Whether we realize it or not, popular social features like live Snapchat and Instagram filters are already leveraging this type of tech. But more profoundly, AR in particular could change the way we live when we’re outside the realm of entertainment, like how we drive to work or buy groceries. At least that’s what tech companies are hoping with their latest AR/VR spending spree. Will you support Vox’s explanatory journalism? Most news outlets make their money through advertising or subscriptions. But when it comes to what we’re trying to do at Vox, there are a couple reasons that we can't rely only on ads and subscriptions to keep the lights on. First, advertising dollars go up and down with the economy. We often only know a few months out what our advertising revenue will be, which makes it hard to plan ahead. Second, we’re not in the subscriptions business. Vox is here to help everyone understand the complex issues shaping the world — not just the people who can afford to pay for a subscription. We believe that’s an important part of building a more equal society. We can’t do that if we have a paywall. That’s why we also turn to you, our readers, to help us keep Vox free. If you also believe that everyone deserves access to trusted high-quality information, will you make a gift to Vox today? One-Time Monthly Annual $5 /month $10 /month $25 /month $50 /month Other $ /month /month We accept credit card, Apple Pay, and Google Pay. You can also contribute via Next Up In Technology Most Read The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained Formula 1 grew too fast. Now its new fans are tuning out. The Ballad of Songbirds & Snakes might be the best Hunger Games movie yet Why are so few people getting the latest Covid-19 vaccine? What are Israel and Palestine? Why are they fighting? vox-mark Sign up for the newsletter Sentences The day's most important news stories, explained in your inbox. Thanks for signing up! Check your inbox for a welcome email. Email (required) Oops. Something went wrong. Please enter a valid email and try again. The Latest Most of Israel’s weapons imports come from the US. Now Biden is rushing even more arms. By Jonathan Guyer Formula 1 grew too fast. Now its new fans are tuning out. By Izzie Ramirez The controversy over TikTok and Osama bin Laden’s “Letter to America,” explained By A.W. Ohlheiser and Li Zhou Your phone is the key to your digital life. Make sure you know what to do if you lose it. By Sara Morrison Alex Murdaugh stands guilty of killing his wife and son. That’s just scratching the surface. By Aja Romano Is the green texting bubble about to burst? By Sara Morrison Chorus Facebook Twitter YouTube About us Our staff Privacy policy Ethics & Guidelines How we make money Contact us How to pitch Vox Contact Send Us a Tip Vox Media Terms of Use Privacy Notice Cookie Policy Do Not Sell or Share My Personal Info Licensing FAQ Accessibility Platform Status Advertise with us Jobs @ Vox Media "

"Microsoft’s HoloLens 2: a $3500 mixed reality headset for the factory - The Verge"

"https://www.theverge.com/2019/2/24/18235460/microsoft-hololens-2-price-specs-mixed-reality-ar-vr-business-work-features-mwc-2019"

"The Verge homepage The Verge homepage The Verge The Verge logo. / Tech / Reviews / Science / Entertainment / More Menu Expand Menu Tech Microsoft’s HoloLens 2: a $3,500 mixed reality headset for the factory, not the living room Designed to get work done By Dieter Bohn Photography by Vjeran Pavic Feb 24, 2019, 5:20 PM UTC | Comments Share this story I am in a tiny room in a basement somewhere in Microsoft’s Redmond, Washington headquarters, wearing an early version of the HoloLens 2 headset. In front of me is a very real ATV, which is missing a bolt. Not quite at the corner of my vision — but certainly off to the side — I see a glowing indicator pointing to a bucket of the right bolts. I walk over, bend down to look more closely at the shelf, and grab one. Back at the ATV, a holographic set of instructions hovers above it, telling me what to do and pointing to the exact spot where the bolt needs to go. After a couple of minutes, I’ve successfully fixed the thing — guided by holograms. I tap a holographic button on the guide to close out the instructions. This sort of demo is quickly becoming commonplace for tech journalists like myself. But if you read the previous description closely, you’ll find that there are three key pieces of technical innovation hidden in plain sight. Here they are: I saw a hologram off to the side because the field of view in which they can appear is much larger than before. I bent down and didn’t worry about an awkward headset shifting around because it was better balanced on my head. I pushed a button just by pushing a button because I didn’t need to learn a complicated gesture to operate the HoloLens 2. Those three things might not seem all that remarkable to you, but that’s precisely the point. Microsoft needed to make the HoloLens feel much more natural if it really plans to get people to use it, and it has. There’s one more unremarkably remarkable thing: even though it was just a demo, I was playing the part of a worker because that’s who the HoloLens 2 is exclusively designed for — workers, not consumers. The Microsoft HoloLens 2 is available for preorder today for $3,500, and it’s expected to ship later this year. However, Microsoft has decided that it is only going to sell to enterprise customers who want to deploy the headset to their workers. As of right now, Microsoft isn’t even announcing a developer kit version of the HoloLens 2. Compared to the HoloLens we first saw demonstrated four years ago , the second version is better in nearly every important way. It’s more comfortable, it has a much larger field of view, and it’s better able to detect real physical objects in the room. It features new components like the Azure Kinect sensor, an ARM processor, eye-tracking sensors, and an entirely different display system. It has a couple of speakers, the visor flips up, and it can see what your hands are doing more accurately than before. There’s an 8-megapixel front-facing camera for video conferencing, it’s capable of full 6 degrees of tracking, and it also uses USB-C to charge. It is, in short, chock-full of new technology. But after four years, that should be no surprise. Before we go any further, a disclosure: my wife works for Oculus, the VR division of Facebook. We don’t discuss her work or the stories that I am working on. It doesn’t affect how I think about this tech, and I have no idea if Facebook and Oculus are building anything directly competitive with this product. The biggest complaint about the first HoloLens was simple: you only saw the holograms in a relatively small box, directly in front of you. Turn your head even a little, and they would disappear from your field of view. Worse, their edges would clip out of existence even when you were staring right at them. It was like looking at a digital world through a tiny rectangle. The HoloLens 2 has a field of view that’s twice as big as before. It doesn’t quite fill your entire field of vision — there’s still clipping — but it’s big enough now that you no longer feel constantly annoyed by a letterbox. Microsoft says that each eye has the equivalent of a 2K display in front of it, but it’s better to think of that as a metaphor than a precise spec. The exact spec is that it has a “holographic density of 47 pixels per degree,” which means that the pixel density is high enough to allow you to read 8-point font. Typically, when a tech product gets better specs like these, it happens through sheer force of technical iteration: faster processors, bigger batteries, more RAM, and so on. But that strategy wouldn’t have worked for the display on the HoloLens 2. It needed to get lighter, not heavier. So Microsoft had to completely change over to a different kind of display technology. Lasers and mirrors Laser-based displays have become the thing to do for computers on your face. Intel’s Vaunt project used lasers, and the North Focals smart glasses do, too. Although Microsoft is using some of the same basic components, it’s taken them in a different direction and gone much further in developing what they can do. The lasers in the HoloLens 2 shine into a set of mirrors that oscillate as quickly as 54,000 cycles per second so the reflected light can paint a display. Those two pieces together form the basis of a microelectromechanical system (MEMS) display. That’s all tricky to make, but the really tricky part for a MEMS display is getting the image that it paints into your eyeball. One solution that companies like North have used is a holographic film on the lens to reflect the image directly into your retina. That has lots of drawbacks: a tiny display and low resolution, for two. But the truly problematic part is simply ensuring the display is aimed right into your eye. You have to be custom-fitted for the North glasses, and the image can disappear entirely if they’re misaligned. Microsoft doesn’t want any of those problems, so it turned to the same thing it used on the first HoloLens: waveguides. They’re the pieces of glass in front of your eye that are carefully etched so they can reflect the holograms in front of your eyes. The waveguides on the HoloLens 2 are lighter now because Microsoft is using two sandwiched glass plates instead of three. When you put the whole system together — the lasers, the mirrors, and the waveguide — you can get a brighter display with a wider field of view that doesn’t have to be precisely aimed into your eyes to work. Zulfi Alam, general manager for Optics Engineering at Microsoft, contends that Microsoft is way out ahead with this system and that waveguides are definitely the way to go for mixed reality. “There’s no competition for the next two or three years that can come close this level of fidelity in the waveguides,” he argues. Do you want a wider field of view? Simple. Just increase the angle of the mirrors that reflect the laser light. A wider angle means a bigger image. Do you want brighter images? Simple again. Lasers, not to put too fine a point on it, have light to spare. Of course, you have to deal with the fact that waveguides lose a ton of light, but the displays I saw were set to 500 nits and looked plenty bright to me. Microsoft thinks it could go much brighter in the final version, depending on the power draw. Do you want to see the holograms without getting specifically fitted for your headset? Simple yet again. The waveguide doesn’t require specific fitting or measurement. You can just put the headset on and get going. It also can sit far enough in front of your eyes to allow you to wear whatever glasses you need comfortably. Simple, simple, simple, right? In truth, it’s devilishly complex. Microsoft had to create an entirely new etching system for the waveguides. It had to figure out how to direct light to the right place in the waveguides nearly photon by photon. “We are simulating every photon that comes from the laser,” Alam says. The light from the lasers isn’t just reflected; it’s split apart in multiple colors and through multiple “pupils” in the display system and then “reconstituted” into the right spot on the waveguides. “Each photon is calculated where it’s expected to go,” Alam says. That takes a ton of computing power, so Microsoft had to develop custom silicon to do all of the calculations on where the photos would go. And though alignment is much easier with the waveguide, that doesn’t mean it’s perfect. That’s why there are two tiny cameras on the nose bridge, directed at your eyeballs. They will allow the HoloLens 2 to automatically measure the distance between your pupils and adjust the image accordingly. Those cameras will also allow the HoloLens 2 to vertically adjust the image if it gets tilted or if your eyes are not perfectly even. (They are not. Sorry.) A sort of free benefit of those cameras is that they can also scan your retinas to log you into the HoloLens 2 securely. It runs Windows, after all, and therefore it supports Windows Hello. They also track where you’re looking, which enables some new user interactions I’ll get to below. Then there’s power: lasers, oscillating mirrors, and custom chips to handle the computing for all of that must chew through battery. But Alam tells me that even with all of that, it still manages to require less power than the alternative. The mirrors oscillate in resonance, so it takes less energy to move them, sort of like they’re the fastest metronomes ever. Lasers are also less lossy than LEDs, and custom silicon can be optimized to its specific task. ”Our evolution is toward a form factor that is truly glasses,” Alam says, “and all these are significant steps in this journey.” All that tech is impressive for sure, but I don’t want to oversell the image quality. What I was using wasn’t a finished product. I did see a tiny halo around some of the holograms, and they sometimes jumped around a bit. Most of the features based on the nose bridge eye scanners weren’t flipped on yet, either. Still, compared to the first HoloLens, what I saw crossed over the line from “cool demo I’d use for 20 minutes and then be annoyed” to “I could see people using this for a few hours if the software was really useful.” But if you’re going to use a headset for “a few hours,” it needs to be comfortable enough to leave on in the first place. Comfort zone Here’s how you put the HoloLens 2 on: you put it on like a baseball cap, twist a knob on the back to tighten the headband, and then you’ll start seeing holograms. The end. It’s much less fiddly than the last HoloLens or any other face-mounted display I’ve ever tried. Because of all the work on the display system, you can skip the extra “fuss with the position to make sure you can see the image” step. The body of the thing is simpler, too. It’s a single band that’s held on with minimal pressure on the back of your head and on your forehead. (There’s an optional top strap if you need it.) All of that is nice, but it’s pointless if the headset is uncomfortable to wear. And though I never had it on for more than a 20-minute stint, I think it will hold up for longer periods. Microsoft has a “human factors” lab where it loves to show off its collection of dummy human heads and high-speed cameras. Carl Ledbetter, senior director of design for the Microsoft Device Design Team, walked me through all of the prototypes and material Microsoft tried to get into the final product. He explained how Microsoft experimented with different designs and materials, ultimately landing on carbon fiber to save weight. ”The reality is [we have to] fit kids, adults, men, women, and different ethnicities around the world. Everybody’s head is different,” he says. Microsoft has a database of around 600 heads tracking the shape of the cranium, eye depth, the size and relative position of the nose bridge, and other variations. Ledbetter’s team attached sensors to people’s necks to measure muscle strain, to make sure the center of gravity was right. The result is that the HoloLens 2 has a more forgiving and flexible fit. It simply does a better job of accommodating basic, physical human realities. You can flip the visor up so it’s out of your field of view so you can make eye contact without removing the headset. The memory foam pad that rests on your forehead is removable and cleanable, and the thermals have been completely redesigned so heat is piped away from your head. All of that really helps, but the most important thing Microsoft did was move the center of gravity right behind your ears instead of up by your eyes. The HoloLens 2 isn’t really much lighter than the original HoloLens. It feels lighter, though, because it’s balanced more naturally on your head. That balance makes a huge difference. The weight of it is less noticeable and should put less strain on your neck. Ledbetter moved the weight by literally moving the heaviest part: the main processor and battery are now located in a module that sits on the back of the headset, with wires inside the headband running up to the display board and components in the front. That processor, by the way, is an ARM-based Qualcomm Snapdragon 850, and that’s important because it addresses another basic human reality: we hate when the battery dies, and we hate plugging stuff in. An ARM processor means it can have a smaller battery. “If you’re going to be on battery, [it’s] hard to find a product that’s not running ARM today.” The original HoloLens ran on an Intel processor, and it ran Windows. Since then, Microsoft has done a ton of work to get Windows working well on ARM. Those efforts are slowly coming to fruition on laptops , but Intel is still the order of the day on those machines where raw speed is usually more important to users than battery life. In general, there’s a tension with Intel. It’s not delivering the lower-power chips that mobile devices demand. Intel even reportedly had to lobby Microsoft to keep the Surface Go on its chips. So what about the HoloLens 2? Alex Kipman is the person in charge of the whole HoloLens project. He says that “ARM rules in battery-operated devices. The ARM decision became fairly easy. If you’re going to be on battery, [it’s] hard to find a product that’s not running ARM today.” When I point out that there are plenty of Windows laptops running on batteries using Intel chips, he becomes blunter. “Intel doesn’t even have an SoC [system on chip] right now for these types of products that run on battery. They did have one, the previous version [of the HoloLens] had Cherry Trail , which they discontinued. That decision is a no-brainer.” For workers, not consumers The HoloLens 2 is only being sold to corporations, not to consumers. It’s designed for what Kipman calls “first-line workers,” people in auto shops, factory floors, operating rooms, and out in the field fixing stuff. It’s designed for people who work with their hands and find it difficult to integrate a computer or smartphone into their daily work. Kipman wants to replace the grease-stained Windows 2000 computer sitting in the corner of the workroom. It’s pretty much the same decision Google made for Google Glass. “If you think about 7 billion people in the world, people like you and I — knowledge workers — are by far the minority,” he replies. To him, the workers who will use this are “maybe people that are fixing our jet propulsion engine. Maybe they are the people that are in some retail space. Maybe they’re the doctors that are operating on you in an operating room.” He continues, saying it’s for “people that have been, in a sense, neglected or haven’t had access to technology [in their hands-on jobs] because PCs, tablets, phones don’t really lend themselves to those experiences.” “I’m here to tell you that it’s still not a consumer product.” Fair enough. That’s completely in fitting with Microsoft’s new focus on serving corporate and enterprise needs instead of trying to crank out hit consumer products. That was one of my takeaways when I interviewed CEO Satya Nadella last year , and it holds true today. As I wrote then, it’s “a different kind of Microsoft than what we’re used to thinking of. It’s a little less flashy, yes, but it has the benefit of being a lot more likely to succeed.” Besides, Kipman argues, even the HoloLens 2 isn’t good enough to be a real mass-market consumer technology product. “This is the best, highest watermark of what can be achieved in mixed reality and I’m here to tell you that it’s still not a consumer product,” he says, then continues: Why is it not a consumer product? It’s not as immersive as you want it to be. It’s more than twice as immersive as the previous one, [but it’s] still not immersive enough for that consumer off the street to go use it. It’s still not comfortable enough … I would say that until these things are way more immersive than the most immersive product, way more comfortable than the most comfortable product, and at or under $1,000, I think people are kidding themselves in thinking that these products are ready. Kipman says that Microsoft has not participated in the consumer hype cycle for these types of products. “We were not the company that hyped VR. We are certainly not the company that hyped AR. And since we merged the two into the mixed reality and AI efforts, we haven’t hyped either.” That’s not exactly true. We have seen plenty of demos from Microsoft showing off games — including Minecraft — and other consumer applications for the HoloLens. So this move to the enterprise market is absolutely a pivot. But it’s a pivot that’s part and parcel with Microsoft’s larger corporate strategy. And just because it’s no longer being positioned as a consumer product doesn’t mean that it’s not an important product — one that Microsoft appears to be committed to and is developing software for. A better interface on your face The first HoloLens required users to learn awkward gestures with names like “Air Tap” and “Bloom.” You had to make these really specific hand gestures because that’s all the first HoloLens’ sensors could detect and understand. The HoloLens 2 can detect and understand much more because of a new array of sensors for reading the room called the Azure Kinect. “Kinect” because that’s the brand for Microsoft’s cameras that can scan rooms, “Azure” because seemingly everything the company does these days is somehow connected to its cloud service and as a further signal that this is a business product, not an Xbox add-on. “HoloLens 1 is just one big mesh. It’s like dropping a blanket over the real world,” Kipman says. “With HoloLens 2, we go from spatial mapping to semantic understanding of spaces. You understand what’s a couch, what is a human sitting on the couch, what’s the difference between a window and a wall.” I can’t speak to how well Kinect is actually able to identify objects — Microsoft didn’t demo any of that for us — but it theoretically works because the Azure Kinect sees the room at a higher resolution and because it is hooked up to cloud services that help it figure out what things are. There’s one aspect where I can definitively say that the higher fidelity is real: it’s able to identify my hand and what it’s doing much more easily. It can track up to 25 points of articulation on both hands in space, which means that you shouldn’t need to use the Air Tap gesture to interact with holograms anymore. In one demo, I paced around a room looking at various holograms that were set up on tables. As I reached my hands in, a box appeared around each one with little grab handles on the edges and corners. I could just reach in and grab the whole box and move the hologram around. I could also just grab one edge to rotate it, or two to resize it. When there was a button, I could stick my finger out and push it. I doubt that it’s accurate enough to, say, let you type on a virtual QWERTY keyboard, but it’s a big step up over the first generation, nonetheless. Eye tracking also comes into play in how you interact with holograms. The HoloLens 2 can detect where you’re looking and use that information as a kind of user interface. There were demos where I just stared at a little bubble to make it pop into holographic fireworks, but the most useful one was an auto-scroller. The closer to the bottom of the page I got, the faster the words scrolled, but then it stopped when I looked back up. I didn’t see the full top-level user interface, so I don’t know if that’s changing. But one thing absolutely isn’t: it still runs Windows. It utilizes the shared code in Windows OneCore , which means you won’t get a traditional Windows desktop shell, but you will be able to run any Universal Windows App on it. It also has the necessary drivers to let you connect a keyboard and a mouse to it over Bluetooth if you really want to. Chaitanya Sareen, the principal group program manager for Microsoft Mixed Reality, explains that they’re trying to “make the machine work around the person versus the other way around.” Sareen calls this “instinctual interaction” as opposed to “intuitive,” since it can piggyback off of what we already do with real objects in the world. “Is anyone born saying ‘There’s going to be a close button [in the upper corner of a window]’? No,” he says. “A lot of interfaces we use are learned.” “Is anyone born saying, ‘there’s going to be a close button’? No.” Sareen is still thinking through some of the details of what the user interface will be, but the goal is to use many of the natural gestures you picked up as a toddler instead of making you learn a whole new interface language. Microsoft is also making new software tools available to developers. One of the most important, Dynamic 365 Guides, will be a mixed reality app with templates to create instructions for repairing real-world things like that ATV. Other tools depend on Microsoft’s cloud services. One is Azure Remote Rendering that lets the HoloLens offload some compute load to the cloud. It exists because the HoloLens 2 can only store and render a limited kind of detail for something like a 3D render of an engine locally. With Remote Rendering, some of the detail can come in real time from the cloud, so it displays potentially infinite levels of detail, allowing you to model and interact with the smallest parts of a holographic machine. Finally, there’s Azure Spatial Anchors. It lets you pin holograms to real places in the world. At a basic level, it’s not all that different from what Apple and Google are already doing in augmented reality: letting multiple devices see and interact with the same virtual object. Microsoft’s ambitions are much grander, though: it wants to create the infrastructure for a “world scale” set of holograms, and it’s building tools that let developers use that infrastructure across platforms, including iOS and Android. Solving that requires more than just GPS location and object recognition. Kipman talks a lot about distinguishing between identically boring conference rooms that are in the same spot on different floors. Tracking objects in space using optics is famously difficult. Walk in a circle around a building, and your position will drift, so the computer won’t put your ending point at the starting point. It’s a little fuzzy about how far along Microsoft has actually gotten toward solving these problems, but it’s actively working on them. Alex Kipman believes we are on the precipice of the “third era of computing.” First came PCs with their open architectures, second came phones with walled garden app stores, and now he hopes mixed reality headsets will swing the pendulum back to openness because Microsoft intends to keep the HoloLens open. The HoloLens works with Microsoft’s cloud services, but it would work with other ecosystems, too. Kipman says the HoloLens and Azure are “loosely coupled, but tightly aligned.” I could do more than quibble with his summary of the history of computing and point out that there’s also quite a history of underdogs calling for openness, but the larger point stands: Microsoft thinks that mixed reality is going to be a Big Deal. Understanding what Microsoft’s plans lately has required wading through a lot more jargon than it used to. With the HoloLens 2 specifically, expect a lot of discussion about “time-to-value” (how quickly a user can do something useful after getting a device from an employer) and “intelligent edge” (devices with their own computing power nevertheless connected to the cloud). There’s a cognitive dissonance for regular consumers with all of that talk. Kipman’s protestations to the contrary, there is plenty of hype around the HoloLens 2. It’s just directed at corporations now. Some of it is well-deserved. I think that the HoloLens 2 is a technical marvel. Just because it isn’t being sold as a consumer device doesn’t mean that it’s not also an important piece of technology, something that could change our conception of what a computer should look like. But we’re used to consumer electronics companies doing their best to put such technical marvels on store shelves, translating that hype into gadgets in our pockets and on our heads. For the HoloLens 2, the hype isn’t about personal technology. It’s just business. The Verge on YouTube / Exclusive first looks at new tech, reviews, and shows like Better Worlds. Sam Altman fired as CEO of OpenAI Breaking: OpenAI board in discussions with Sam Altman to return as CEO Windows is now an app for iPhones, iPads, Macs, and PCs Screens are good, actually What happened to Sam Altman? Verge Deals / Sign up for Verge Deals to get deals on products we've tested sent to your inbox daily. From our sponsor Advertiser Content From More from this stream MWC 2019: foldable phones, 5G, and other news from Mobile World Congress Vergecast: Mobile World Congress round table Mar 1, 2019, 4:31 PM UTC The Punkt MP02 is Android minimalism at its finest Mar 1, 2019, 11:50 AM UTC The OnePlus 7 is looking unlikely to have wireless charging Mar 1, 2019, 9:24 AM UTC The best phones of MWC 2019 Feb 28, 2019, 1:00 PM UTC Terms of Use Privacy Notice Cookie Policy Do Not Sell Or Share My Personal Info Licensing FAQ Accessibility Platform Status How We Rate and Review Products Contact Tip Us Community Guidelines About Ethics Statement The Verge is a vox media network Advertise with us Jobs @ Vox Media © 2023 Vox Media , LLC. All Rights Reserved "

"The Chip Shortage Is Easing—but Only for Some | WIRED"

"https://www.wired.com/story/the-chip-shortage-is-easing-but-only-for-some"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Will Knight Business The Chip Shortage Is Easing—but Only for Some Photograph: Costfoto/Getty Images Save this story Save Save this story Save This month, Taiwanese chipmaker TSMC, which produces some of the world’s most advanced silicon , announced record profits for the past quarter—up by 76.4 percent from the year before to 237.03 billion New Taiwan dollars ($8.05 billion). It also warned that weakening consumer demand coupled with chip hoarding would put a dent in future financials. “Our expectation is for the excessive inventory in the semiconductor supply chain to take a few quarters to rebalance to a healthier level,” C.C. Wei, TSMC’s CEO, said during the company’s earnings call. It’s just the latest sign that the recent chipmaking boom is finally over—for some at least. But that doesn’t mean the shortage of chips that has bedeviled the global economy is about to disappear, or that the US need no longer worry about shoring up its advanced chipmaking capacity. “In certain industries, there’s an easing—an equilibrium,” says Julie Gerdeman, CEO of Everstream Analytics, a company that analyzes supply chain data to help companies forecast risk. But she says the complexity of the chip supply chain, the diversity of components used in different sectors, and evolving risks affecting product availability, require a more nuanced picture. Gerdeman says people often talk as if all chips are the same, “but you really need to look at the kind of chip and the industry.” Some sectors still see shortages, as well as growing uncertainty around future supply, she adds. Many chip companies have made a killing in the past few years, thanks to the pandemic rush to buy laptops , games consoles , and other gadgets ; soaring use of cloud computing ; and increased need for chips in industries like automotive and home appliances. The unprecedented demand, combined with supply chain shocks and pandemic shutdowns, has caused critical shortages of some chips, shuttering factories and forcing companies to redesign or reengineer products and hoard components. Now soaring inflation, growing economic uncertainty, crashing cryptocurrency prices , and a glut of some components have eased some shortages, and sky-high pricing for certain chips are coming down. Other manufacturers of high-end consumer chips also expect orders to start drying up. Last month, Intel said it would put a freeze on hiring in the group that produces desktop and laptop chips, due to declining sales prospects. Reports published last week suggest the South Korean memory chipmaker SK Hynix is considering whether to slash its 2023 capital expenditure by a third because of softening consumer demand. The price of some chips reflects the downward trajectory. The cost of DRAM memory chips, for instance, fell by 10.6 percent from April to July, according to TrendForce , a Taiwanese market research company. The cost of graphics processing units (GPUs), which are needed for gaming PCs, for crypto-currency computations, and to run artificial intelligence computations, has fallen roughly 17 percent over the past month, according to one analysis. In April, Gartner forecast that semiconductor revenue growth would be roughly 13 percent in 2022, compared with 25 percent in 2021. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But the turnaround is far from uniform. Everstream’s data shows that lead times for some advanced chips needed for medical devices, telecommunications, and cybersecurity systems is around 52 weeks, compared to a prior average of 27 weeks. Automotive companies that were badly affected by the pandemic because they initially canceled orders for components were then blindsided by an uptick in demand and had no spare inventory and little negotiating leverage when it came to ramping back up. Modern cars can have thousands of chips, and future models are likely to pack even greater computing power, thanks to more advanced in-car software and autonomous driving functionality. “Anything automotive—or competing with capacity for automotive—is still highly constrained,” says Jeff Caldwell, director of global supply management at MasterWorks Electronics, a manufacturer of printed circuit boards, cables, and other electronics products. Actify CEO Dave Opsahl, whose company sells operation management software to automotive companies, says the supply of chips has not improved for carmakers, and shortages of raw materials like resin and steel, as well as of labor, have also gotten worse. Frank Cavallaro is CEO of A2 Global, a company that finds, procures, and tests electronic components for manufacturers. He says the current situation reflects the complexity of the chip market and supply chain. Many end products include numerous semiconductor components sourced from all over the world and require devices to be packaged by companies that are mostly in China. “It’s macro, it’s micro, it’s down to individual regions,” he says. Everstream’s Gerdman says the appearance of the new BA5 Covid variant in China has raised fears of draconian lockdowns that could hamper the production of chips and other products. She adds that uncertainty around future capacity—as well as geopolitical restrictions on chip exports—makes it difficult to plan ahead. The geopolitical picture may significantly increase global capacity to produce advanced chips. Legislation making its way through the US Senate would provide $52 billion in subsidies to increase domestic chip production. The US share of global chip production has fallen from 37 percent in the 1980s to 12 percent today. But while chip shortages have been cited by those boosting subsidies, much of the money would go to reshoring production of advanced chips. The country’s most advanced technology, from Intel, lags behind that of TSMC, presenting a potential weakness in US access to technology that promises to be vital for everything from AI to biotechnology to 5G. The current downturn may only contribute to instability further along the semiconductor supply chain. “Unfortunately, a slowing economy brings with it the risk of some suppliers going into financial distress or liquidity crunch if they cannot access capital,” says Bindiya Vakil, CEO of Resilinc, a company that sells AI-based supply chain management tools. “This can introduce a lot of risk into the supply situation. Companies should really monitor supplier financial health and collaborate closely with suppliers to give them favorable payment terms, upfront payments, and so on, to help them with liquidity.” The cyclical nature of the semiconductor industry even has some, including Syed Alam, who leads the global semiconductor practice at consulting firm Accenture, envisioning the shortage turning into a glut. “A rising concern for 2023 is the possibility of overcapacity for chip production,” he says. “Companies need to be focused on building an agile and resilient supply chain for the longer term, and be prepared to react.” Updated 7-28-2022, 5 pm EDT. This piece was updated to correct the name of South Korean chipmaker SK Hynix. Updated 7-26-2022, 9 am EDT. TSMC is a Taiwanese chip manufacturer, not South Korean as previously stated. You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Senior Writer X Topics chips China microchips auto industry David Gilbert Kari McMahon Nelson C.J. Peter Guest Andy Greenberg Joel Khalili Steven Levy Jacopo Prisco Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"With Subscriptions, Automakers Mimic Netflix’s Playbook | WIRED"

"https://www.wired.com/story/subscriptions-automakers-mimic-netflix"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Aarian Marshall Business With Subscriptions, Automakers Mimic Netflix’s Playbook BMW offers subscriptions for an onboard dashcam and a remote car starter. Photograph: BMW Save this story Save Save this story Save In 2021, credit card statements are loaded with routine monthly charges: Netflix for video, Spotify for music, XBox Game Pass for gaming, Peloton for fitness—and so on, with meal kits, wine boxes, and high-protein, low-carb cereals. The financial services company UBS estimates that the “subscription economy,” powered by pandemic-induced changes in buying habits, will grow 18 percent annually for the next four years, hitting $1.5 trillion in 2025. Now automakers want to join the party. The idea is simple: We’ll sell you a car with a dashcam, or that can be driven hands-free, or that can coach you with telematics data to be a better driver. But if you actually want to use any of the new toys, you’ll have to pay extra. Credit Tesla with popularizing the notion that cars could be updated with software even after they're driven off the lot. General Motors told investors this month that subscription services could bring in an additional $20 billion to $25 billion annually by 2030. The company says 4.2 million customers already pay for its OnStar security services, which include an app that costs $15 a month. Electric vehicle startup Rivian said in recent financial filings that it could bring in an additional $15,500 over the life of each car with software-enabled services, including an autonomous driving feature and subscriptions for infotainment, internet connectivity, and diagnostics. BMW last summer created buzz—and consternation—with plans to charge, through subscription fees, for features like heated seats. In the US, the automaker offers subscriptions for an onboard dashcam and a remote car starter. Over the past few years, automotive companies have laid out plans to transform from “being an industry that sells products to an industry that sells services and products,” says Brian Irwin, who heads the automotive and mobility practice at the consultancy Accenture. Today’s vehicles come with multiple computer chips, cameras, and sensors—and thus, the tantalizing opportunity to use detailed data to both create and sell new products. The industry’s move towards electrification might make the idea more attractive. “Consumers see EV as a new technology that's enabling new things,” says Alan Wexler, who oversees connected services and data insights at General Motors. That means they’re willing to think about paying for cars in a new way too. In fact, carmakers would love it if you started thinking of your wheels as a “platform,” a smartphone-like device that will require a few extra app purchases to fit neatly into your lifestyle. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg In 2019, BMW walked back plans to charge drivers an annual fee to use Apple CarPlay, pictured above. Photograph: BMW Automakers have long been attracted to the idea of software-enabled add-ons, because manufacturing vehicles is a low-margin business—and building software is not. Developers can build a product once and push it out to millions, rather than offer more customization as the car is built. It helps automakers’ bottom lines when the average car on the road is almost 12 years old. It also offers an opportunity to cement customers to a brand, the same way iPhone users keep buying Apple products. Plus, there’s a sad and sneaky secret to subscriptions: People forget they’ve subscribed, allowing businesses to charge their credit cards into perpetuity, or at least until someone finally takes a magnifying glass to their credit card statement. (Federal regulators are reportedly studying how to make it harder for companies to trap consumers with automatic renewals and subscriptions.) It’s an open question, however, whether drivers will get on board with subscription payments. Car buyers might succumb to “ subscription fatigue ,” as they realize that unbundling products into monthly charges sometimes costs more in the end, and refuse to purchase yet another one. They could also decide that the offered features simply aren’t worth the money. “The giant gap in the logic is, nobody has exactly cracked the code to what you can get people to subscribe to long-term,” says Mike Ramsey, an automotive analyst with Gartner. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Internal research from General Motors suggests that customers are willing to pay up to $135 a month for the right mix of products and services, the company says. That could include enhanced map services, data analysis for business owners who run fleets of GM (and non-GM) vehicles, and software-enabled performance upgrades that boost acceleration. The company also touts a future in which it might allow outside developers to create apps to run on its in-car platform, as smartphone makers do today. Still, subscriptions and aftermarket charges for features that once came standard have already generated pushback. In 2019, BMW reversed a plan to charge drivers $80 a year to use Apple CarPlay in their vehicles. The company faced similar resistance last summer, when it announced plans to charge for what it calls “digital personalizations,” like lane-keep assistance features or heated steering wheels. Jay Hanson, a spokesperson for BMW, says these are “part of a global BMW strategy,” but declined to discuss what the company has learned about customers’ willingness to pay. In general, experts say, carmakers should be cautious about charging drivers for basic safety and security features, which could antagonize drivers by creating the appearance that they’re being upsold to have a safe ride. The magic of marketing may help. “Subscriptions can be packaged in different ways to different demographics, depending on whether it’s a scary word or foreign concept to them,” says Accenture's Irwin. After all, many US drivers already make monthly car payments. Think of that cool new feature less as a subscription, and more as the cherry on top of your regular bill. 📩 The latest on tech, science, and more: Get our newsletters ! Rain boots, turning tides, and the search for a missing boy Astronomers prepare to probe Europa's ocean for life Clearview AI has new tools to identify you in photos Dragon Age and why it sucks to play cult favorites How a Google geofence warrant helped catch DC rioters 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 📱 Torn between the latest phones? Never fear—check out our iPhone buying guide and favorite Android phones Staff Writer X Topics Infotainment cars Telematics auto industry General Motors software Aarian Marshall Aarian Marshall Aarian Marshall Caitlin Harrington Paresh Dave Reece Rogers Morgan Meaker Amanda Hoover Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"A New Jailbreak for John Deere Tractors Rides the Right-to-Repair Wave | WIRED"

"https://www.wired.com/story/john-deere-tractor-jailbreak-defcon-2022"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Lily Hay Newman Security A New Jailbreak for John Deere Tractors Rides the Right-to-Repair Wave Photograph: Paul Marriott/Alamy Save this story Save Save this story Save farmers around the world have turned to tractor hacking so they can bypass the digital locks that manufacturers impose on their vehicles. Like insulin pump “looping” and iPhone jailbreaking, this allows farmers to modify and repair the expensive equipment that’s vital to their work, the way they could with analog tractors. At the DefCon security conference in Las Vegas on Saturday, the hacker known as Sick Codes is presenting a new jailbreak for John Deere & Co. tractors that allows him to take control of multiple models through their touchscreens. The finding underscores the security implications of the right-to-repair movement. The tractor exploitation that Sick Codes uncovered isn't a remote attack, but the vulnerabilities involved represent fundamental insecurities in the devices that could be exploited by malicious actors or potentially chained with other vulnerabilities. Securing the agriculture industry and food supply chain is crucial, as incidents like the 2021 JBS Meat ransomware attack have shown. At the same time, though, vulnerabilities like the ones that Sick Codes found help farmers do what they need to do with their own equipment. John Deere did not respond to WIRED's request for comment about the research. Sick Codes, an Australian who lives in Asia, presented at DefCon in 2021 about tractor application programming interfaces and operating system bugs. After he made his research public, tractor companies, including John Deere, started fixing some of the flaws. “The right-to-repair side was a little bit opposed to what I was trying to do,” he tells WIRED. “I heard from some farmers; one guy emailed me and was like ‘You’re fucking up all of our stuff!’ So I figured I would put my money where my mouth is and actually prove to farmers that they can root the devices." This year, Sick Codes says that while he is primarily concerned about world food security and the exposure that comes from vulnerable farming equipment, he also sees important value in letting farmers fully control their own equipment. “Liberate the tractors!” he says. After years of controversy in the US over the “right to repair” the equipment one purchases, the movement seems to have reached a turning point. The White House issued an executive order last year directing the Federal Trade Commission to increase enforcement efforts over practices like voiding warranties for outside repair. That, combined with New York state passing its own right-to-repair law and creative activist pressure , has generated unprecedented momentum for the movement. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Facing mounting pressure, John Deere announced in March that it would make more of its repair software available to equipment owners. The company also said at the time that it will release an “enhanced customer solution” next year so customers and mechanics can download and apply official software updates for Deere equipment themselves, rather than having John Deere unilaterally apply the patches remotely or force farmers to bring products to authorized dealerships. “Farmers prefer the older equipment simply because they want reliability. They don’t want stuff to go wrong at the most important part of the year when they have to pull stuff out of the ground,” Sick Codes says. “So that's what we should all want too. We want farmers to be able to repair their stuff for when things go wrong, and now that means being able to repair or make decisions about the software in their tractors.” To develop his jailbreak, Sick Codes got his hands on numerous generations of John Deere tractor control touchscreen consoles. But ultimately he focused on a few models, including the widely deployed 2630 and 4240 models, for the exploit he is presenting. It took experimentation on a number of touchscreen circuit boards over many months to find bypasses to John Deere's dealer authentication requirements, but eventually Sick Codes was able to game a reboot check to restore the device as if it were being accessed by a certified dealer. He found that when the system thought it was in such an environment, it would offer more than 1.5 GB worth of logs that were meant to help authorized service providers diagnose problems. The logs also revealed the path to another potential timing attack that might grant deeper access. Sick Codes soldered controllers directly onto the circuit board and eventually got his attack to bypass the system's protections. “I launched the attack, and two minutes later a terminal pops up,” Sick Codes says of the program used to access a computer's command-line interface. “I had root access, which is rare in Deere land.” The approach requires physical access to the circuit board, but Sick Codes says it would be possible to develop a tool based on the vulnerabilities to more easily execute the jailbreak. Mostly he says he is curious to see how John Deere will react. He's unsure how comprehensively the company can patch the flaws without implementing full disk encryption, an addition that would mean a significant system overhaul in new tractor designs and likely wouldn't be deployed in existing equipment. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The first priority, though, once Sick Codes had the exploit working? Running custom farm-themed Doom on the tractor, of course. Update Thursday, August 18, 2022, at 12:15 pm ET: John Deere sent WIRED the following statement: "John Deere’s top priority is, and will always be, to protect our customers, their machines, and their data. The capabilities that Sick Codes demonstrated during his recent presentation at DEF CON were obtained through invasive/persistent physical access, disassembly of a hardware product and reverse engineering of proprietary software. At no point were a customer or dealer’s equipment, networks, or data at risk. “Any researcher, given unfettered physical access and time, will eventually be able to adversely impact the operations of a device, and no company, including John Deere, is immune to such access. However, we are deeply committed and work tirelessly to safeguard our customers, and the role they play in the global food supply chain. In addition to a dedicated team of over 300 product and information security professionals, we also work closely with industry-leading cybersecurity partners like HackerOne and embrace the broader ethical hacking community to ensure our security capabilities continue to lead the industry.” You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Senior Writer X Topics vulnerabilities hacking DefCon Lily Hay Newman Andy Greenberg Andrew Couts David Gilbert Andy Greenberg Justin Ling David Gilbert David Gilbert Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"AI Comes to Car Repair, and Body Shop Owners Aren’t Happy | WIRED"

"https://www.wired.com/story/ai-car-repair-shop-owners-not-happy"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Aarian Marshall Business AI Comes to Car Repair, and Body Shop Owners Aren’t Happy Insurance companies increasingly ask drivers to download an app and take photos of damaged cars at certain angles, and in certain light. Photograph: Getty Images Save this story Save Save this story Save Sector Consumer services Finance Automotive Source Data Images Technology Machine vision Machine learning In the Before Times, Jerry McNee wasn’t always a fan of appraisers. McNee is the president of Ultimate Collision Repair, an auto repair shop in Edison, New Jersey. From his perspective, appraisers and claims adjusters, paid by insurance companies, generally want to pay less for repairs than he thinks his shop deserves. Since Covid-19 swept the globe last year, McNee sees far fewer appraisers. Instead, insurers are deploying technology, including photo-based estimates and artificial intelligence. McNee kind of misses his old adversaries. “When the appraisers were here, face to face, you had a better relationship with them,” he says. “The appraiser knew you, he trusted you.” The pandemic has upended many businesses. The auto repair industry is a case study of the unexpected effects of technology replacing in-person interactions. Before the pandemic, about 15 percent of US auto claims were settled using photos rather than in-person visits by adjusters, says Bill Brower, the head of Auto Claims at LexisNexis Risk Solutions, a data and analytics company. Now, that’s 60 percent, and he expects it to reach 80 percent by 2025. At the same time, insurers accelerated their investment in AI. Last year “was the year that AI really crossed the threshold from novelty to norm,” says Marc Fredman, the chief strategy officer at CCC Information Services, which sells technology to insurers. The company says half of all claims now involve at least some AI tools. Auto insurance is “not something that you’d necessarily assume would be very innovative and cutting edge, but it actually is,” says Fredman. The changes are here to stay. Using AI and virtual estimates, “insurers have really seen improvements in efficiency, consistency, and timeliness,” says Mark Friedlander, a spokesperson for the Insurance Information Institute, an industry group. The technology isn’t meant to replace human workers, Friedlander says, but to help resolve claims more quickly and consistently. The technology has created “great results not only for insurers, but also policyholders,” he says. It’s auto claims pitched to the millennial set: speedy and phone-based, with as few back-and-forth calls as possible. CCC says internal surveys show that 80 percent of customers who initiate photo claims find the process “appealing to navigate.” Tractable, a company that uses computer vision and machine learning to build algorithms for insurance companies, says 25 percent of its estimates are so on-the-nose, they don’t need human intervention. The company wants to get that figure to 75 percent by the end of the year, says Alex Dalyac, Tractable’s CEO and cofounder. One group not happy with the results: body-shop owners. “I'd say 99.9 percent of the estimates are incorrect,” says Jeff McDowell, who owns Leslie's Auto Body in Fords, New Jersey. “You can’t diagnose suspension damage or a bent wheel or frame misalignment from a photograph.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Repair shop owners say they’re spending much more time haggling with insurance companies to determine the correct price for a repair—time for which they’re not compensated. In some cases, that means damaged vehicles are stuck in the shop for longer than usual. Incomplete estimates can lead to incomplete repairs. Motorists sometimes bring their vehicles to Hernandez Collision Repair to make sure work done by other shops was done properly. The company’s two shops in southeast Georgia have seen more shoddy or incomplete work during the pandemic, says April Hernandez, whose family owns the business. She attributes the change to photo-based estimates and the AI that’s applied during the process. “I feel like it’s getting worse as time goes on,” she says. “A photo is worth a thousand words, but it doesn’t come up with the value of the damage,” says Mike LeVasseur, who directs the collision division at the Automotive Service Association, an industry trade group. “I'd say 99.9 percent of the estimates are incorrect. You can’t diagnose suspension damage or a bent wheel or frame misalignment from a photograph.” Jeff McDowell, owner, Leslie's Auto Body, Fords, New Jersey Virtual estimates work like this: Many major insurance companies ask drivers who have been in accidents to download an app. The app directs them to take photos of their cars at certain angles, and in certain light. Using just those photos, a claims adjuster estimates how much it will cost to fix the car. Photo estimates make sense for insurers. In person, adjusters can travel to and inspect three to eight vehicles a day. With photos, the adjusters don’t need cars or gas, just a computer, and can finish 15 to 20 estimates a day. Add in AI and the process can get even faster and more efficient. Automobiles are good candidates for image-based machine learning. Like cats —which have pointy ears, whiskers, little noses—cars have a consistent form—doors, windshields, fenders. A million things could go wrong with the 30,000 parts in an average car, but the most common of them generally look a certain way. So algorithms are trained in image classification using millions of photos of damaged cars, of every make and model. The tech can then “read” a photo taken by a policyholder and draw conclusions about what needs to be fixed—or whether a human inspection is needed. Using data from local parts suppliers and repairers, it then estimates the cost. Then comes the human touch: The systems guide adjusters through the estimation process, in many cases automatically populating forms. The adjuster just has to double check the computer’s work. CCC, the technology provider, says insurers can boost productivity 30 percent with its AI product, called Smart Estimate. Some industry insiders are looking toward a completely automated, “touchless” estimate process, at least for some kinds of damage. “Touchless happens to be the holy grail, the final destination of automated estimating,” Olivier Baudoux, an executive at the insurance claims technology company Mitchell, told an industry audience last month. “A photo is worth a thousand words, but it doesn’t come up with the value of the damage.” Mike LeVasseur, director, collision division, Automotive Service Association That’s already happening in some places outside the US. Last fall, the Spanish insurer Admiral Seguro said it had started to use AI to resolve auto claims within minutes after policyholders upload photos of the damage. Last month, Israeli smart-dashcam company Nexar began working with Japan’s Mitsui Sumitomo Insurance to translate the high-definition footage and acceleration and GPS data captured by its cameras into scripts, like subtitles on a foreign movie. Claims adjusters can use the machine-generated scripts to resolve claims. The technology will learn as adjusters translate those scripts into estimate line-items, says Bruno Fernandez-Ruiz, Nexar’s cofounder and chief technology officer. That means the humans are training the tech to improve. The technology suppliers acknowledge that their programs aren’t flawless. “This is new technology for the industry, and there are going to be some kinks in the system,” says Friedlander, the Insurance Information Institute spokesperson. “It’s an evolving system, and it will continue to get more precise and more accurate.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The virtual, AI-assisted estimates seem to be very good at separating out, within a matter of seconds, vehicles that can be fixed from vehicles that should be totaled. Experts say they’re also good at evaluating minor vehicle damage, from crashes where no one is hurt. These make up the majority of incidents, so in many cases, photo-based estimates work out. Dalyac, the Tractable CEO, says that he hopes the algorithms can evolve into agreed-upon standards that reduce disagreements between insurers and repairers. “We’ve got to make the process frictionless,” he says. During the pandemic, insurers have turned to estimates based on customers’ photos for all sorts of collisions, even severe ones. Insurance companies sometimes consider these estimates “starting places” for in-person repairers. But body shop owners say that customers get frustrated at them when the insurer’s initial estimate is lower than the repairer’s quote—in some cases, by thousands of dollars. Repair shops get stuck in the middle. The shops don’t know when artificial intelligence has been applied to the estimates they receive. But whatever’s happening, they say, isn’t consistent. “People say that this is the way of the future,” McDowell, the New Jersey auto repair owner, says of virtual estimates. “I don’t agree with that. There are certain things you can’t do from a photograph.” 📩 The latest on tech, science, and more: Get our newsletters ! Audio pros “upmix” vintage tracks and give them new life 5 years after the Oculus rift, where do VR and AR go next ? YouTube has a disturbingly creepy Minecraft problem How to get a battery replacement for your aging smartphone The Roaring-’20s post-pandemic summer terrifies me 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more ✨ Optimize your home life with our Gear team’s best picks, from robot vacuums to affordable mattresses to smart speakers Staff Writer X Topics Safety artificial intelligence machine learning computer vision Self-Driving Cars insurance Caitlin Harrington Will Knight Niamh Rowe Amanda Hoover Reece Rogers Will Knight Will Knight Amanda Hoover Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Paul Le Roux, the Coder Who Became a Criminal Mastermind | WIRED"

"https://www.wired.com/story/mastermind-excerpt"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Evan Ratliff Backchannel Meth, Murder, and Pirates: The Coder Who Became a Crime Boss Illustration: Eric Petersen Save this story Save Save this story Save This story is excerpted from The Mastermind: Drugs. Empire. Murder. Betrayal , by Evan Ratliff. How a brilliant self-made software programmer from South Africa single-handedly built an online startup that became one of the largest individual contributors to America’s burgeoning painkiller epidemic. In his world, everything was for sale. Pure methamphetamine manufactured in North Korea. Yachts built to outrun coast guards. Police protection and judges’ favor. Crates of military-grade weapons. Private jets full of gold. Missile-guidance systems. Unbreakable encryption. African militias. Explosives. Kidnapping. Torture. Murder. It's a world that lurks just outside of our everyday perception, in the dark corners of the internet we never visit, the quiet ports where ships slip in by night, the back room of the clinic down the street. On a gray afternoon, three men enter a drab hotel room for a business meeting, months in the making. Two are white: a portly South African and his muscled European deputy. The other, with dark hair and a paunch of his own, is Latino—Colombian, or so he says. The hotel is in the Liberian capital, abutting the Atlantic Ocean on the coast of West Africa, but it could be any number of places in the world. The men’s business is drugs and weapons, and drugs and weapons are everywhere. They shake hands, nod heads, and begin speaking in the elliptical but familiar way of people who share the vernacular of a trade. They are cautious, but not cautious enough. A video exists to prove it. This article was excerpted from The Mastermind: Drugs. Empire. Murder. Betrayal, by Evan Ratliff. Buy on Amazon Random House “I can see why you picked this place,” says the South African, settling his substantial bulk into a maroon leather couch pressed against the wall. “Because it’s chaotic. It should be easy to move in and out, from what I’ve seen.” His name is Paul, and to a trained ear his cadence carries a tinge of not just South Africa but his childhood home, Zimbabwe, where he lived until his teens. His large white head is shaved close, and what hair remains has gone gray as he approaches forty. He has the look of a beach vacationer cleaned up for a dinner out, in an oversize blue polo shirt and a pair of khaki cargo shorts. His clothes seem out of keeping with both the scope of his international influence and the deal he is about to complete, with a man he believes to be the head of a South American drug cartel. “Very easy,” replies the Colombian, whom Paul refers to only as Pepe. In the video recording of the meeting, Pepe sits down just offscreen, on a matching couch. His disembodied voice speaks in flawless, if heavily accented, English. “Very few people, not too many eyes. It looks like the right place.” “Trust me—what’s your name again?” “Paul.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg “Paul, trust me, it’s the right place. I’ve been here already for quite a bit of time. And always, me and my organization, we pick places like this. First of all, for corruption. You can buy anything you want here. Anything. You just tell me what you need.” “Yeah, it’s safe here,” Paul says. “If there’s a problem here, you can fix it. I understand this type of place.” “Everything is easy here. Just hand to hand, boom boom boom, you can see,” Pepe says, laughing. “Well, thanks to your guy here, now we are meeting.” He gestures at the third man in the room, the European employee of Paul’s who goes by the name Jack. It was Jack who made the initial connection between Paul and Pepe. Evan Ratliff is an award-winning journalist and founder of The Atavist Magazine. He is a two-time finalist for the National Magazine Awards and the Livingston Awards. His 2009 WIRED cover story “ Vanish ,” about his attempt to disappear and the public’s effort to find him, was selected by the magazine as one of the 20 best stories in its history. The deal Jack brokered was complex enough that, when I meet him years later, I need him to walk me through it several times. The Colombians, who deal primarily in the cocaine produced in their own country, are looking to expand into methamphetamine, which they want to manufacture in Liberia and distribute to the United States and Europe. Paul, a computer programmer who heads his own kind of cartel based in the Philippines, will provide the materials to build the Colombians’ meth labs: precursor chemicals, formulas for cooking them into meth, and a “clean room” in which to synthesize it all. While the labs are being built, Paul has agreed to also sell Pepe his own stash of meth, in exchange for an equivalent amount of cocaine at market rates. After months of back-and-forth, Jack has urged Paul to travel to Liberia and meet his new associate “boss to boss” to finalize the deal. “So where do you want to start?” Pepe says. “First of all is the clean room.” Paul tells him that the parts needed to build it are already en route by boat. “If you have any problem, I’ll send guys here to assemble it like that.” He snaps his fingers. “We shouldn’t have any. I got my guys here, my chemist.” “To compensate you for the delays, we will just, when we do business, we will give you back the money.” “Paul, you don’t have to compensate me for nothing.” Paul flicks his hand in the air. “We feel bad it took so long.” “This is just business,” Pepe says. “We don’t have to compensate, just doing business. This is about money.” Pepe turns to the second part of the deal: the trade of his Colombian cocaine for Paul’s methamphetamine, a sample of which Paul has shipped to him from his base in the Philippines. “Let me ask you a question,” Pepe says. “Sure.” “You are not Filipino, why the Philippines?” “Same reason you are in Liberia. Basically, as far as Asia goes, it’s the best shithole we can find, which gives us the ability to ship anywhere. It’s the best position in Asia. And it’s also a poor place. Not as bad as here, but we can still solve problems.” “You are cooking your shit in the Philippines?” Pepe says. “Actually, right now we manufacture in the Philippines and we also buy from the Chinese. We’re getting it from North Korea. So the quality you saw was very high.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg “That’s not just very high. That is awesome.” “Yeah.” “I was going to tell you that later on, but now that you talk about it: That stuff is fucking incredible.” “That is manufactured by the North Koreans,” Paul says. “We get it from the Chinese, who get it from the North Koreans.” “So my product is going to be the same, the amount that I’m going to buy from you?” “The same. Exactly the same.” Paul nods. “I know you want the high quality for your market.” “Yeah, because the product—you know that one of the best customers, and you probably know that, is the Americans.” “Number one.” “It’s the number one. They are fucking—they want everything over there. I don’t know what the word is from Spanish. Consumistas? Consumists?” “Consumers,” Jack interjects, off-camera. “Yeah, they buy everything and they never stop,” Paul says. “So everything that I ship is to America,” Pepe says. “Trust me, when I brought this, fucking everyone was asking me for it. Everyone.” Paul and Pepe consider different payment possibilities. First they will trade the cocaine for meth. After that, Paul says that he is happy to be paid in gold or diamonds. If they need to conduct bank transfers, he works primarily through China and Hong Kong, although he sounds a note of caution. “We just had, in Hong Kong, twenty million dollars frozen, by bullshit,” he says. “You need to be cautious. It becomes worse, because the American, he likes to control everything. And they are there, making a lot of trouble.” “I say fuck Americans,” Pepe says. “Americans, like you say, they think that they can control everything, but they cannot. It’s not impossible, but they cannot. We have to be very careful.” They discuss shipment methods, and how many kilos of each drug the other could move in a month. Paul owns ships already picking up loads in South America and traveling to Asia, but he much prefers to work in Africa, territory he knows well. His customers are in Australia, Thailand, China. “We are not touching the US right now,” he says. “Why not?” Eric Petersen Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg “Actually we move pills in the US,” Paul says. “These American fucks, they have an appetite for everything. They will just spend and spend and spend.” Indeed, Paul has gotten rich, fabulously rich, by selling tens of millions of prescription painkillers to Americans over the Internet for nearly a decade. But unlike Pepe’s organization, Paul carefully avoids shipping street drugs like meth to the States. “It generates too much heat,” he says. As the meeting winds down, Paul flashes a hint of his technical prowess, offering to send Pepe mobile phones that he has set up with encryption software to allow the two organizations to communicate securely. He tells Pepe he can get him any weapons he needs out of Iran, particularly if a Liberian general can be produced to make the transaction look official. Then he pauses to reflect. “I can tell you, you won’t find a better partner,” he says. He is a man, he explains, who keeps his organization in line. “One thing I tell all the guys, OK, everyone I deal with: Just don’t fucking steal. You know what I’m saying? That’s the one thing that pisses me off.” Earlier he described an employee who stole $5 million from him, then began driving a Lamborghini around Manila, buying his girlfriends designer handbags and diamond necklaces. The employee was no longer a problem, he said. “He’s moved on, let’s put it that way.” Now Paul has more management advice. “Don’t steal,” he repeats, “and don’t fucking run your mouth to the government. You get caught doing anything, remember: You keep your mouth shut. You’ve got some guys—I’m sure you’ve had this: They come like this”—he makes a motion as if operating a jabbering puppet—“they get afraid in jail and then they think that the government is going to help them. They think the government is their best friend. I’m sure you’ve seen this, right?” “That is only in movies,” Pepe says. “They are running their fucking mouth like this. What’s going to happen when you get out, you make the deal? You think we’re going to forget about you?” He slaps his hands together. “You have a problem, we help you. Your family has a problem, we help them. Nobody has a problem. Just follow these rules, we are very straight on that. So I tell you, we do business, you trust me one hundred percent. We will deliver for you. One hundred percent.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg “This is a trust deal,” Pepe says, before the three men stand up to shake hands. “That’s exactly what we are going to do.” In the months before and after Paul and Pepe’s meeting, a series of strange events occurred in disparate parts of the globe, events that appeared unrelated. I say “appeared” as if anyone on the outside was observing them at all. At the time no one was, including me. Even if anyone had been, none of these incidents appeared tied to any other as they filtered into public view. Like a handful of random jigsaw-puzzle pieces, each one was incomprehensible without an understanding of the larger picture. It would be a year before I picked up even one of those pieces to examine it, and several more before I began to understand the image that the whole collection of them combined to reveal. In March 2012, six months before Paul and Pepe’s meeting in Liberia, agents from the United States Drug Enforcement Administration walked through the glass doors of a small pharmacy on Main Street in Oshkosh, Wisconsin. They were armed with search warrants targeting its 82-year-old owner, Charles Schultz. A pillar of the local community for four decades, Schultz had been charged with shipping more than 700,000 illegal painkiller prescriptions from the back of his two local pharmacies. In return, the agents calculated, he had received more than $27 million in wire transfers from a mysterious Hong Kong bank account. Roughly a month later, officers from the Organized Crime and Triad Bureau in Hong Kong raided a warehouse in Tsuen Wan, a bayside district north of the city. Inside they discovered twenty tons of ammonium nitrate fertilizer, divided into a thousand bags and falsely labeled as sodium chloride. It was enough to create an explosive 10 times more powerful than the one used in the Oklahoma City bombing. On the warehouse lease they found the name of an Israeli-Australian citizen, a former member of an elite division of the Israeli Defense Forces. When they raided the man’s office and apartment, they turned up deeds for two stash houses, receipts for tens of millions of dollars in gold bars, and handwritten directions to a meeting in Buenaventura, Colombia, with a man named “Don Lucho”—the head of one of the world’s biggest cocaine cartels. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Then, in November, a pair of spear fishermen diving off an atoll in Tonga discovered a wrecked forty-four-foot sailboat with a badly decomposed body on board. Lining the walls of the boat’s cabin, local authorities found, were 204 bricks of cocaine, neatly wrapped in brown plastic and worth more than $90 million on the street in Australia, where they suspected it had been destined. In early December, 3,000 miles to the northeast, a contractor for the National Security Agency named Edward Snowden organized a gathering of cryptography buffs in the back room of a strip mall storefront in Honolulu. After a couple dozen people had assembled, he plugged his laptop into a projector and began an instructional talk about a free program called TrueCrypt. It was, he said, the world’s most secure software for encrypting a laptop hard drive, protecting it from the prying eyes of governments. Very little was known about the people behind TrueCrypt, he cautioned; the programmers who created it were anonymous. But Snowden also knew something about TrueCrypt that he was not yet ready to reveal: He had stolen documents from the NSA showing that the agency couldn’t break it. When I began trying to investigate this series of events later, they were tantalizing but baffling to me. As I rewound back through them, each seemed like a kind of message from an adjacent reality that few of us experience directly. In that world, I would learn, a brilliant self-made software programmer from South Africa could single-handedly build a dystopian company to rival today’s tech giants. Through his creation, an online startup selling hundreds of millions of dollars’ worth of pills to American customers, he would become one of the largest individual contributors to America’s burgeoning painkiller epidemic, and the most successful cyber-criminal in history. He would leverage that fortune into a sprawling criminal empire, fulfilling his seemingly insatiable appetite for the clandestine and the illegal. His ambition for wealth and power would slip the bonds of the Internet and enter the realm of flesh and blood. “The scope of his criminal conduct,” as one US federal prosecutor later put it, “is simply staggering.” In the adjacent world he came to occupy, everything was for sale if you knew what to offer and to whom. Pure methamphetamine manufactured in North Korea. Yachts built to outrun coast guards. Police protection and judges’ favor. Crates of military-grade weapons. Private jets full of gold. Missile-guidance systems. Unbreakable encryption. African militias. Explosives. Kidnapping. Torture. Murder. Former soldiers from the United States, United Kingdom, and elsewhere, drifting in the murky realm of global security contracting, could reinvent themselves as roving assassins for hire. Call center managers in Tel Aviv could wake up and find themselves arms dealers. Family doctors could turn into conspirators in an international drug cartel at the click of a button. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg That world lurks just outside of our everyday perception, in the dark corners of the internet we never visit, the quiet ports where ships slip in by night, the back room of the clinic down the street. The events of 2012, I discovered, were simply the edges of that world crossing over into our own. And I came to understand how ordinary people could take one morally ambiguous step across that divide, then a second and a third, until suddenly cops or killers were at their door. There was one puzzle piece I couldn’t get out of my head. At 6:30 am on the morning of February 13, 2012, Jeremy Jimena, a garbage collector in the Philippines, had just started his shift. He set out with his driver on their regular route through Taytay, an industrial city an hour east of Manila. It had rained most of the night, and a light drizzle fell as they turned down Paseo Monte Carlo, a quiet road with no lights. Their first stop was a large vacant lot overrun by low shrubs, a green carpet of vines, and a scattering of banana trees. The field wasn’t an official pickup spot, but local residents often dumped garbage there, and the collectors had informally added it to their route. That morning there was a small pile of trash spilling into the road: two large bags filled with waste and a bulging, rolled-up bedspread. Jimena, a small, wiry man with jet-black hair and a wisp of a mustache, hopped off the truck and approached the pile. When he leaned down and grasped the damp edge of the blanket, he saw a woman’s foot sticking out. Jimena dropped the blanket and ran, shouting to the driver, and the two of them abandoned the truck and sprinted to the municipal headquarters. There they told the local head of security what they had found, and he called the police. Jimena returned to his route in a daze. He never spoke to the police himself, and never learned who the woman was. When I met him four years later, I didn’t tell him what I knew: That her name was Catherine Lee, and she had been an accomplished real estate agent with a husband and a child. That she’d been shot below each eye with a .22-caliber pistol, rolled up in a blanket, and dumped out of a van. That somehow, her death connected back to a pharmacist in Oshkosh, Wisconsin, a warehouse raid in Hong Kong, a wrecked boat in Tonga. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Eric Petersen Jimena didn’t seem to want to know those details anyway. Mostly he just seemed to want to forget. For years, he told me, he dreamed of her every night. The woman, wrapped in a blanket. Sometimes she would be asking him for help. Other times she would just scream. So much of reporting, it took me a long time to discover, is waiting. Waiting for people to call back. Waiting for documents to arrive in the mail. Waiting for a plane to take you halfway across the world, only to arrive at the appointed time in a dreary office and sit in a plastic chair, waiting for an official who never shows up. Standing on a doorstep, waiting to see if a victim’s family will return. Sending out pleas for information and staring at a phone, waiting for them to boomerang back. All of it, in some sense, amounts to waiting for the same thing: that one sliver of fact that will help make sense of all the ones that came before it. In December 2015, when I flew to the Philippines to try to untangle the connections behind Catherine Lee’s still-unsolved murder, I discovered entirely new magnitudes of waiting. Much of it I did in a rented van, with a Filipina American journalist I’d enlisted to assist me, Aurora Almendral. The two of us were stuck in the grip of Manila’s endless traffic, crawling to appointments that would inevitably involve more waiting once we arrived. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg So it was that one afternoon, a few weeks before Christmas, we pulled up to a neglected cinder-block building on a steep hill in the town of Taytay. We’d been told this was the investigative division of the local police. We walked in, past a woman stapling paper holiday decorations to the wall, through a pair of swinging doors, and into a cramped room with four desks. An air conditioner rattled in the window and three detectives pecked away on ancient-looking computers. We tried to rouse one of them and explain the reason we were there: to visit the vacant lot where Jeremy Jimena had encountered Catherine Lee’s body. The chief of police had promised, over the phone, to take us there, but that morning he’d been called away by a kidnapping. The other cops had no idea when he would return. No one claimed to know much about the body, and in the years since the murder, those people who did know something had tended to disappear. Some murders, perhaps, were better left unsolved. So Almendral and I settled in to wait, sitting on a bench in front of a framed police “Loyalty Pledge” that hung on the wall. “Remember that an ounce of loyalty is worth a pound of cleverness,” it read in English. If you must growl, condemn and eternally find fault Why! resign your position. And when you are outside, Damn to your hearts content. But as long as you’re a part of the institution, Do not condemn it. If you do, the first high wind that comes along will blow you away And probably you’ll never know why. It read to me more like the blood oath of a criminal enterprise than the pledge of a law enforcement organization. But this was before I fully grasped how easily, under the right conditions, the two could sometimes come to resemble one another. After some coaxing by Almendral in Tagalog, an officer named Abigail Del Monte agreed to pull the case file for us. She returned from a back room and proceeded to flip through it idly at her desk, as if trying to discern why I had flown 8,000 miles and then driven three hours to visit a crime scene nearly four years after the fact. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Finally another detective showed up, a friendly guy in a jean jacket. He introduced himself as George Arada. Suddenly everyone shifted into action. “You’re here for the Catherine Lee case?” he asked. “OK, let’s go.” We offered our slightly beat-up van and driver for transportation, and Del Monte decided to join as well. Along the way we picked up the local watchman who had called the cops after Jimena’s discovery. Then we drove over to the vacant lot. At the site, the watchman showed us where the body had been positioned, and how he’d marked off the area back in February 2012. “The body was moved a little bit by the guy who picked up the blanket,” he said. “I didn’t find out anything about who she was.” We walked over to an older woman selling drinks at a roadside stand. She remembered that day. “I saw the body,” she said, “but it was covered up, so we couldn’t see who it was. Three streets down, somebody had been missing for a couple of days, so we thought it could be them.” Later, word came back from the cops that the body belonged to a real estate agent from another part of the country. When I asked what happened to the missing neighbor, the drink-stand woman said that the family had just moved on. I wandered around taking photos, looking for signs that Jimena’s horrible discovery had somehow transformed this otherwise ordinary place. If the body had left a mark, it wasn’t visible. We piled back into the van, and on the drive to the station I asked the detectives whether they often encountered corpses in Taytay, a city of just over 300,000 people. “Sometimes over five in a month, but not over 10,” Arada said cheerfully. “It’s kind of a well-known place to dump bodies. Don’t tell the chief!” He laughed. The cases were difficult to solve, he said. The bodies were often mutilated or “broken up and stuffed in garbage bags.” I asked if I could look at the case file, and to my surprise Del Monte turned and handed it to me. Photos taken at the crime scene showed Lee’s body, unwrapped, dressed in a black jacket and jeans, lying facedown with her feet in the road. A crowd stood at the edge of a police cordon. The facts in the file were spare: A team from the national police’s Scene of Crime Operations division had arrived at 7:50 that morning. An autopsy report listed the cause of “instantaneous death”: a gunshot wound under each eye. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The investigators had little trouble identifying the victim. She was found with her identification: Catherine Cristina Lee, 43, from Las Piñas City, an hour south of Taytay. Also with the body were a cellphone, an Anne Klein wristwatch, a silver bracelet, and a pair of rings, one silver and one gold. She had not been robbed; there was no sign of sexual assault. Flipping through the file as we drove back to the police station, I came across mention of a 2015 meeting between Filipino officers and a special agent from the DEA’s Los Angeles office, along with a copy of his business card. I wasn’t the first person, it seemed, to travel to the Philippines and ask questions about the body. Hoping to make some sense of what happened in Taytay, Almendral and I went to see Rizaldy Rivera, an agent at the Philippine National Bureau of Investigation who we’d learned had been assigned to the Lee murder case. The NBI’s Death Investigation Division was housed in a charmless room with tiled floors and the insipid fluorescent lighting that marks bureaucracies worldwide. On the wall was a whiteboard outlining agents’ assignments, organized by nickname: “Cardinal,” “Undertaker,” “Mechanic,” “Hitman,” “Braveheart,” “Snakedoc,” “KGB.” A genial cop with a waist-length ponytail and a talent for sharp-shooting, Rivera was a natural showman. Almost immediately after we had shaken hands, he urged me to check out his target- shooting videos on YouTube. (Later I did, and had to admit that the clips were impressive—in one he cuts a credit card in half at 20 yards with a handgun, aiming over his shoulder using a compact mirror.) Most people called him Zaldy, but his nickname around the NBI offices was Slayer, bestowed after three shootouts early in his career, one of which left a bullet in his thigh. Rivera had picked up the Catherine Lee case after her husband contacted the NBI and requested that it look into her murder, the day after the body was discovered. The agency is required by law to take over cases at the request of victims’ families, and often those requests stem from concerns that local officers are incompetent, or worse. The ranks of local and national police in the Philippines are rife with corruption, and the NBI had a better, though not spotless, reputation for integrity. In the case of a murder-for-hire, which is what Rivera deduced the Lee case to be, it wasn’t unusual to hear whispers that cops themselves were in on the job. Police work pays poorly, with as much as 60 percent of the national police force living below the poverty line. Contract murder was a thriving industry in the Philippines; having someone killed cost as little as 5,000 pesos, or around $100. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg “I cannot provide the real names of the witnesses, or their addresses and photos, in order to protect them,” Rivera said when we arrived. Otherwise, “I can probably answer any question that you want me to answer.” He gestured to a pair of plastic lawn chairs in a cubicle, facing a desk completely devoid of papers or equipment. We started at the beginning, talking above the sounds of an NBA game—basketball being a Philippine national obsession—from a television somewhere just out of sight. Over the course of an hour, Rivera laid out everything he knew about Lee’s murder. He spoke in the world-weary manner of a cop who had seen his share of vicious crimes. But at times, he sounded as mystified as I was about how all the pieces of Lee’s killing fit together. Rivera had reconstructed Lee’s movements from interviews with everyone she had encountered the day she disappeared, as well as clues found on her laptop and phone. The day before her body was discovered, Lee had been out showing properties to two foreigners, Canadians named Bill Maxwell and Tony. For some of the showings she had invited along several friends and fellow real estate agents. They’d last seen her climb into a silver Toyota Innova minivan with the Canadians, mid-afternoon, to go look at another property. From the friends and a security guard at one gated community, Rivera gleaned enough detail to generate sketches: two white men, one goateed and the other clean shaven, both wearing baseball caps. But when it came to their identities, he hit a wall. “It was very hard to check with the immigration bureau in the Philippines,” Rivera said, “because Bill Maxwell and Tony—the names were fictitious.” As for physical evidence, there was little to go on. The body had been out in the rain long enough that Philippine police technicians were unable to check for trace elements of DNA. The Toyota van lacked license plates, although the security guard had written down the number from a temporary registration sticker. When Rivera tried to trace it, nothing matched. He concluded that the number was probably faked. Without the van, there would be no fingerprints, no hair, no fibers. One aspect of the crime stood out to Rivera: Lee had been shot under each eye, with what forensics determined was a .22-caliber handgun. “In our experience,” he said, “if you shoot a person dead, you don’t normally use a low-caliber firearm.” Hit men in the Philippines, he said, typically used “Armalite weapons, hand grenades, or a .40-caliber pistol. This is one of the few times that I discovered that the caliber was a .22 magnum.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg To Rivera, the weapon said something about the crime, namely that it might be a type of “signature killing.” He believed that Lee’s death was not a crime of passion but a professional murder committed by someone looking to send a message. “That’s an arrogant way of killing, putting two bullet holes beneath the eye,” he said. “That’s not how you normally execute a person.” After a few months, Rivera’s leads dried up. Other murders required his attention. But like Jimena, he was haunted by Lee’s murder, and his failure to solve it. “I couldn’t sleep soundly at night,” he said. “I was thinking about that case. But the fact is, I cannot just proceed without solid evidence.” For three years the Lee file languished at the NBI. Then, in April 2015, Rivera got a call from the US embassy in Manila. The Americans had some information regarding the Lee murder: A man the DEA had arrested three and a half years earlier on drug charges had been cooperating with the government, and he had tipped them off to possible suspects. Eric Petersen Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg A few months after that phone call, three DEA agents came to meet with Agent Rivera at the Death Investigations Division. Rivera walked them through what he’d learned about the case, using a PowerPoint presentation to recap the investigation’s key points. When he finished, he asked them jokingly, “From one to 10, how would you rate my investigation?” Everyone laughed. The DEA agents confirmed Rivera’s hunch: Bill Maxwell and Tony weren’t the men’s real names. They were not Canadian, nor did they live in the Philippines. They were, the agents suspected, Americans from Roxboro, North Carolina. Rivera introduced the DEA agents to the witnesses he had interviewed about Lee’s last days. The agents showed them photos of the two Americans, Rivera told me, “mingled with seven or eight different photos of seven or eight different individuals.” Some of the witnesses identified the two Americans as having met with Lee. Others didn’t. But after those sessions, one of the DEA agents faxed a report back to the States. The next day, the two men were arrested in Roxboro. Rivera was pleased with the arrests, but he also expressed frustration about his own continuing investigation, which he resumed after the DEA meeting. A local accomplice had allegedly helped supply the murder weapon and vehicle to the suspects, but Rivera still didn’t have enough information to track him down. He pointed out to me that the NBI hadn’t gotten any credit for the arrests, while at the same time suggesting that such credit was unnecessary. “We were not included," he said. "We were happy about that, it’s no problem with us. We have nothing to gain with being famous.” But something else was bothering him: There was someone, or something, much bigger behind the crime that remained shrouded in mystery. Why would the US government send agents across the world to gather evidence against two Americans for the murder of a Filipino woman? Overseas murders, no matter how tragic, typically don’t fall under American jurisdiction. Why not just extradite the pair to the Philippines, where the crime occurred, and hand them off to the NBI? I had the same questions. Perhaps it was related to something more fundamental about the case that I still didn’t understand: Why was Catherine Lee important enough for two men from North Carolina to fly across the world to kill her? Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Rivera had an answer, although at first he was reluctant to tell me. The crime, he said, was the work of “the Mastermind.” At first, Rivera would only identify this Mastermind as the head of a powerful crime organization based in Manila. But he did tell me the motive behind the murder: The Mastermind had once enlisted Catherine Lee to purchase vacation property for him in Batangas, a coastal region south of Manila. He had given her money, at least 50 million pesos, or around a million dollars. “But the deal never materialized,” Rivera said, “because the person who Catherine Lee instructed to do the verification of the land, to arrange the deeds and everything, went off with the money.” That person had also been killed, Rivera said, “the body was never found.” And then the Mastermind had ordered Lee’s murder, too. Catherine Lee, it seemed, had stepped across the invisible divide between her world and the underworld, oblivious to the chain of events she had set in motion that would end in her own death. I asked Rivera if he would tell me the name of the Mastermind, and at first he refused. He had a name but he didn’t want to say it. The DEA, he told me, would “neither confirm nor deny it.” But I already knew who it had to be. “If I tell you the name that I think it is, will you tell me if that’s the person?” I asked. “I will confirm,” he said. “Paul Le Roux.” Rivera slammed his fist down on the table, then held my gaze for several seconds in silence. He lowered his voice to a whisper. “This Paul Le Roux,” he said, “is a very badass guy.” Excerpted with permission from the new book The Mastermind: Drugs. Empire. Murder. Betrayal by Evan Ratliff. Published by Random House, an imprint of Random House, a division of Penguin Random House LLC, New York. Copyright © 2019 by Evan Ratliff. All rights reserved. When you buy something using the retail links in our stories, we may earn a small affiliate commission. Read more about how this works. One man’s epic quest for his Cambridge Analytica data The pitfalls of Facebook merging all its chat apps Ending the government shutdown won't fix flight delays Drones drop poison bombs to fight a rat invasion Have phones become boring? They’re about to get weird 👀 Looking for the latest gadgets? Check out our picks , gift guides , and best deals all year round 📩 Get even more of our inside scoops with our weekly Backchannel newsletter Contributor X Topics Book Excerpt opioids cryptography Edward Snowden Crime Brendan I. Koerner Brandi Collins-Dexter Andy Greenberg Steven Levy Lauren Smiley Angela Watercutter Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Is Bitcoin's Creator this Unknown Australian Genius? Probably Not. (Updated) | WIRED"

"https://www.wired.com/2015/12/bitcoins-creator-satoshi-nakamoto-is-probably-this-unknown-australian-genius"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Andy Greenberg Gwern Branwen Security Is Bitcoin's Creator this Unknown Australian Genius? Probably Not (Updated) Adam Voorhes | Gail Anderson + Joe Newton Save this story Save Save this story Save Editor's note, 4/30/2019: In the days following publication of this story, WIRED published an update that identified inconsistencies in the evidence supporting the notion that Craig Wright is Satoshi Nakamoto. Wright later came forward to claim that he was indeed the creator of Bitcoin, but offered some evidence that appeared to be fraudulent. This piece has been updated to clarify Wright's claims, and the headline has been changed to make clear that WIRED no longer believes Wright is likely to be the creator of Bitcoin. Even as his face towered 10 feet above the crowd at the Bitcoin Investor’s Conference in Las Vegas, Craig Steven Wright was, to most of the audience of crypto and finance geeks, a nobody. The 44-year-old Australian, Skyping into the D Hotel ballroom’s screen, wore the bitcoin enthusiast’s equivalent of camouflage: a black blazer and a tieless, rumpled shirt, his brown hair neatly parted. His name hadn’t made the conference’s list of "featured speakers." Even the panel’s moderator, a bitcoin blogger named Michele Seven, seemed concerned the audience wouldn’t know why he was there. Wright had hardly begun to introduce himself as a "former academic who does research that no one ever hears about," when she interrupted him. "Hold on a second, who are you?" Seven cut in, laughing. "Are you a computer scientist?" "I’m a bit of everything," Wright responded. "I have a master's in law…a master’s in statistics, a couple doctorates..." "How did you first learn about bitcoin?" Seven interrupted again, as if still trying to clarify Wright’s significance. Wright paused for three full seconds. "Um. I’ve been involved with all this for a long time," he stuttered. "I—try and stay—I keep my head down. Um..." He seemed to suppress a smile. The panel’s moderator moved on. And for what must have been the thousandth time in his last seven years of obscurity, Wright did not say the words WIRED’s study of Wright over the past weeks suggests he may be dying to say out loud. "I am Satoshi Nakamoto, the creator of bitcoin." Either Wright invented bitcoin, or he's a brilliant hoaxer who very badly wants us to believe he did. Since that pseudonymous figure first released bitcoin’s code on January 9th, 2009, Nakamoto’s ingenious digital currency has grown from a nerd novelty to a kind of economic miracle. As it’s been adopted for everything from international money transfers to online narcotrafficking, the total value of all bitcoins has grown to nearly $5 billion. Nakamoto himself, whoever he is, appears to control a stash of bitcoins easily worth a nine-figure fortune (it rose to more than a billion at the cryptocurrency’s peak exchange rate in 2014). But the true identity of bitcoin’s creator remains a cipher. Media outlets from the New Yorker to Fast Company to Newsweek have launched investigations into unmasking Nakamoto that were either inconclusive or, in Newsweek’s case , pointed to a man who subsequently denied having anything to do with cryptography, not to mention cryptocurrency. Altogether, the world’s Satoshi-seekers have hardly put a dent in one of the most stubborn mysteries of the 21st century, one whose answer could resonate beyond a small sphere of crypto geeks and have real economic effects. In the last weeks, WIRED has obtained the strongest evidence yet of Satoshi Nakamoto’s true identity. The signs point to Craig Steven Wright, a man who never even made it onto any Nakamoto hunters’ public list of candidates, yet fits the cryptocurrency creator’s profile in nearly every detail. And despite a massive trove of evidence, we still can’t say with absolute certainty that the mystery is solved. But two possibilities outweigh all others: Either Wright invented bitcoin, or he’s a brilliant hoaxer who very badly wants us to believe he did. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The first evidence pointing to Wright appeared in mid-November, when an anonymous source close to Wright began leaking documents to Gwern Branwen , a pseudonymous, independent security researcher and dark web analyst. Branwen provided those documents to WIRED, and they immediately led to several direct, publicly visible connections between Nakamoto and Wright: An August 2008 post on Wright’s blog, months before the November 2008 introduction of the bitcoin whitepaper on a cryptography mailing list. It mentions his intention to release a "cryptocurrency paper," and references "triple entry accounting," the title of a 2005 paper by financial cryptographer Ian Grigg that outlines several bitcoin-like ideas. A post on the same blog from November, 2008. It includes a request that readers who want to get in touch encrypt their messages to him using a PGP public key apparently linked to Satoshi Nakamoto. A PGP key is a unique string of characters that allows a user of that encryption software to receive encrypted messages. This one, when checked against the database of the MIT server where it was stored, is associated with the email address [email protected], an email address very similar to the [email protected] address Nakamoto used to send the whitepaper introducing bitcoin to a cryptography mailing list. An archived copy of a now-deleted blog post from Wright dated January 10, 2009, which reads: "The Beta of Bitcoin is live tomorrow. This is decentralized... We try until it works." (The post was dated January 10, 2009, a day after Bitcoin’s official launch on January 9th of that year. But if Wright, living in Eastern Australia, posted it after midnight his time on the night of the 9th, that would have still been before bitcoin’s launch at 3pm EST on the 9th.) That post was later replaced with the rather cryptic text "Bitcoin - AKA bloody nosey you be…It does always surprise me how at times the best place to hide [is] right in the open." Sometime after October of this year, it was deleted entirely. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg WIRED In addition to those three blog posts, we received a cache of leaked emails, transcripts, and accounting forms that corroborate the link. There’s a leaked message from Wright to his lawyer date June 2008 in which Wright imagines "a P2P distributed ledger"—an apparent reference to bitcoin’s public record of transactions known as the blockchain, long before it was publicly released. The email goes on to reference a paper called "Electronic Cash Without a Trusted Third Party" that Wright expects to release in 2009. 'I did my best to try and hide the fact that I've been running bitcoin since 2009. By the end of this I think half the world is going to bloody know.' Craig Steven Wright Another leaked email from Wright to computer forensics analyst David Kleiman, a close friend and confidant, just before bitcoin’s January 2009 launch discusses a paper they’d been working on together. Wright talks about taking a buyout from his job and investing in hundreds of computer processors to "get [his] idea going." There’s also a PDF authored by Kleiman, who died in April of 2013, in which he agrees to take control of a trust fund, codenamed the "Tulip Trust," containing 1.1 million bitcoins. The PDF appears to be signed with Kleiman’s PGP signature, a cryptographic technique that ensures it couldn’t have been altered post-signature. That million-coin trove—The Tulip Trust—is the same size as a mysterious bitcoin fortune that’s long been visible on bitcoin’s blockchain and widely attributed to Satoshi Nakamoto. No one but Nakamoto is known to have assembled such a massive hoard of the cryptocurrency, and only Nakamoto could have generated so many bitcoins so early in its evolution, when a bitcoin could be “mined” with relatively small amounts of processing power. Only one such bitcoin megapile exists, and the closely-watched coins haven’t moved in bitcoin’s entire history. Bitcoin Survival Guide: Everything You Need to Know About the Future of Money The Rise and Fall of Bitcoin Everyone Says Bitcoin Is Back. But It Never Really Left Another clue as to Wright’s bitcoin fortune wasn’t leaked to WIRED but instead remains hosted on the website of the corporate advisory firm McGrathNicol: a liquidation report on one of several companies Wright founded known as Hotwire, an attempt to create a bitcoin-based bank. It shows that the startup was backed in June 2013 by $23 million in bitcoins owned by Wright. That sum would be worth more than $60 million today. At the time of the company’s incorporation, Wright’s investment in that one firm alone represented more than 1.5 percent of all existing bitcoins, a strangely large stash for an unknown player in the bitcoin world. The giveaways go on: There’s a leaked email from Wright to an associate in January 2014 about a tax dispute with the Australian government. In it, he seems to consider using Nakamoto’s name to wield influence with New South Wales Senator Arthur Sinodinos "Would our Japanese friend have weight coming out of retirement?" Wright asks. It includes a draft email to the senator signed "Satoshi Nakamoto." And a leaked transcript of Wright’s meeting with attorneys and tax officials in February 2014 quotes him in a moment of exasperation: "I did my best to try and hide the fact that I've been running bitcoin since 2009," Wright says. "By the end of this I think half the world is going to bloody know." On December 1st, WIRED sent an encrypted email to Wright suggesting that we knew his secret and asking for a meeting. A few hours later, we received a wary response from the address [email protected], a cyberpunk reference to a rich and powerful corporate dynasty in William Gibson’s Sprawl trilogy. Wright had referenced the same fictional family in the bio of his private twitter profile. The email’s IP showed that it came from an IP address in Panama controlled by Vistomail, the same service that Satoshi Nakamoto had used to send his emails introducing bitcoin and to run Bitcoin.org. “This is a throw away account. There are ways even with [the anonymity software] Tor, but the people in Panama are exteremly [sic] good and do not violate people's desired privacy,” the email read. “You are digging, the question is how deep are you?” The message ended, “Regards, the Director of Tessier-Ashpool” After WIRED sent an encrypted email to Wright suggesting that we knew his secret, we received a perplexing message: 'You seem to know a few things. More than you should.' A few hours later, we received another, even more perplexing message from the same account. “The nature of this moniker is selected for a purpose. I now have resources. This makes me a we now. I am still within that early phase of learning just what my capabilities happen to be. So, even now with resources I remain vulnerable,” it read. “You seem to know a few things. More than you should.” When we responded by describing the three blog posts that showed Wright’s clear connection to bitcoin’s creation and asking again for a meeting, he gave a revealing answer. “Although we all desire some level of credit, I have moved past many of these things,” read his response from the same Tessier-Ashpool account. “Too many already know secrets, the world does not need to know. There are other means to lead change than to be a dictator.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg After our second followup message asking for a chance to talk, Wright responded that he would consider our request. Then he stopped responding altogether. Despite that overwhelming collection of clues, none of it fully proves that Wright is Nakamoto. All of it could be an elaborate hoax—perhaps orchestrated by Wright himself. The unverified leaked documents could be faked in whole or in part. And most inexplicably of all, comparisons of different archived versions of the three smoking gun posts from Wright’s blog show that he did edit all three—to insert evidence of his bitcoin history. The PGP key associated with Nakamoto’s email address and references to an upcoming "cryptocurrency paper" and "triple entry accounting" were added sometime after 2013. Even the post noting bitcoin’s beta launch is questionable. While it was ostensibly posted in January 2009, it later seems to have been deleted and then undeleted—or possibly even written for the first time—sometime between October 2013 and June of 2014. Wright’s blog, his public records, and his verified writings on mail lists and Twitter sketch a man who matches with Satoshi Nakamoto's known characteristics well enough to place him leagues above other candidates. Why those breadcrumbs were dropped remains a mystery. Is Wright trying to falsely steal Nakamoto’s glory (or money)? Is he quietly revealing himself as bitcoin’s creator? But this much is clear: If Wright is seeking to fake his Nakamoto connection, his hoax would be practically as ambitious as bitcoin itself. Some of the clues added to his blog were made more than 20 months ago—a very patient deception if it were one. His references to Grigg’s "triple entry accounting" paper would represent an uncannily inventive lie, representing a new and obscure possible inspiration for bitcoin. And there’s little doubt Wright is a certified bitcoin mogul. Even the $60 million portion of his cryptocurrency stash that’s verifiable in McGrathNicol’s public audit record is suspiciously large. More circumstantially, Wright’s blog, his public records, and his verified writings on mail lists and Twitter sketch a man who matches with Satoshi Nakamoto’s known characteristics well enough to place him leagues above other candidates. He’s a former subscriber to the 1990s "cypherpunks" mailing list devoted to anti-authoritarianism and encryption, an advocate of gold as a financial tool, an accomplished C++ coder, a security professional plausibly capable of writing a tough-to-hack protocol like bitcoin, a libertarian who battled with tax authorities, and a fan of Japanese culture. He is also—parallels to Nakamoto aside—a strange and remarkable person: an almost obsessive autodidact and self-claimed double-PhD who once boasted of obtaining new graduate degrees at a rate of about one a year. He’s a climate-change denier, a serial entrepreneur who claims to have started companies ranging from security consultancies to a bitcoin bank, and an eccentric who wrote on his blog that he once accepted a challenge to create a pencil from scratch and spent years on the problem, going so far as to make his own bricks to build his own kiln in which to mix the pencil’s graphite. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Wright’s blogging and leaked emails describe a man so committed to an unproven cryptocurrency idea that he mortgaged three properties and invested more than $1 million in computers, power, and connectivity—even going so far as to lay fiberoptic cables to his remote rural home in eastern Australia to mine the first bitcoins. His company, Tulip Trading, claims to have built two supercomputers that have officially ranked among the top 500 in the world, both seemingly related to his cryptocurrency projects. (Wright seems to enjoy tulip references, a likely taunt at those who have compared bitcoin to the Netherlands’ 17th century "tulip bubble.") The first of those supercomputers he named Sukuriputo Okane —Japanese for "script money." Wright claims another, named Co1n , holds the title of the world’s most powerful privately owned supercomputer. As Wright told the Bitcoin Investor’s conference, he’s applying that second machine towards the mysterious task of "modeling Bitcoin’s scalability," and meanwhile building an even more powerful supercomputing cluster in Iceland because of its cheap geothermal power. Bitcoin watchers have long wondered why the giant cache of coins they attribute to Satoshi Nakamoto never moved on the bitcoin’s publicly visible blockchain. Wright’s "Tulip" trust fund of 1.1 million bitcoins may hold the key to that mystery. The trust fund PDF signed by Wright’s late friend David Kleiman keeps those coins locked in place until 2020, yet gives Wright the freedom to borrow them for applications including "research into peer-to-peer systems" and "commercial activities that enhance the value and position of bitcoin." Despite those exceptions to the trust’s rules, the million-coin hoard has yet to budge, even after Kleiman’s death in 2013. That may be because Wright could be keeping the coins in place as an investment. He could be leveraging the trust in less visible ways, like legally transferring ownership of money to fund his companies while still leaving it at the same bitcoin address. Or he might still be waiting for January 1st, 2020, a countdown to a date that could take the lid off the biggest cryptocurrency fortune in history. In spite of all the clues as to Wright’s possible secret life—some that he apparently placed himself—Wright has demonstrated such a talent for obfuscation and a love of privacy that he’s never even raised the suspicions of most Nakamoto-worshipping bitcoiners. "If we don't want to go out there and say ‘I’m a billionaire,’ or ‘I’m running XYZ,’ or ‘this is my life,’ I shouldn't have to tell people that," Wright told the Las Vegas crowd in October when an audience member asked his thoughts about what bitcoin means for property rights. "We should be able to choose how we live." In the leaked emails, Wright seems to bristle at the few times anyone has attempted to out bitcoin’s creator. "I am not from the bloody USA! Nor am I called Dorien [sic]," reads a message from Wright to a colleague dated March 6, 2014. That’s the same day as Newsweek ’s largely discredited story claimed the inventor of bitcoin to be the American Dorian Satoshi Nakamoto. If Wright is bitcoin's creator, the revelation of his work carries more importance than merely sating the curiosity of a few million geeks. Wright seemed to take personal offense at the Newsweek story. "I do not want to be your posterboy. I am not found and I do not want to be," he writes in another message the same day. The email, addressed to a colleague and titled "please leak," may have been an early draft of the Nakamoto’s posted denial of Newsweek ’s story. That public denial, a rare message from Nakamoto posted from his account on the P2P Foundation forum, simply read “ I am not Dorian Nakamoto. ” But Wright’s private response was far angrier. "Stop looking... Do you know what privacy means? A gift freely given is just that and no more!" At times, however, Wright has seemed practically envious of Nakamoto. "People love my secret identity and hate me," he complained to Kleiman in a leaked email from 2011. "I have hundreds of papers. Satoshi has one. Nothing, just one bloody paper and I [can’t] associate myself with ME!" Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg If Wright is bitcoin’s creator, the revelation of his work carries more importance than merely sating the curiosity of a few million geeks. The bitcoin economy would need to consider that if his million-bitcoin trust unlocks in 2020, Wright and those to whom he may have assigned hundreds of thousands of bitcoins would be free to sell them on the open market, potentially tanking the cryptocurrency’s price; debates within the bitcoin community like the current fracas over bitcoin’s "block size” may look to long-lost Nakamoto for guidance; the world would have to grapple with the full scope of Wright's vision when he unleashes the result of his companies' post-bitcoin research. The other suspected Satoshis may finally get a reprieve from nosey reporters like us. And the intellectual history of cryptocurrencies would be forever rewritten. Wright himself, despite his hostile response to Satoshi-seekers, has lately seemed to be dropping clues of a double life. In the last two years he’s started to write more frequently about bitcoin on his blog; he’s even peppered Twitter with hints (Though he also deleted many of those earlier this month and made his tweets private.) "'Identity' is not your name. Where people go wrong is that they do not see it to be the set of shared experiences with other individuals," he wrote in one tweet in October. When a UCLA professor nominated Satoshi Nakamoto for a Nobel Prize earlier this month—and he was declared ineligible due to the mystery of his identity—Wright lashed out. "If Satoshi-chan was made for an ACM turing price [sic] or an Alfred Nobel in Economics he would let you bloody know that," he wrote on twitter, using the Japanese "chan" suffix that indicates familiarity or a nickname. "I never desired to be a leader but the choice is not mine," reads a third recent tweet from Wright. "We are a product of the things we create. They change us." In one cryptic and meandering blog post in September in which Wright takes stock of his long career, he even seems to concede that no one can build and wield the wealth that Satoshi Nakamoto has amassed and remain hidden indefinitely. "There is a certain power and mystery in secrets," Wright mused. "Am slowly coming to the realisation and acceptance," he added, "No secret remains forever." Senior Writer X Topics bitcoin Digital Currency Threat Level Andy Greenberg Andy Greenberg Matt Burgess Matt Burgess Kate O'Flaherty Andrew Couts Lily Hay Newman Andy Greenberg Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Writer Evan Ratliff Tried to Vanish: Here's What Happened | WIRED"

"https://www.wired.com/2009/11/ff-vanish2"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Evan Ratliff Backchannel Writer Evan Ratliff Tried to Vanish: Here's What Happened Photograph: Joe Pugliese Save this story Save Save this story Save August 13, 6:40 PM: I'm driving East out of San Francisco on I-80, fleeing my life under the cover of dusk. Having come to the interstate by a circuitous route, full of quick turns and double backs, I'm reasonably sure that no one is following me. I keep checking the rearview mirror anyway. From this point on, there's no such thing as sure. Being too sure will get me caught. I had intended to flee in broad daylight, but when you are going on the lam, there are a surprising number of last-minute errands to run. This morning, I picked up a set of professionally designed business cards for my fake company under my fake name, James Donald Gatz. I drove to a Best Buy, where I bought two prepaid cell phones with cash and then put a USB cord on my credit card—an arbitrary dollar amount I hoped would confuse investigators, who would scan my bill and wonder what gadgetry I had purchased. An oil change for my car was another head fake. Who would think that a guy about to sell his car would spend $60 at Oil Can Henry's? I already owned a couple of prepaid phones; I left one of the new ones with my girlfriend and mailed the other to my parents—giving them an untraceable way to contact me in emergencies. I bought some Just for Men beard-and-mustache dye at a drugstore. My final stop was the bank, to draw a $477 cashier's check. It's payment for rent on an anonymous office in Las Vegas, which is where I need to deliver the check by midday tomorrow. Crossing the Bay Bridge, I glance back for a last nostalgic glimpse of the skyline. Then I reach over, slide the back cover off my cell phone, and pop out the battery. A cell phone with a battery inside is a cell phone that's trackable. About 25 minutes later, as the California Department of Transportation database will record, my green 1999 Honda Civic, California plates 4MUN509, passes through the tollbooth on the far side of the Carquinez Bridge, setting off the FasTrak toll device, and continues east toward Lake Tahoe. What the digital trail will not reflect is that a few miles past the bridge I pull off the road, detach the FasTrak, and stuff it into the duffle bag in my trunk, where its signal can't be detected. Nor will it note that I then double back on rural roads to I-5 and drive south through the night, cutting east at Bakersfield. There will be no digital record that at 4 am I hit Primm, Nevada, a sad little gambling town about 40 minutes from Vegas, where $15 cash gets me a room with a view of a gravel pile. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Whiskey Pete’s in Primm, Nevada. Photograph: Evan Ratliff "Author Evan Ratliff Is on the Lam. Locate Him and Win $5,000." —WIRED.com/vanish, August 14, 2009 5:38 pm Officially it will be another 24 hours before the manhunt begins. That's when WIRED’s announcement of my disappearance will be posted online. It coincides with the arrival on newsstands of the September issue of the magazine, which contains a page of mugshot-like photos of me, eyes slightly vacant. The premise is simple: I will try to vanish for a month and start over under a new identity. WIRED readers, or whoever else happens upon the chase, will try to find me. The idea for the contest started with a series of questions, foremost among them: How hard is it to vanish in the digital age? Long fascinated by stories of faked deaths, sudden disappearances, and cat-and-mouse games between investigators and fugitives, I signed on to write a story for WIRED about people who've tried to end one life and start another. People fret about privacy, but what are the consequences of giving it all up, I wondered. What can investigators glean from all the digital fingerprints we leave behind? You can be anybody you want online, sure, but can you reinvent yourself in real life? Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg It's one thing to report on the phenomenon of people disappearing. But to really understand it, I figured that I had to try it myself. So I decided to vanish. I would leave behind my loved ones, my home, and my name. I wasn't going off the grid, dropping out to live in a cabin. Rather, I would actually try to drop my life and pick up another. WIRED offered a $5,000 bounty—$3,000 of which would come out of my own pocket—to anyone who could locate me between August 15 and September 15, say the password "fluke," and take my picture. Nicholas Thompson, my editor, would have complete access to information that a private investigator hired to find me might uncover: my real bank accounts, credit cards, phone records, social networking accounts, and email. I'd give Thompson my friends' contact information so he could conduct interviews. He would parcel out my personal details online, available to whichever amateur or professional investigators chose to hunt for me. To add a layer of intrigue, WIRED hired the puzzle creators at Lone Shark Games to help structure the contest. Evan carried glasses and hats for his disguises, prepaid cell phones, and gift cards. Photograph: Evan Ratliff Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg I began my planning months in advance. I let my hair and beard grow out, got a motorcycle license, and siphoned off extra cash whenever I visited an ATM, storing it in a hollowed-out book. One day over lunch, a friend from Google suggested software to hide my Internet address—"but all of these things can be broken," he warned—and how best to employ prepaid phones. I learned how to use Visa and American Express gift cards, bought with cash, to make untraceable purchases online. I installed software to mask my Web searches and generated a small notebook's worth of fake email addresses. I shared my plans with no one, not my girlfriend, not my parents, not my closest friends. Nobody knew the route I was taking out of town, where I was going, or my new name. Not even a hint. If I got caught, it would be by my own mistakes. Friday afternoon, August 14, I arrive in Vegas wearing a suit and sporting my normal brown hair, a beard, and a pair of rectangular tortoiseshell glasses. Carrying enough electronic equipment to stock a RadioShack, I drive straight to a dreary two-story office complex among the strip malls on South Pecos Road and hand over the cashier's check, securing a tiny windowless office. There I set up two laptops, flip on a webcam to track any activity in the office, and leave. Evan’s office on South Pecos Road in Las Vegas. Photograph: Evan Ratliff Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg At CarMax, a used-auto outlet, I then sell my Civic for $3,000. The next day, the first official one of my disappearance, is spent dyeing my hair and goatee jet-black and locking down the security on my laptops—including a third one that I'll carry with me. At 5 am on Sunday morning, the graveyard shift clerk at the Tropicana hotel hands over my $100 cash deposit, barely looking up. If she had, she might have noticed that the man checking out of room 480—wearing a pair of oversize Harry Potter-style glasses, hazel-colored contact lenses, slicked-back hair, and a belt with $2,000 cash hidden in an underside pocket—bears surprisingly little resemblance to the one who checked in two days before. Photograph: Joe Pugliese wayale Found #vanish SF apt (http://bit .ly/6yvkR), talked to lady upstairs said he moved to NY. He can't be in NY apt, according to @wired. 8:27 pm aug 17th moshi77 #vanish Evan bought swim trunks for $78, + UPS of $12. 8/10/09 they had a sale on them at gilt.com 8:10 pm Aug 19th Xov0x another address: 166 GERMANIA ST SAN FRANCISCO, CA 94117 middle name Donald? ;) #vanish 8:27 pm Aug 19th When Sarah Manello heard from a friend about the search for Ratliff, she couldn't resist. A researcher based in Rochester, New York, Manello had long worked with private investigators, digging up information for defense attorneys and tracking down missing people. She quit a few years ago after growing increasingly dissatisfied with the industry's tactics. But her skills remained intact. The initial question she posted on Twitter, under the handle @menacingpickle, was private investigation 101: What was Ratliff's middle name? Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The first trickle of discussion among Manello and other hunters appeared by the morning of August 16, 36 hours after news of the hunt was posted on WIRED.com. The next day it had grown into a deluge. On Twitter, anonymous users dedicated to Ratliff's pursuit sprouted by the hour: @VanishingAct01, @FindEvanRatliff, @EvanOffGrid, @FinderofEvan, @FindThatMan, among others. They organized around the Twitter tag #vanish, which, when placed in a post, allowed the growing horde of investigators to exchange theories, clues, and questions. They created Web sites and blogs and flyers and even a telephone tip line. A programmer in St. Louis, Michael Toecker, started a Facebook group called "The Search for Evan Ratliff." A week later it would have nearly a thousand members. (A countergroup designed to help Ratliff, founded by a banker in Cincinnati named Rich Reder, garnered a few dozen.) What drew all these people? Some of them were lured by the $5,000 bounty. Others were intrigued by the technical challenges of online tracking or the thrill of stakeouts. Some felt that a public dare needed to be answered. For many, Ratliff's flight evoked their own fleeting thoughts of starting over. "It was an adventure," says Matty Gilreath, a grant manager at UC San Francisco, referring to the dozens of hours he spent on the pursuit. "I'm grateful for my career. But there are other things I'd like to do, and this brought up a lot of issues about reinventing yourself." From the WIRED offices, Thompson began doling out information from Ratliff's accounts onto a blog—starting with the final credit card purchases and the FasTrak data. The would-be hunters dissected it as quickly as Thompson could post it. Using two FedEx tracking numbers from Ratliff's credit card bill, Manello managed, in a few aboveboard telephone calls, to find out where the packages had gone and who had signed for them. Hunters scoured the pictures on Ratliff's Flickr page, writing software code to extract information about the camera used and search for other photos it had taken. They combined the FasTrak data with other clues to build maps of possible routes. Within days, they knew that Ratliff was a borderline-obsessive US national soccer team fan and a follower of the English team Fulham. That he had celiac disease, a condition under which he ate a diet entirely free of gluten, a protein found in wheat. That he and his girlfriend had bought an apartment in Brooklyn (in fact, the hunters posted a scan of Ratliff's signature from the deed). That he had recently attended a wedding, sporting a beard, in Palo Alto. They knew of his purchases at Best Buy and Oil Can Henry's and bombarded both businesses with calls. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg What had started as an exercise in escape quickly became a cross between a massively multiplayer online game and a reality show. A staggeringly large community arose spontaneously, splintered into organized groups, and set to work turning over every rock in Ratliff's life. It topped out at 600 Twitter posts a day. The hunters knew the names of his cat sitter and his mechanic, his favorite authors, his childhood nicknames. They found every article he'd ever written; they found recent videos of him. They discovered and published every address he'd ever had in the US, from Atlanta to Hawaii, together with the full name and age of every member of his family. They discovered almost every available piece of data about Ratliff, in fact, except his current location. Some of the items Evan carried. Photograph: Joe Pugliese The Search for Evan Ratliff Facebook wall Michael P. Anderson (Dallas / Fort Worth, TX) wrote at 2:21 pm on August 19th, 2009 Sooooo. If I am trying to disappear wouldn't it make sense to leave a misdirection? I would arrange in advance to have some packages mailed to someplace where I knew that I would not be. Likewise I would make sure that a tab turned up at a local bar somewhere. What we really need to see is an ATM where he takes cash out. Michael Toecker wrote at 7:27 pm on August 19th, 2009 1999 Honda Civic - 4MUN509 CA - Don't ask me how I found out, but it's solid and legal. If you are looking to launch a disappearance, I cannot recommend any location more highly than a big-city Greyhound bus station. A mode of transportation Americans have seemingly left to the poor and desperate, it reeks of neglect and disdain. But for anonymity in the post-9/11 world—when the words "I'll just need to see a photo ID" are as common as a handshake—bus travel remains a sanctuary untouched by security. At the station in Las Vegas, I paid cash for a ticket under the name James Gatz, no ID required. Six cramped hours later I was in Los Angeles. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Lounging on Venice Beach on August 16. Photograph: Evan Ratliff I hopped a city bus to Venice Beach and checked in to 15 Rose, a quaint European-style hostel that I'd found online. The laid-back day manager sympathized with my story of losing my credit cards and driver's license and showed me to a clean, spare room with free Wi-Fi. So began what I thought might be a few pleasant days on the beach: no phone calls to return, no deadlines to hit. Just my new life, stretching leisurely out before me. When I flipped open my laptop and saw my private information spilling onto the Web, however, I got my first taste of a soon-to-be-permanent state of fitful anxiety. I'd signed up for it, of course. But actually living the new, paranoid reality felt different. Absurd ideas suddenly seemed plausible. They'd contacted my cat sitter; would they kidnap my cat? Email was choking the inbox of the account WIRED had made public, [email protected]. Most of the messages consisted of efforts to subtly or not-so-subtly trick me into revealing my location by replying or visiting a Web site designed to trap my Internet protocol (IP) address, which maps to a physical location. I also started getting what I came to think of as little plea bargain offers: "Send me a picture and the code word and I'll split the $5K 50/50." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Fortunately, while I was shocked by the intensity of the pursuit, I had anticipated the tactics. To keep my Web surfing from being tracked I often used a piece of free software called Tor, designed to protect the Internet activities of dissidents and whistleblowers around the world. Tor masks a computer's IP address by diverting its requests through designated routers around the world. So when I logged in to Gmail from IP 131.179.50.72 in Los Angeles, the logs showed my request originating from 192.251.226.206 in Germany. But as my friend from Google had reminded me, no security is unbreakable, so I'd added another layer: Vegas. I used the laptop I carried with me to log in remotely to my computers there, using free software from LogMeIn.com. The Vegas machines, in turn, were running Tor. Anyone clever enough to untangle those foreign routers would get only as far as a laptop sitting in an empty office on South Pecos Road. Meanwhile, in LA, I meticulously kept up my physical disguise. One afternoon, a few blocks from my hotel, I had a chance to test it. A camera crew, fronted by an Internet news correspondent named Amanda Congdon, was corralling passersby for man-on-the-street interviews about their views on swine flu. I volunteered myself as an interview subject. A few days later, I found my interview on the Sometimesdaily .com site, Venice Beach in the background. It was time to get out of LA. socillion @dimitrirose the only IP not part of the Tor network is in Los Angeles and is owned by Trit Networks #vanish 5:33 pm Aug 20th menacingpickle @alanbly I personally would not hide out in Vegas as every single movement is captured on camera 7:15 pm aug 2oth evanoffgrid Hunch Evan started growing out his hair/grew beard knowing his friends wld give out info, now he's bald or crewcut and blond #vanish 6:06 pm aug 26th labfly on yet another evan stake out :) following a hunch #vanish 6:27 pm Aug 27th On August 20, a 16-year-old high school student in Portland, Oregon, named Jonathan Mäkelä saw a link to the story about the WIRED contest on Hacker News. Mäkelä was a casual participant in the online community 4chan, whose pranks sometimes involved tracking down documents concerning unsuspecting targets. Mäkelä had grown fascinated by how much intel could be legally dug up online. Here was a guy, Ratliff, who invited people to use that same intel to find him. Now that was interesting. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Mäkelä began using a Twitter account under an anonymous handle, @socillion, and started pulling apart Ratliff's IP addresses. He quickly marshaled a collection of online tools with which he could peg IPs to a physical location and Internet service provider, often triangulating between several sites. By now, other hunters had determined that Ratliff's IPs—which Thompson published several times a day after logging in to Ratliff's email—appeared to be useless nodes from the Tor network. But Mäkelä meticulously verified that each was indeed a Tor node. He shared his information with the crowd and then got feedback in return. Eventually, he figured, the target might make a mistake. Mäkelä quickly became one of the most active investigators, posting ideas to Twitter at least a dozen times a day. But this public collaboration, he soon realized, was itself a problem. The hunters were benefiting from their collective brainpower, but Ratliff could follow their thoughts just as easily. "Groups need to take this private," he posted to Twitter on August 20, "otherwise we are guaranteed never to win." Mäkelä set up a secure chat room and gave the password to only those he could verify weren't Ratliff. To [email protected] From Mike Date Fri, Aug 21, 2009 1:47 AM Subject Your Disappearance I want you to know right now that this is not an attempt to track you down ... I want to know firsthand from you, what is it like disappearing? How does it feel? Are you lonely? Do you miss life? Is it liberating to be free from everything? I ask these questions because the idea of leaving and starting a new life entertains me. My plan involved leaving LA for good by midday Friday, August 21, and heading east. But before I left, I wanted to give my investigators a parting diversion, something to keep them fixated on the West Coast. So at 11:55 pm Thursday night, I inserted my bank card into an ATM in nearby Santa Monica, deposited the $3,000 car check, and took out $300 cash, the maximum single-day withdrawal. Figuring that as long as I was revealing my location to the world, I might as well pad my reserves, I withdrew another $300 at 12:01. Then I treated myself to a credit card purchase: a $13 vodka martini at the nearby Viceroy hotel. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The Trackers: Jeff Leach and Brock Fillinger stalked Ratliff in New Orleans. Photograph: Joe Pugliese Friday, I woke up at dawn and found the hostel Wi-Fi down. Blind to my pursuers, I decided to risk a last jog; I donned a baseball cap and trotted down along the water's edge. As I turned around to head back, a helicopter came up the beach from the opposite direction, flying low. It stopped and hovered between me and a group of surfers floating idly on their boards. I'm not sure when the thought entered my head, but when it did, it lodged there: Was it possible that someone had seen my ATM transactions, called up a friend with a helicopter, and sent them out to scan the beach for me? The correct answer was no. Deep down I knew this. But there the chopper was, hovering. I jogged a little bit farther, and it seemed to ease toward me, staying not-quite-directly overhead. I stopped to see if it would pass over. It didn't. The beach was empty. I jogged up to a lifeguard stand, putting it between me and the helicopter, and waited. A few seconds later, the nose crept around the building and back into my line of sight. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg In that moment, reason evaporated. I took off toward the boardwalk, a lone figure sprinting across the sand at dawn. Seen from the air, I must have appeared, at this point, worth following. Whatever the reason, the helicopter kept coming. I reached the pavement and turned down a side street, bolted up one alley and down another, and finally ducked under a tree, lungs burning. I could still hear the thump-thump of the blades. I waited, my thoughts spinning out into ever-wilder fantasies. Were they radioing a ground team to drive by and yell "fluke"? Had they already staked out my hotel? Really? All for $5,000? A few minutes passed and I heard it drift away. I took off again down the alley and ducked into a convenience store. There was an old pay-by-the-minute Internet terminal, and I slipped in a dollar. The ATM transactions hadn't even posted to my account yet. alanbly he just hit an ATM in Santa Monica #vanish 11:51 AM Aug 21st lookingforevan @combobulate #vanish. His phone has been off for days. I think he's using a prepaid. 1:26 PM Aug 21st labfly okay now i'm walking up to 30 something guys that look anyting like evan & people r thinking i'm nutz 4:14 PM Aug 21st socillion @RatliffPatrol According to the statements its at 1300 4TH ST SANTA MONICA CA whre thrs a wells fargo. street view blckd by bus tho #vanish 1:23 AM Aug 22nd When Thompson posted Ratliff's ATM transactions online, late the morning of August 21, the pursuit kicked into high gear. For the first time, Ratliff had pegged himself to a specific place, and hunters hit the streets to try to nab him. Mäkelä pinpointed the exact location of the ATM in Santa Monica. One man set about frantically calling restaurants in the area, asking whoever picked up the phone to scan the crowd for someone who met Ratliff's description. Manello called the car dealer in Vegas, then she found a bookstore owner who claimed to have seen him. In the private chat room that Mäkelä ran as Socillion, however, the consensus seemed to be that Ratliff had moved on. They discussed and discarded strategies ranging from the clever to the outlandish to the completely illegal. Somehow, they had to figure out how to get ahead of him. "Right now, Evan is controlling us," a participant named AtavistTracker wrote. "Evan's had over two months to plan this. We need to alter that plan. I like disinformation." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg "Me too," Socillion replied. "Fight with his tools." EvanOffGrid remember we can't trust messages from Evan. 8:46 am Aug 27th how2stalk Latest Evan Google Earth file: http://bit.ly/nNh7K #vanish 9:39 am aug 27th TrackEvan Update: "Evan's Reading List" now on http://www.trackevan.com/ #vanish 7:24 pm Aug 27th bellyscratcher #vanish Contacting more PIs, will update when done. 12:13 am Aug 28th By the end of the first week, the deception had already begun to wear me down. Lying about your identity involves more than just transgressing some abstract prohibition against deceit. It means overcoming a lifetime of built-up habits, from a well-rehearsed life story to the sound of your own name. When I convinced people that I really was James Donald Gatz, I occasionally felt a mischievous thrill. Most of the time, however, I felt awful. The people I encountered weren't credulous; they were just nice. I left LA with a band called the Hermit Thrushes , trading gas money for a spot onboard a converted retirement-home shuttle van that served as their tour bus. An indie rock group composed of college grads from Philadelphia, they'd responded to an ad I posted on craigslist, under the name Don, needing a ride to Austin or New Orleans. We rattled along from show to show: LA to Tempe to Las Cruces, up to Lubbock and Tulsa, east to Fayetteville, then north toward Chicago. The band played whiskey bars, coffee shops, and rowdy house parties. We crashed on living room floors or crammed into the seats of the bus, and, once, on the grass at a rest stop in Texas. The band was serious about its music but unperturbed about much else, and I settled into a role somewhere between lazy roadie and moneyed patron, pulling $100 bills from my belt at gas stations. On board, I staked out the bus's backseat, where I could use my laptop without anyone looking over my shoulder. With a $150 wireless broadband card from Virgin Mobile, the only nationwide service that didn't require a credit check, I had almost uninterrupted online access. On tour with the Hermit Thrushes. Photograph: Evan Ratliff Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg So I passed the long hours on the road building up an online life for my new identity. I'd opened a Facebook account under "GatzJD" and a Twitter account under @jdgatz (which I kept open to the world for days, cataloging my location for posterity, before panicking and locking it from public view). For the average person, populating an online social network account is as easy as finding your friends, connecting to their friends, and watching the virtual acquaintances pile up. As Gatz, though, I had no actual friends. Instead, I set about finding people who would accept my friendship automatically, and soon my profile was overrun with multilevel marketers and inspirational speakers. Enough, I thought, to convince potential real acquaintances who didn't look too hard that I wasn't friendless. I'd been set to depart the tour in Lubbock, Texas, but the band was cool and I was safe, so I kept going. On the afternoon of August 26, the bus finally pulled into St. Louis, where the band had a college radio gig scheduled and I had a plan to get to the train station. A half hour later, listeners to KWUR heard the Hermit Thrushes dedicate their show to a mysterious single-named traveler, Don, headed for New Orleans. The Coder: Jeff Reifman designed a Facebook application to spy on Ratliff. Photograph: Joe Pugliese I looked out my office window (about 6 floors up) about 11AM and spotted Evan walking up 1st avenue from the direction of Qwest Field—he was wearing a backpack and heading into downtown ... My heart started to race as I ran out of the office and hit the elevator button. Once I got to the street Evan w/ backpack was nowhere to be found ... Walking to the bus that evening I surveyed the faces of every stranger I walked past—looked at the eyes, the hair, finding at least 3 possible Evans on my 15 minute walk to the bus. I think I was going insane! —Jeremy Thompson aka @evan_ratliff On August 24, a former Microsoft group program manager in Seattle named Jeff Reifman read about the hunt in WIRED. Reifman, self-employed these days, had recently launched a series of grant-funded Facebook applications to study the engagement of young people with the news. From a technical standpoint, the contest seemed intriguing. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg On August 27, working on a desktop in his living room, he created Vanish Team , a Facebook app dedicated to information and discussion about Ratliff. He announced it on Twitter, and people began clicking over to check it out. Reifman was late to the party, however; most of the real intel swap stayed on Twitter or in Mäkelä's secure chat room. Down in Portland, Mäkelä was learning that it wasn't secure enough. One night, as a San Diego-based hunter was making the drive to Las Vegas—where the chat room believed Ratliff was headed—an insider emailed Ratliff to tip him off. When Thompson posted the anonymous email on the WIRED blog, it was the hunters' turn to be paranoid. Mäkelä moved to another chat room, and then started another, jettisoning all but a few of his most trustworthy correspondents. One of the people he kicked out, after a set of heated exchanges, was Reifman. SearchForEvan Ok, best guesses ... what is Evan doing RIGHT NOW? #vanish 9:40 pm aug 28th From St. Louis I took a bus to Carbondale, Illinois, and caught a train south to New Orleans. To get around Amtrak's mandatory government ID requirements, I booked online, using my real name, and picked up the ticket from a machine at the station. I still might need an ID on the train, so to obscure myself to anyone who might get into the Amtrak database, I booked under my middle name and misspelled my last name ever so slightly, leaving out the l. I'd chosen New Orleans months before, distant enough from the coasts to provide obscurity but familiar to me from trips I'd taken years before. Showing up in a city with no friends, no contacts, no credit cards, and no ID is itself a discomfiting experience, and having a basic grip on the layout eases the alienation. After four days in a vacation condo, rented from an absentee landlord who accepted PayPal, I found a cheap one-bedroom apartment around the corner. The next day I signed my well-practiced J. D. Gatz scrawl on the lease. The landlord, after a friendly chat, was ready to hand over the keys. He would, he said, just need to see my driver's license. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg I'd been working for months to establish James Donald Gatz as a separate identity. The name itself—the one that Jay Gatsby sheds to start over in The Great Gatsby—was easy for me to remember. More important, due to the prolific amount of Gatsby analysis online, it was basically un-Googleable. The middle name was my own, but Mr. Gatz received an entirely new birthday: July 1, 1976, shaving about a year off my age. Business card for Bespect LLC. Photograph: Evan Ratliff He also got a "research firm," Bespect LLC, registered in the state of New Mexico and complete with a logo—a bespectacled cartoon man with a mustache—and a Web site at Bespect.com. Gatz's PayPal account was funded using gift cards. I'd even ordered up a gift card with his name on it that looked to the casual eye like a real credit card. My new landlord glanced at the business card and flimsy home-laminated "visiting scholar" credentials that I slid across the table. "Bespect.com, eh?" he said. "Interesting. These will do." He turned around, photocopied them, and dropped the copy in a folder along with my lease. At this point, my new life seemed, superficially at least, satisfactory. My days were spent jogging along the Mississippi, haunting the coffee shops and jazz bars of my adopted neighborhood, and exploring the city by bike. I located a soccer bar and even got a one-night job selling beer and nachos for tips during a Saints game at the Superdome. The gnawing flaw in the idyllic life of J. D. Gatz was that I did all of these activities alone. It wasn't just that I had no friends. It was that the interactions I did have were beyond superficial. They were fake. My online social networks were populated with strangers; my girlfriend was thousands of miles away; my family knew about me only from news reports and online speculation. I'd always prided myself on being comfortable with solitude, but this wasn't normal solitude. It was everyone-is-out-to-get-me isolation. What to the hunters felt like an intricate puzzle felt real enough to me—and there was no one around to laugh and tell me otherwise. Instead there was just me, staring into my laptop all day, wondering if it was safe to go out and get the paper. For the first time in my life, I couldn't sleep. One night I awoke at 4 am drenched in sweat, having dreamed that a childhood friend turned me in. vanishteam Evan shaved his cat on Aug 19 http://bit.ly/zrO86 - after shaving his own head? It's the easiest and coolest way to chg appearance #vanish 11:38 PM Aug 28th vanishteam Am pretty certain @theatavist is openly blogging and posting photos of his travels somewhere on the net. #vanish 2:57 PM Sep 1st vanishteam Hope @theatavist returns safely or we're all suspects! #vanish 6:41 PM Sep 2nd Out in Seattle, Reifman wasn't generating solid leads. Through a convoluted set of clues, some of which later turned out to be inaccurate, he developed a theory that the target had headed to San Diego. Reifman posted it to the Vanish Team site, but nothing came of it. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg He decided to try a different tack. Instead of using the Vanish Team application to gather news about Ratliff, he'd use it to track him. He installed 38 lines of new code. It was rudimentary and unlikely to work if Ratliff had set up Tor, his anonymity software, correctly. But it gave Reifman a tool to easily pick out the IP addresses of Facebook visitors to Vanish Team. Ratliff might be among them. He'd be the guy without many friends. jdgatz Just arranged to sublet cool apt yesterday. Upstairs back of shotgun house, called a "camel back" apartment. Sounds dirty, but it's not. 2:33 PM Aug 30th jdgatz I'm not sure I've ever stayed up all night before in order to (partially) re-shave my head before a morning flight. But desperate times... 12:51 AM Sep 5th jdgatz I'm learning to love Amtrak, but anything over 5 hrs w/out sleeping car = yearning for the development of air travel. Wait, they have that? 12:51 AM Sep 5th Illustration: Oliver Jeffers Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg In constructing a proper disguise, there is no place for vanity or pride. Altering your appearance, after all, is not about convincing people. It's about misdirection, diverting their attention from the physical features you are unable to change and toward the ones you can. Success often involves making yourself look older, fatter, nerdier, sleazier, or otherwise more unpleasant than you were before. The goal is to be overlooked, ignored, or, sometimes, noticed and then dismissed with a chuckle. It was the last to which I aspired as I walked through security at the Memphis airport, on Saturday morning, September 5, barely resembling the face on the real ID I showed at the security line. My hair was shaved clean on top with a razor but left short-cropped on the sides and back, in the manner of advanced male pattern baldness. The bald spot had been enhanced with tanning cream, compensation for the sudden paleness of my newly shorn dome. I wore a borderline-creepy mustache, above which a new set of prescriptionless glasses were backed by brown prescription contacts. I twirled a fake wedding band on my finger. A hands-free cell phone headset dangled from my ear. Unable to completely abandon the hobbies of my previous life, I was headed to Salt Lake City for the US World Cup qualifying soccer match against El Salvador. The logistics had been complicated: a train to Memphis, followed by a flight to San Francisco (which needed to be under $250, the maximum gift card available) that stopped in Salt Lake. The greater problem would be avoiding the hunters. They had long speculated that I might attend the game, and I'd seen stakeout rumors on Twitter. So I bought two fully refundable tickets to Salt Lake on my credit card for September 4, originating in LA and Portland—misdirections I knew they'd discover and that I hoped would lead them to the airport on the wrong day. I'd anonymously emailed a prominent hunter a link to the Venice Beach "swine flu video" to fix my previous appearance in their minds. Finally, I'd unmasked my computers' address in Las Vegas several times, turning off Tor while visiting Web sites that I knew were trapping IPs. Evan’s game-day disguise. Photograph: Evan Ratliff Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But it was my disguise that gave me confidence as I breezed off the plane in Salt Lake City, dressed in a suit and tie, jabbering loudly to imaginary business contacts on my hands-free. I met an accomplice, an old friend also dressed as a low-rent sales rep; we dodged a suspicious lurker at the baggage claim. Then we checked in to a downtown hotel and changed into our game-day disguises. For him: a red, white, and blue afro wig. For me: waving stars and stripes painted atop my head, augmented with a bulky pair of American flag sunglasses and a red clown nose. Walking to the stadium, we passed several people who seemed to be doing nothing other than scanning the crowd. "I've already seen a few people that I thought could be him," one man murmured as we passed a few feet away. socillion @nxthompson #vanish a Wired reader/tw telecoms hostmaster tells me that the LV IPs are from a biz @ 4760 S. Pecos Road, Las Vegas 89121 3:48 pm sEp 3rd viequense @EvanOffGrid We were pretty sure we saw Evan last nt but we were also pretty drunk. Got pick & password. #vanish 8:06 am sep 5th viequense @EvanOffGrid It was last night, maybe about 11pm at a bar in SLC where we were having a USMNT party for the game tomorrow. 8:16 am sep 5th For the hunters, it was again time to put boots on the ground. But where? Mäkelä, jumping on the real IP address, called a technician at an ISP in Las Vegas who happily revealed the address on South Pecos Road. The hunters puzzled over the businesses listed there, wondering if Ratliff somehow had a friend among them. For now, though, the action was headed for Salt Lake City. One woman bought a refundable ticket to get through security and stake out departure gates at the Portland airport. A man did the same for arrivals in Salt Lake City, waiting for seven hours over two days. Mäkelä generated a map of all the known gluten-free eateries in the area, and hunters hit pregame parties. All that turned up were look-alikes. That Friday afternoon in Seattle, Reifman was sorting through more Facebook profiles. Recalling Thompson's statement that Ratliff would not just be hiding but trying to make new friends, Reifman had decided to expand his search to include Vanish Team visitors with up to 50 Facebook friends. He pulled up the profile for a James Donald Gatz, who seemed to be visiting Vanish Team regularly. The name didn't ring a bell, but the photo looked familiar. Then he realized where he'd seen that look before: the swine flu video. He flipped back and forth between the two, and soon he was positive. Gatz was Ratliff. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg At first, he was giddy. All he needed to do was friend one of Gatz's friends or convince one to reveal their new pal's location. Looking through the profile, though, he realized that Ratliff had populated his account with what amounted to Facebook automatons. Reifman tried sending messages to a few, telling them about the hunt. No luck. He decided to try Twitter. Eventually, he typed in "jdgatz" and found the account, locked from public view. Friends of @jdgatz could see his posts, but the general public, including Reifman, couldn't. With a simple Google search for "jdgatz," Reifman located an archived, unprotected version of jdgatz's posts from the previous week. Gatz, at least at that point, had been revealing his location as he moved around. Maybe he'd do it again. Currently, though, gaining access to Gatz's daily feed would require his permission. Not wanting to spook the target, Reifman tried to enlist the help of one of Gatz's current connections, who would already have access. Again, most were multilevel marketers or auto-reply bots. But he managed to find three real people among them: a Hawaii real estate agent, a Segway aficionado in New Zealand, and a blogger in Atlanta. Reifman convinced all three to keep him apprised of whatever Gatz wrote. At 4 am on Sunday morning, Reifman's girlfriend came downstairs and found him staring into the screen. "What are you doing?" "I think I've found Evan." The Search for Evan Ratliff Facebook wall Landon Anderson (Salt Lake City, UT) wrote at 8:26pm on September 6, 2009 EVERYBODY!!!!! I do not know how to use Twitter, so I am posting this information here so that someone can post it on Twitter. Evan is in ATLANTA. He landed there at about 8:10 pm Atlanta time today. He showed up to SLC airport this morning, canceled the itinerary from SLC to SFO, purchased a new ticket to Atlanta via Denver. I am sure my knowledge will soon be confirmed by Nicholas. I did nothing illegal ... just have connections. The morning after the soccer game, I caught a flight to Atlanta via Denver. After landing at Hartsfield Airport, I rushed off the jetway, a businessman in a hurry. Safely a few gates away, I opened my laptop for a routine check of the WIRED blog. Headline: "Evan Ratliff will arrive in Atlanta in 5 minutes." I slammed the laptop shut and took off. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg All of the Hartsfield terminals funnel out to a single exit. But as a former Atlanta resident, I knew one other way out, a solitary revolving door from the T Gates leading to a remote part of baggage claim. It was eerily empty when I got there. I slipped out, hustled to the public transit station at the far end, and caught a train into town. Only later would I learn that a hunter in Atlanta arrived minutes after I'd left, sprinted to the trains, and frantically canvassed the passengers. I crashed for a few hours at the house of a friend—one of only a few I was willing to reach out to, knowing that Thompson was posting interview transcripts of his talks with them. The next morning I caught the first Amtrak train out, sinking down in my seat for the 12-hour ride back to New Orleans. A few times en route I opened my laptop to check on reports of the hunters scurrying furiously around Atlanta. On Twitter, the guy running the Vanish Team Facebook application kept announcing new scoops, exhorting people to check out his site. Each time, I'd click over to Facebook, using James Gatz's account. What scoops? Vanish Team seemed like all bluster. At this point, I'd stopped logging in to my Vegas computers for anything but the riskiest Web surfing. This was partly out of a growing laziness; the whole process took longer than dialup circa 1993. I also figured that I could freely visit Facebook pages like Vanish Team. Anyone who built an application to use on a corporate site, I assumed, would need cooperation from the company to track their users. Once back safely in New Orleans, I decided to redouble my efforts to socialize, both online and in real life. For starters, I opened up my @jdgatz Twitter feed to the public—maybe I could connect with some local friends. I searched for New Orleans businesses I might follow. One was a local gluten-free pizza place I'd wanted to go to called NakedPizza. From Jeff Reifman Date Mon, Sep 7, 2009 9:48 PM Subject Re: ALERT Evan in Jacksons Gap, Alabama — Got a clear lead just now By Monday, Jeff Reifman had mentioned the @jdgatz account to a few active hunters, including Sarah Manello and Mäkelä, with whom he'd patched things up. When Ratliff opened his Twitter feed to the public, Reifman created two fake accounts of his own—crafted to look like automated Twitter bots, so as not to raise Ratliff's suspicion—and started following the account. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Then Monday night, Reifman noticed James Gatz logging in from a new IP address: 74.180.70.233. According to the database Reifman was using, the address pointed to Jacksons' Gap, Alabama. After he emailed his select group of trusted hunters, Mäkelä ran the address through his own little triangulated system and discovered where it actually originated from. Two minutes later he sent a one-line response to Reifman: "That IP is in New Orleans." Reifman flipped over to the @jdgatz Twitter feed and noticed that the number of accounts Gatz was following had gone up by three—all New Orleans businesses. He looked up NakedPizza's Web site and fired off an email explaining the hunt. "I have accurate information that Evan has arrived in New Orleans and plans to go to NakedPizza Tuesday or Wednesday," he wrote. A few minutes later, he followed up. "I forgot to mention," he said, "that we know Evan has shaved his head either partially (male pattern bald) or fully." Reifman informed his fellow hunters, and Manello spent the evening dialing 50 hotels near the restaurant, asking for a James Gatz. The next morning when Jeff Leach, cofounder of NakedPizza and a tech-savvy entrepreneur, got the email, he thought at first it was a scam. But he passed it along to his business partner, and after delving into the hunt information online, they concluded it was real. Leach decided to help. To Jeff Reifman From Jeff Leach Date Tue, Sep 8, 2009 8:17 AM We will catch him. Tuesday, September 8, 7 am: Just seven days to go. I awake in my apartment in New Orleans, relieved to find no online indication of anyone wise to my location. Aside from a few random new followers to my Twitter feed, all of whom seem like automated bots, nobody seems to be paying attention to my fake accounts either. View from the porch of Evan’s New Orleans apartment. Photograph: Evan Ratliff Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg I use a gift card to book a flight to New York City on September 15, the final day of my disappearance, and hatch plans to surprise Thompson in his office using a fake security badge. I've been communicating sporadically with my editor through a public blog—I'd post something, he'd read it, delete it, and then post his response. Before Salt Lake City, I'd boasted that I could survive the month, "just by keeping my head down and being careful with my phones and IPs." Now WIRED has decided to up the stakes, offering me $400 for each of a series of challenges I complete. And I could use it. As much as any other factor—personal gall, or endurance, or discipline—staying on the run requires an abundance of cash. I've already nearly spent the three grand I brought with me. Besides, I made it through the Salt Lake City gauntlet and survived a near miss in Atlanta. I can do this. The first two challenges—clues to which are embedded, with the help of Will Shortz and Lone Shark Games, for the hunters to find in the New York Times crossword puzzle—are to go to the 50th story of a building and to attend a book reading. Checking online, I identify only two buildings in downtown New Orleans of 50 stories or taller, and I choose One Shell Square. At the security desk, back in my businessman disguise, I step up and announce that I'm here to visit the law firm occupying the upper floors. "Just sign in here. And we'll need to see your ID." "Well, I've lost mine. Will a business card and a credit card do?" Elevator in One Shell Square. Photograph: Evan Ratliff Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg In two minutes, I'm on the 50th floor, video camera rolling. Later, as I wander home through the French Quarter, a street vendor sidles up beside me with some friendly unsolicited advice. "Hey buddy," he says, gesturing to my haircut. "You gotta shave the rest of that off, man." That same morning, Leach, of NakedPizza, calls Reifman, and the two begin comparing notes. Leach searches through his Web site's logs, finding that IP address 74.180.70.233—aka James Gatz—visited NakedPizza.biz late the previous evening. By 11 am, Leach has briefed all of his employees on the hunt. If they see the target, he explains, they need to say "fluke" and take a photo. He creates a folder on the company network with pictures for them to study. One is a Photoshopped mock-up of Ratliff, bald. Brock Fillinger, also a cofounder, whose own pate is clean-shaven, heads over to stake out the tours at Old New Orleans Rum, another business Ratliff was following on Twitter and that Reifman had contacted. "Hey," the woman behind the desk says as Fillinger lingers nearby, "are you that WIRED writer?" Snide street comments aside, I've already decided to shave the rest of my head and mustache. My acquisition of actual friends will require looking less creepy. I change into casual clothes, grab a fedora, and ride my bicycle to the barber. Evan after shaving his head. Photograph: Evan Ratliff Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg At 5:20 I'm completely bald, and I'll have to hustle to make it across town for the book reading I plan to attend. At 5:48, Leach and Fillinger are watching both entrances to the Garden District BookShop. They're expecting someone "wigged up," someone who looks like he doesn't quite belong. But the reading started promptly at 5:30, and there is no sign of Ratliff. Leach sends a text message to Fillinger. This looks like a bust. They meet up out front, ready to move on. It's surreal, in those moments when I stop to think about it. Scores of people have studied my picture, stared into those empty eyes in the hopes of relieving me of thousands of dollars. They have stood for hours, trying to pick out my face in a crowd. They've come to know me like we've been friends for years. It's weirdly thrilling, in a narcissistic kind of way, but also occasionally terrifying. I almost ride past the bookshop before I see the sign, tucked into a tiny shopping center. I stop at the corner and pull out my bike lock. Two men stand on the stairs outside, facing the street. They glance over at me. My first impulse is to ride away. But at what point do I separate caution from self-delusion? Not every out-of-place person is looking for me. Tired from the bike ride, tired of the corrosive suspicion, I decide to walk past them on the sidewalk, making no move toward the bookstore. Just a local, heading down the street to visit a friend. "Hey," Leach calls out from the stairs, taking a hesitant step toward me. I freeze and stare back helplessly. "You wouldn't happen to know a guy named Fluke, would you?" To Nicholas Thompson From Laurie Ambrose Date Wed, Sep 9, 2009 12:54 PM Subject My #Vanish Story Why would a middle-aged woman with virtually no technical knowledge be interested in following the Evan's Vanished story on Twitter? You see, my father walked out one morning in Sumter, South Carolina, kissed the wife and two young children good-bye as if he was going to work as always, and disappeared for 12 years. He was around Evan's age. He sent the family a telegraph a few days later asking them not to look for him. To this day, no one knows anything about his personal life during those years. I guess I'm hoping to have some clues to some of my questions. At first I was angry: at myself for getting caught and losing the money, at WIRED for tempting me with the challenges. But that was soon replaced by the thrill of being redeposited in my own identity, with a family, a partner, friends, and a past I didn't have to hide. I packed up my apartment, rented a car, and visited my parents in Florida. Then I bought a plane ticket home. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Leach and Reifman had agreed to split the prize money, but they both ended up giving it all to Unity of Greater New Orleans, a charity helping the city recover from Hurricane Katrina. Socillion started his junior year of high school. The online chatter dissolved as quickly as it had formed. And what of our original questions? Had I shown that a person, given enough resources and discipline, could vanish from one life and reinvent himself in another? I thought I had, though only up to a point. Obviously the smarts and dedication of the hunters had overwhelmed my planning and endurance. Along the way they'd also proven my privacy to be a modern fiction. It turns out that people—ordinary people—really can gather an incredible dossier of facts about you. But a month later, life was back to normal and no one was taking any interest. More than all that, I'd discovered how quickly the vision of total reinvention can dissolve into its lonely, mundane reality. Whatever reason you might have for discarding your old self and the people who went with it, you'll need more than a made-up backstory and a belt full of cash to replace them. For weeks after the hunt ended, I still paused when introducing myself and felt a twinge of panic when I handed over my credit card. The paranoid outlook of James Donald Gatz was hard to shake. Even now, my stomach lurches when I think back to the night I got caught. "You wouldn't happen to know a guy named Fluke, would you?" Right after it happened, I rode my bike back to my apartment and sat in the air-conditioning, unsure what to do. Finally I got online and logged in to the hunters' private chat room for the first time. Rich Reder, founder of the Facebook countergroup designed to help me stay hidden, had infiltrated the room and sent me the password. Just a little too late. I found Mäkelä there, still logged in. I asked him why he was hanging around a chat room dedicated to catching a guy who'd already been caught. "Just lurking," he wrote. "Working out the moles." After a while I signed off, closed my laptop, and walked down the street to J. D. Gatz's local dive bar. I ordered a whiskey and tried to tell the bartender how I abandoned my life and then got it back. For the first time in weeks, someone didn't seem to believe my story. Stories From the Hunt Media, From TV to Mags to Blogs, Followed the Hunt Social Networking Sites at Center of Coast-to-Coast Coordinated Search WIRED Tests Writer With a Series of Bold Challenges You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Contributor X Topics Wired Issue 17.12 Vanish WIRED Classic longreads privacy identity Lauren Smiley Andy Greenberg Brandi Collins-Dexter Steven Levy Angela Watercutter Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"The Crypto-Currency | The New Yorker"

"https://www.newyorker.com/magazine/2011/10/10/the-crypto-currency"

"Newsletter To revisit this article, select My Account, then View saved stories Close Alert Search The Latest News Books & Culture Fiction & Poetry Humor & Cartoons Magazine Puzzles & Games Video Podcasts Goings On Shop Open Navigation Menu Find anything you save across the site in your account Close Alert Dept. of Technology The Crypto-Currency By Joshua Davis Save this story Save this story Save this story Save this story It’s not clear if bitcoin is legal, but there is no company in control and no one to arrest. Illustration by Grafilu There are lots of ways to make money: You can earn it, find it, counterfeit it, steal it. Or, if you’re Satoshi Nakamoto, a preternaturally talented computer coder, you can invent it. That’s what he did on the evening of January 3, 2009, when he pressed a button on his keyboard and created a new currency called bitcoin. It was all bit and no coin. There was no paper, copper, or silver—just thirty-one thousand lines of code and an announcement on the Internet. Nakamoto, who claimed to be a thirty-six-year-old Japanese man, said he had spent more than a year writing the software, driven in part by anger over the recent financial crisis. He wanted to create a currency that was impervious to unpredictable monetary policies as well as to the predations of bankers and politicians. Nakamoto’s invention was controlled entirely by software, which would release a total of twenty-one million bitcoins, almost all of them over the next twenty years. Every ten minutes or so, coins would be distributed through a process that resembled a lottery. Miners—people seeking the coins—would play the lottery again and again; the fastest computer would win the most money. Interest in Nakamoto’s invention built steadily. More and more people dedicated their computers to the lottery, and forty-four exchanges popped up, allowing anyone with bitcoins to trade them for official currencies like dollars or euros. Creative computer engineers could mine for bitcoins; anyone could buy them. At first, a single bitcoin was valued at less than a penny. But merchants gradually began to accept bitcoins, and at the end of 2010 their value began to appreciate rapidly. By June of 2011, a bitcoin was worth more than twenty-nine dollars. Market gyrations followed, and by September the exchange rate had fallen to five dollars. Still, with more than seven million bitcoins in circulation, Nakamoto had created thirty-five million dollars of value. And yet Nakamoto himself was a cipher. Before the début of bitcoin, there was no record of any coder with that name. He used an e-mail address and a Web site that were untraceable. In 2009 and 2010, he wrote hundreds of posts in flawless English, and though he invited other software developers to help him improve the code, and corresponded with them, he never revealed a personal detail. Then, in April, 2011, he sent a note to a developer saying that he had “moved on to other things.” He has not been heard from since. When Nakamoto disappeared, hundreds of people posted theories about his identity and whereabouts. Some wanted to know if he could be trusted. Might he have created the currency in order to hoard coins and cash out? “We can effectively think of ‘Satoshi Nakamoto’ as being on top of a Ponzi scheme,” George Ou, a blogger and technology commentator, wrote. It appeared, though, that Nakamoto was motivated by politics, not crime. He had introduced the currency just a few months after the collapse of the global banking sector, and published a five-hundred-word essay about traditional fiat, or government-backed, currencies. “The root problem with conventional currency is all the trust that’s required to make it work,” he wrote. “The central bank must be trusted not to debase the currency, but the history of fiat currencies is full of breaches of that trust. Banks must be trusted to hold our money and transfer it electronically, but they lend it out in waves of credit bubbles with barely a fraction in reserve.” Banks, however, do much more than lend money to overzealous homebuyers. They also, for example, monitor payments so that no one can spend the same dollar twice. Cash is immune to this problem: you can’t give two people the same bill. But with digital currency there is the danger that someone can spend the same money any number of times. Nakamoto solved this problem using innovative cryptography. The bitcoin software encrypts each transaction—the sender and the receiver are identified only by a string of numbers—but a public record of every coin’s movement is published across the entire network. Buyers and sellers remain anonymous, but everyone can see that a coin has moved from A to B, and Nakamoto’s code can prevent A from spending the coin a second time. Nakamoto’s software would allow people to send money directly to each other, without an intermediary, and no outside party could create more bitcoins. Central banks and governments played no role. If Nakamoto ran the world, he would have just fired Ben Bernanke, closed the European Central Bank, and shut down Western Union. “Everything is based on crypto proof instead of trust,” Nakamoto wrote in his 2009 essay. Bitcoin, however, was doomed if the code was unreliable. Earlier this year, Dan Kaminsky, a leading Internet-security researcher, investigated the currency and was sure he would find major weaknesses. Kaminsky is famous among hackers for discovering, in 2008, a fundamental flaw in the Internet which would have allowed a skilled coder to take over any Web site or even to shut down the Internet. Kaminsky alerted the Department of Homeland Security and executives at Microsoft and Cisco to the problem and worked with them to patch it. He is one of the most adept practitioners of “penetration testing,” the art of compromising the security of computer systems at the behest of owners who want to know their vulnerabilities. Bitcoin, he felt, was an easy target. “When I first looked at the code, I was sure I was going to be able to break it,” Kaminsky said, noting that the programming style was dense and inscrutable. “The way the whole thing was formatted was insane. Only the most paranoid, painstaking coder in the world could avoid making mistakes.” Kaminsky lives in Seattle, but, while visiting family in San Francisco in July, he retreated to the basement of his mother’s house to work on his bitcoin attacks. In a windowless room jammed with computers, Kaminsky paced around talking to himself, trying to build a mental picture of the bitcoin network. He quickly identified nine ways to compromise the system and scoured Nakamoto’s code for an insertion point for his first attack. But when he found the right spot, there was a message waiting for him. “Attack Removed,” it said. The same thing happened over and over, infuriating Kaminsky. “I came up with beautiful bugs,” he said. “But every time I went after the code there was a line that addressed the problem.” He was like a burglar who was certain that he could break into a bank by digging a tunnel, drilling through a wall, or climbing down a vent, and on each attempt he discovered a freshly poured cement barrier with a sign telling him to go home. “I’ve never seen anything like it,” Kaminsky said, still in awe. Kaminsky ticked off the skills Nakamoto would need to pull it off. “He’s a world-class programmer, with a deep understanding of the C++ programming language,” he said. “He understands economics, cryptography, and peer-to-peer networking.” “Either there’s a team of people who worked on this,” Kaminsky said, “or this guy is a genius.” Kaminsky wasn’t alone in this assessment. Soon after creating the currency, Nakamoto posted a nine-page technical paper describing how bitcoin would function. That document included three references to the work of Stuart Haber, a researcher at H.P. Labs, in Princeton. Haber is a director of the International Association for Cryptologic Research and knew all about bitcoin. “Whoever did this had a deep understanding of cryptography,” Haber said when I called. “They’ve read the academic papers, they have a keen intelligence, and they’re combining the concepts in a genuinely new way.” Haber noted that the community of cryptographers is very small: about three hundred people a year attend the most important conference, the annual gathering in Santa Barbara. In all likelihood, Nakamoto belonged to this insular world. If I wanted to find him, the Crypto 2011 conference would be the place to start. “Here we go, team!” a cheerleader shouted before two burly guys heaved her into the air. It was a foggy Monday morning in mid-August, and dozens of college cheerleaders had gathered on the athletic fields of the University of California at Santa Barbara for a three-day training camp. Their hollering could be heard on the steps of a nearby lecture hall, where a group of bleary-eyed cryptographers, dressed in shorts and rumpled T-shirts, muttered about symmetric-key ciphers over steaming cups of coffee. This was Crypto 2011, and the list of attendees included representatives from the National Security Agency, the U.S. military, and an assortment of foreign governments. Cryptographers are little known outside this hermetic community, but our digital safety depends on them. They write the algorithms that conceal bank files, military plans, and your e-mail. I approached Phillip Rogaway, the conference’s program chair. He is a friendly, diminutive man who is a professor of cryptography at the University of California at Davis and who has also taught at Chiang Mai University, in Thailand. He bowed when he shook my hand, and I explained that I was trying to learn more about what it would take to create bitcoin. “The people who know how to do that are here,” Rogaway said. “It’s likely I either know the person or know their work.” He offered to introduce me to some of the attendees. Nakamoto had good reason to hide: people who experiment with currency tend to end up in trouble. In 1998, a Hawaiian resident named Bernard von NotHaus began fabricating silver and gold coins that he dubbed Liberty Dollars. Nine years later, the U.S. government charged NotHaus with “conspiracy against the United States.” He was found guilty and is awaiting sentencing. “It is a violation of federal law for individuals . . . to create private coin or currency systems to compete with the official coinage and currency of the United States,” the F.B.I. announced at the end of the trial. Online currencies aren’t exempt. In 2007, the federal government filed charges against e-Gold, a company that sold a digital currency redeemable for gold. The government argued that the project enabled money laundering and child pornography, since users did not have to provide thorough identification. The company’s owners were found guilty of operating an unlicensed money-transmitting business and the C.E.O. was sentenced to months of house arrest. The company was effectively shut down. Nakamoto seemed to be doing the same things as these other currency developers who ran afoul of authorities. He was competing with the dollar and he insured the anonymity of users, which made bitcoin attractive for criminals. This winter, a Web site was launched called Silk Road, which allowed users to buy and sell heroin, LSD, and marijuana as long as they paid in bitcoin. Still, Lewis Solomon, a professor emeritus at George Washington University Law School, who has written about alternative currencies, argues that creating bitcoin might be legal. “Bitcoin is in a gray area, in part because we don’t know whether it should be treated as a currency, a commodity like gold, or possibly even a security,” he says. Gray areas, however, are dangerous, which may be why Nakamoto constructed bitcoin in secret. It may also explain why he built the code with the same peer-to-peer technology that facilitates the exchange of pirated movies and music: users connect with each other instead of with a central server. There is no company in control, no office to raid, and nobody to arrest. Today, bitcoins can be used online to purchase beef jerky and socks made from alpaca wool. Some computer retailers accept them, and you can use them to buy falafel from a restaurant in Hell’s Kitchen. In late August, I learned that bitcoins could also get me a room at a Howard Johnson hotel in Fullerton, California, ten minutes from Disneyland. I booked a reservation for my four-year-old daughter and me and received an e-mail from the hotel requesting a payment of 10.305 bitcoins. By this time, it would have been pointless for me to play the bitcoin lottery, which is set up so that the difficulty of winning increases the more people play it. When bitcoin launched, my laptop would have had a reasonable chance of winning from time to time. Now, however, the computing power dedicated to playing the bitcoin lottery exceeds that of the world’s most powerful supercomputer. So I set up an account with Mt. Gox, the leading bitcoin exchange, and transferred a hundred and twenty dollars. A few days later, I bought 10.305 bitcoins with the press of a button and just as easily sent them to the Howard Johnson. It was a simple transaction that masked a complex calculus. In 1971, Richard Nixon announced that U.S. dollars could no longer be redeemed for gold. Ever since, the value of the dollar has been based on our faith in it. We trust that dollars will be valuable tomorrow, so we accept payment in dollars today. Bitcoin is similar: you have to trust that the system won’t get hacked, and that Nakamoto won’t suddenly emerge to somehow plunder it all. Once you believe in it, the actual cost of a bitcoin—five dollars or thirty?—depends on factors such as how many merchants are using it, how many might use it in the future, and whether or not governments ban it. My daughter and I arrived at the Howard Johnson on a hot Friday afternoon and were met in the lobby by Jefferson Kim, the hotel’s cherubic twenty-eight-year-old general manager. “You’re the first person who’s ever paid in bitcoin,” he said, shaking my hand enthusiastically. Kim explained that he had started mining bitcoins two months earlier. He liked that the currency was governed by a set of logical rules, rather than the mysterious machinations of the Federal Reserve. A dollar today, he pointed out, buys you what a nickel bought a century ago, largely because so much money has been printed. And, he asked, why trust a currency backed by a government that is fourteen trillion dollars in debt? Kim had also figured that bitcoin mining would be a way to make up the twelve hundred dollars he’d spent on a high-performance gaming computer. So far, he’d made only four hundred dollars, but it was fun to be a pioneer. He wanted bitcoin to succeed, and in order for that to happen businesses needed to start accepting it. “We never talk anymore.” Copy link to cartoon Copy link to cartoon Link copied Shop Shop The truth is that most people don’t spend the bitcoins they buy; they hoard them, hoping that they will appreciate. Businesses are afraid to accept them, because they’re new and weird—and because the value can fluctuate wildly. (Kim immediately exchanged the bitcoins I sent him for dollars to avoid just that risk.) Still, the currency is young and has several attributes that appeal to merchants. Robert Schwarz, the owner of a computer-repair business in Klamath Falls, Oregon, began selling computers for bitcoin to sidestep steep credit-card fees, which he estimates cost him three per cent on every transaction. “One bank called me saying they had the lowest fees,” Schwarz said. “I said, ‘No, you don’t. Bitcoin does.’ ” Because bitcoin transfers can’t be reversed, merchants also don’t have to deal with credit-card charge-backs from dissatisfied customers. Like cash, it’s gone once you part with it. At the Howard Johnson, Kim led us to the check-in counter. The lobby featured imitation-crystal chandeliers, ornately framed oil paintings of Venice, and, inexplicably, a pair of faux elephant tusks painted gold. Kim explained that he hadn’t told his mother, who owned the place, that her hotel was accepting bitcoins: “It would be too hard to explain what a bitcoin is.” He said he had activated the tracking program on his mother’s Droid, and she was currently about six miles away. Today, at least, there was no danger of her finding out about her hotel’s financial innovation. The receptionist handed me a room card, and Kim shook my hand. “So just enjoy your stay,” he said. Nakamoto’s extensive online postings have some distinctive characteristics. First of all, there is the flawless English. Over the course of two years, he dashed off about eighty thousand words—the approximate length of a novel—and made only a few typos. He covered topics ranging from the theories of the Austrian economist Ludwig von Mises to the history of commodity markets. Perhaps most interestingly, when he created the first fifty bitcoins, now known as the “genesis block,” he permanently embedded a brief line of text into the data: “The Times 03/Jan/2009 Chancellor on brink of second bailout for banks.” This is a reference to a Times of London article that indicated that the British government had failed to stimulate the economy. Nakamoto appeared to be saying that it was time to try something new. The text, hidden amid a jumble of code, was a sort of digital battle cry. It also indicated that Nakamoto read a British newspaper. He used British spelling (“favour,” “colour,” “grey,” “modernised”) and at one point described something as being “bloody hard.” An apartment was a “flat,” math was “maths,” and his comments tended to appear after normal business hours ended in the United Kingdom. In an initial post announcing bitcoin, he employed American-style spelling. But after that a British style appeared to flow naturally. I had this in mind when I started to attend the lectures at the Crypto 2011 conference, including ones with titles such as “Leftover Hash Lemma, Revisited” and “Time-Lock Puzzles in the Random Oracle Model.” In the back of a darkened auditorium, I stared at the attendee list. A Frenchman onstage was talking about testing the security of encryption systems. The most effective method, he said, is to attack the system and see if it fails. I ran my finger past dozens of names and addresses, circling residents of the United Kingdom and Ireland. There were nine. I soon discovered that six were from the University of Bristol, and they were all together at one of the conference’s cocktail parties. They were happy to chat but entirely dismissive of bitcoin, and none had worked with peer-to-peer technology. “It’s not at all interesting to us,” one of them said. The two other cryptographers from Britain had no history with large software projects. Then I started looking into a man named Michael Clear. Clear was a young graduate student in cryptography at Trinity College in Dublin. Many of the other research students at Trinity posted profile pictures and phone numbers, but Clear’s page just had an e-mail address. A Web search turned up three interesting details. In 2008, Clear was named the top computer-science undergraduate at Trinity. The next year, he was hired by Allied Irish Banks to improve its currency-trading software, and he co-authored an academic paper on peer-to-peer technology. The paper employed British spelling. Clear was well versed in economics, cryptography, and peer-to-peer networks. I e-mailed him, and we agreed to meet the next morning on the steps outside the lecture hall. Shortly after the appointed time, a long-haired, square-jawed young man in a beige sweater walked up to me, looking like an early-Zeppelin Robert Plant. With a pronounced brogue, he introduced himself. “I like to keep a low profile,” he said. “I’m curious to know how you found me.” I told him I had read about his work for Allied Irish, as well as his paper on peer-to-peer technology, and was interested because I was researching bitcoin. I said that his work gave him a unique insight into the subject. He was wearing rectangular Armani glasses and squinted so much I couldn’t see his eyes. “My area of focus right now is fully homomorphic encryption,” he said. “I haven’t been following bitcoin lately.” He responded calmly to my questions. He was twenty-three years old and studied theoretical cryptography by himself in Dublin—there weren’t any other cryptographers at Trinity. But he had been programming computers since he was ten and he could code in a variety of languages, including C++, the language of bitcoin. Given that he was working in the banking industry during tumultuous times, I asked how he felt about the ongoing economic crisis. “It could have been averted,” he said flatly. He didn’t want to say whether or not the new currency could prevent future banking crises. “It needs to prove itself,” he said. “But it’s an intriguing idea.” I told him I had been looking for Nakamoto and thought that he might be here at the Crypto 2011 conference. He said nothing. Finally, I asked, “Are you Satoshi?” He laughed, but didn’t respond. There was an awkward silence. “If you’d like, I’d be happy to review the design for you,” he offered instead. “I could let you know what I think.” “Sure,” I said hesitantly. “Do you need me to send you a link to the code?” “I think I can find it,” he said. Soon after I met Clear, I travelled to Glasgow, Kentucky, to see what bitcoin mining looked like. As I drove into the town of fourteen thousand, I passed shuttered factories and a central square lined with empty storefronts. On Howdy 106.5, a local radio station, a man tried to sell his bed, his television, and his basset hound—all for a hundred and ten dollars. I had come to visit Kevin Groce, a forty-two-year-old bitcoin miner. His uncles had a garbage-hauling business and had let him set up his operation at their facility. The dirt parking lot was jammed with garbage trucks, which reeked in the summer sun. “I like to call it the new moonshining,” Groce said, in a smooth Kentucky drawl, as he led me into a darkened room. One wall was lined with four-foot-tall homemade computers with blinking green and red lights. The processors inside were working so hard that their temperature had risen to a hundred and seventy degrees, and heat radiated into the room. Each system was a jumble of wires and hacked-together parts, with a fan from Walmart duct-taped to the top. Groce had built them three months earlier, for four thousand dollars. Ever since, they had generated a steady flow of bitcoins, which Groce exchanged for dollars, averaging about a thousand per month so far. He figured his investment was going to pay off. Groce was wiry, with wisps of gray in his hair, and he split his time between working on his dad’s farm, repairing laptops at a local computer store, and mining bitcoin. Groce’s father didn’t understand Kevin’s enthusiasm for the new currency and expected him to take over the farm. “If it’s not attached to a cow, my dad doesn’t think much of it,” Groce said. Groce was engaged to be married, and planned to use some of his bitcoin earnings to pay for a wedding in Las Vegas later in the year. He had tried to explain to his fiancée how they could afford it, but she doubted the financial prudence of filling a room with bitcoin-mining rigs. “She gets to cussing every time we talk about it,” Groce confided. Still, he was proud of the powerful computing center he had constructed. The machines ran non-stop, and he could control them remotely from his iPhone. The arrangement allowed him to cut tobacco with his father and monitor his bitcoin operation at the same time. Nakamoto knew that competition for bitcoins would eventually lead people to build these kinds of powerful computing clusters. Rather than let that effort go to waste, he designed software that uses the processing power of the lottery players to confirm and verify transactions. As people like Groce try to win bitcoins, their computers are harnessed to analyze transactions and insure that no one spends money twice. In other words, Groce’s backwoods operation functioned as a kind of bank. Groce, however, didn’t look like a guy Wells Fargo would hire. He liked to stay up late at the garbage-hauling center and thrash through Black Sabbath tunes on his guitar. He gave all his computers pet names, like Topper and the Dazzler, and, between guitar solos, tended to them as if they were prize animals. “I grew up milking cows,” Groce said. “Now I’m just milking these things.” A week after the Crypto 2011 conference, I received an e-mail from Clear. He said that he would send me his thoughts on bitcoin in a day. He added, “I also think I can identify Satoshi.” The next morning, Clear sent a lengthy e-mail. “It is apparent that the person(s) behind the Satoshi name accumulated a not insignificant knowledge of applied cryptography,” he wrote, adding that the design was “elegant” and required “considerable effort and dedication, and programming proficiency.” But Clear also described some of bitcoin’s weaknesses. He pointed out that users were expected to download their own encryption software to secure their virtual wallets. Clear felt that the bitcoin software should automatically provide such security. He also worried about the system’s ability to grow and the fact that early adopters received an outsized share of bitcoins. “As far as the identity of the author, it would be unfair to publish an identity when the person or persons has/have taken major steps to remain anonymous,” he wrote. “But you may wish to talk to a certain individual who matches the profile of the author on many levels.” He then gave me a name. For a few seconds, all I could hear on the other end of the line was laughter. “I would love to say that I’m Satoshi, because bitcoin is very clever,” Vili Lehdonvirta said, finally. “But it’s not me.” Lehdonvirta is a thirty-one-year-old Finnish researcher at the Helsinki Institute for Information Technology. Clear had discovered that Lehdonvirta used to be a video-game programmer and now studies virtual currencies. Clear suggested that he was a solid fit for Nakamoto. Lehdonvirta, however, pointed out that he has no background in cryptography and limited C++ programming skills. “You need to be a crypto expert to build something as sophisticated as bitcoin,” Lehdonvirta said. “There aren’t many of those people, and I’m definitely not one of them.” Still, Lehdonvirta had researched bitcoin and worried about it. “The only people who need cash in large denominations right now are criminals,” he said, pointing out that cash is hard to move around and store. Bitcoin removes those obstacles while preserving the anonymity of cash. Lehdonvirta is on the advisory board of Electronic Frontier Finland, an organization that advocates for online privacy, among other things. Nonetheless, he believes that bitcoin takes privacy too far. “Only anarchists want absolute, unbreakable financial privacy,” he said. “We need to have a back door so that law enforcement can intercede.” But Lehdonvirta admitted that it’s hard to stop new technology, particularly when it has a compelling story. And part of what attracts people to bitcoin, he said, is the mystery of Nakamoto’s true identity. “Having a mythical background is an excellent marketing trick,” Lehdonvirta said. A few days later, I spoke with Clear again. “Did you find Satoshi?” he asked cheerfully. I told him that Lehdonvirta had made a convincing denial, and that every other lead I’d been working on had gone nowhere. I then took one more opportunity to question him and to explain all the reasons that I suspected his involvement. Clear responded that his work for Allied Irish Banks was brief and of “no importance.” He admitted that he was a good programmer, understood cryptography, and appreciated the bitcoin design. But, he said, economics had never been a particular interest of his. “I’m not Satoshi,” Clear said. “But even if I was I wouldn’t tell you.” The point, Clear continued, is that Nakamoto’s identity shouldn’t matter. The system was built so that we don’t have to trust an individual, a company, or a government. Anybody can review the code, and the network isn’t controlled by any one entity. That’s what inspires confidence in the system. Bitcoin, in other words, survives because of what you can see and what you can’t. Users are hidden, but transactions are exposed. The code is visible to all, but its origins are mysterious. The currency is both real and elusive—just like its founder. “You can’t kill it,” Clear said, with a touch of bravado. “Bitcoin would survive a nuclear attack.” Over the summer, bitcoin actually experienced a sort of nuclear attack. Hackers targeted the burgeoning currency, and though they couldn’t break Nakamoto’s code, they were able to disrupt the exchanges and destroy Web sites that helped users store bitcoins. The number of transactions decreased and the exchange rate plummeted. Commentators predicted the end of bitcoin. In September, however, volume began to increase again, and the price stabilized, at least temporarily. Meanwhile, in Kentucky, Kevin Groce added two new systems to his bitcoin-mining operation at the garbage depot and planned to build a dozen more. Ricky Wells, his uncle and a co-owner of the garbage business, had offered to invest thirty thousand dollars, even though he didn’t understand how bitcoin worked. “I’m just a risk-taking son of a bitch and I know this thing’s making money,” Wells said. “Plus, these things are so damn hot they’ll heat the whole building this winter.” To Groce, bitcoin was an inevitable evolution in money. People use printed money less and less as it is, he said. Consumers need something like bitcoin to take its place. “It’s like eight-tracks going to cassettes to CDs and now MP3s,” he said. Even though his friends and most of his relatives questioned his enthusiasm, Groce didn’t hide his confidence. He liked to wear a T-shirt he designed that had the words “Bitcoin Millionaire” emblazoned in gold on the chest. He admitted that people made fun of him for it. “My fiancée keeps saying she’d rather I was just a regular old millionaire,” he said. “But maybe I will be someday, if these rigs keep working for me.” ♦ More: Banking Bitcoin Computers Currencies Currency Economy, Economics Encryption Internet Money Satoshi Nakamoto Silk Road Technology Weekly E-mail address Sign up By signing up, you agree to our User Agreement and Privacy Policy & Cookie Statement. This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply. Letter from Amsterdam By Patrick Radden Keefe Annals of Law By Eli Hager A Reporter at Large By Ariel Levy American Chronicles By Ronan Farrow Sections News Books & Culture Fiction & Poetry Humor & Cartoons Magazine Crossword Video Podcasts Archive Goings On More Customer Care Shop The New Yorker Buy Covers and Cartoons Condé Nast Store Digital Access Newsletters Jigsaw Puzzle RSS About Careers Contact F.A.Q. Media Kit Press Accessibility Help © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. The New Yorker may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Facebook X Snapchat YouTube Instagram Do Not Sell My Personal Info "

"Why Meta’s latest large language model only survived three days online | MIT Technology Review"

"https://www.technologyreview.com/2022/11/18/1063487/meta-large-language-model-ai-only-survived-three-days-gpt-3-science"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Why Meta’s latest large language model survived only three days online Galactica was supposed to help scientists. Instead, it mindlessly spat out biased and incorrect nonsense. By Will Douglas Heaven archive page Stephanie Arnett/MITTR; Getty, Envato, NASA On November 15 Meta unveiled a new large language model called Galactica , designed to assist scientists. But instead of landing with the big bang Meta hoped for, Galactica has died with a whimper after three days of intense criticism. Yesterday the company took down the public demo that it had encouraged everyone to try out. Meta’s misstep—and its hubris—show once again that Big Tech has a blind spot about the severe limitations of large language models. There is a large body of research that highlights the flaws of this technology , including its tendencies to reproduce prejudice and assert falsehoods as facts. Related Story Language models are mindless mimics that do not understand what they are saying—so why do we pretend they’re experts? However, Meta and other companies working on large language models, including Google, have failed to take it seriously. Galactica is a large language model for science, trained on 48 million examples of scientific articles, websites, textbooks, lecture notes, and encyclopedias. Meta promoted its model as a shortcut for researchers and students. In the company’s words, Galactica “can summarize academic papers, solve math problems, generate Wiki articles, write scientific code, annotate molecules and proteins, and more.” But the shiny veneer wore through fast. Like all language models, Galactica is a mindless bot that cannot tell fact from fiction. Within hours, scientists were sharing its biased and incorrect results on social media. Absolutely. Galactica is little more than statistical nonsense at scale. Amusing. Dangerous. And IMHO unethical. https://t.co/15DAFJCzIb “I am both astounded and unsurprised by this new effort,” says Chirag Shah at the University of Washington, who studies search technologies. “When it comes to demoing these things, they look so fantastic, magical, and intelligent. But people still don’t seem to grasp that in principle such things can’t work the way we hype them up to.” Asked for a statement on why it had removed the demo, Meta pointed MIT Technology Review to a tweet that says: “Thank you everyone for trying the Galactica model demo. We appreciate the feedback we have received so far from the community, and have paused the demo for now. Our models are available for researchers who want to learn more about the work and reproduce results in the paper.” A fundamental problem with Galactica is that it is not able to distinguish truth from falsehood, a basic requirement for a language model designed to generate scientific text. People found that it made up fake papers (sometimes attributing them to real authors), and generated wiki articles about the history of bears in space as readily as ones about protein complexes and the speed of light. It’s easy to spot fiction when it involves space bears, but harder with a subject users may not know much about. Many scientists pushed back hard. Michael Black, director at the Max Planck Institute for Intelligent Systems in Germany, who works on deep learning, tweeted : “In all cases, it was wrong or biased but sounded right and authoritative. I think it’s dangerous.” I asked #Galactica about some things I know about and I'm troubled. In all cases, it was wrong or biased but sounded right and authoritative. I think it's dangerous. Here are a few of my experiments and my analysis of my concerns. (1/9) Even more positive opinions came with clear caveats: “Excited to see where this is headed!” tweeted Miles Cranmer, an astrophysicist at Princeton. “You should never keep the output verbatim or trust it. Basically, treat it like an advanced Google search of (sketchy) secondary sources!” Galactica also has problematic gaps in what it can handle. When asked to generate text on certain topics, such as “racism” and “AIDS,” the model responded with : “Sorry, your query didn’t pass our content filters. Try again and keep in mind this is a scientific language model.” Related Story A group of over 1,000 AI researchers has created a multilingual large language model bigger than GPT-3—and they’re giving it out for free. The Meta team behind Galactica argues that language models are better than search engines. “We believe this will be the next interface for how humans access scientific knowledge,” the researchers write. This is because language models can “potentially store, combine, and reason about” information. But that “potentially” is crucial. It’s a coded admission that language models cannot yet do all these things. And they may never be able to. “Language models are not really knowledgeable beyond their ability to capture patterns of strings of words and spit them out in a probabilistic manner,” says Shah. “It gives a false sense of intelligence.” Gary Marcus, a cognitive scientist at New York University and a vocal critic of deep learning, gave his view in a Substack post titled “A Few Words About Bullshit,” saying that the ability of large language models to mimic human-written text is nothing more than “a superlative feat of statistics.” And yet Meta is not the only company championing the idea that language models could replace search engines. For the last couple of years, Google has been promoting language models, such as LaMDA , as a way to look up information. It’s a tantalizing idea. But suggesting that the human-like text such models generate will always contain trustworthy information, as Meta appeared to do in its promotion of Galactica, is reckless and irresponsible. It was an unforced error. My considered opinion of Galactica: it's fun, impressive, and interesting in many ways. Great achievement. It's just unfortunate that it's being touted as a practical research tool, and even more unfortunate that it suggests you use it to write complete articles. And it wasn’t just the fault of Meta’s marketing team. Yann LeCun, a Turing Award winner and Meta’s chief scientist, defended Galactica to the end. On the day the model was released, LeCun tweeted : “Type a text and Galactica will generate a paper with relevant references, formulas, and everything.” Three days later, he tweeted : “Galactica demo is off line for now. It’s no longer possible to have some fun by casually misusing it. Happy?” It's not quite Meta's Tay moment. Recall that in 2016, Microsoft launched a chatbot called Tay on Twitter—then shut it down 16 hours later when Twitter users turned it into a racist, homophobic sexbot. But Meta’s handling of Galactica smacks of the same naivete. “Big tech companies keep doing this—and mark my words, they will not stop—because they can,” says Shah. “And they feel like they must—otherwise someone else might. They think that this is the future of information access, even if nobody asked for that future.” Correction: A previous version of this story stated that Google has been promoting the language model PaLM as a way to look up information for a couple of years. The language model we meant to refer to is LaMDA. hide by Will Douglas Heaven Share linkedinlink opens in a new window twitterlink opens in a new window facebooklink opens in a new window emaillink opens in a new window Popular This new data poisoning tool lets artists fight back against generative AI Melissa Heikkilä Everything you need to know about artificial wombs Cassandra Willyard Deepfakes of Chinese influencers are livestreaming 24/7 Zeyi Yang How to fix the internet Katie Notopoulos Deep Dive Artificial intelligence This new data poisoning tool lets artists fight back against generative AI The tool, called Nightshade, messes up training data in ways that could cause serious damage to image-generating AI models. By Melissa Heikkilä archive page Deepfakes of Chinese influencers are livestreaming 24/7 With just a few minutes of sample video and $1,000, brands never have to stop selling their products. By Zeyi Yang archive page Driving companywide efficiencies with AI Advanced AI and ML capabilities revolutionize how administrative and operations tasks are done. By MIT Technology Review Insights archive page Rogue superintelligence and merging with machines: Inside the mind of OpenAI’s chief scientist An exclusive conversation with Ilya Sutskever on his fears for the future of AI and why they’ve made him change the focus of his life’s work. By Will Douglas Heaven archive page Stay connected Illustration by Rose Wong Get the latest updates from MIT Technology Review Discover special offers, top stories, upcoming events, and more. Enter your email Thank you for submitting your email! It looks like something went wrong. We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at [email protected] with a list of newsletters you’d like to receive. The latest iteration of a legacy Advertise with MIT Technology Review © 2023 MIT Technology Review About About us Careers Custom content Advertise with us International Editions Republishing MIT News Help Help & FAQ My subscription Editorial guidelines Privacy policy Terms of Service Write for us Contact us twitterlink opens in a new window facebooklink opens in a new window instagramlink opens in a new window rsslink opens in a new window linkedinlink opens in a new window "

"The growing influence of effective altruism | MIT Technology Review"

"https://www.technologyreview.com/2022/10/17/1060967/effective-altruism-growth"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Inside effective altruism, where the far future counts a lot more than the present The giving philosophy, which has adopted a focus on the long term, is a conservative project, consolidating decision-making among a small set of technocrats. By Rebecca Ackermann archive page Victor Kerlow Oregon 6th Con­gressional District candidate Carrick Flynn seemed to drop out of the sky. With a stint at Oxford’s Future of Humanity Institute, a track record of voting in only two of the past 30 elections, and $11 million in support from a political action committee established by crypto billionaire Sam Bankman-Fried, Flynn didn’t fit into the local political scene, even though he’d grown up in the state. One constituent called him “Mr. Creepy Funds” in an interview with a local paper; another said he thought Flynn was a Russian bot. The specter of crypto influence, a slew of expensive TV ads, and the fact that few locals had heard of or spoken to Flynn raised suspicions that he was a tool of outside financial interests. And while the rival candidate who led the primary race promised to fight for issues like better worker protections and stronger gun legislation, Flynn’s platform prioritized economic growth and preparedness for pandemics and other disasters. Both are pillars of “longtermism,” a growing strain of the ideology known as effective altruism (or EA), which is popular among an elite slice of people in tech and politics. Even during an actual pandemic, Flynn’s focus struck many Oregonians as far-fetched and foreign. Perhaps unsurprisingly, he ended up losing the 2022 primary to the more politically experienced Democrat, Andrea Salinas. But despite Flynn’s lackluster showing, he made history as effective altruism’s first political candidate to run for office. Since its birth in the late 2000s, effective altruism has aimed to answer the question “How can those with means have the most impact on the world in a quantifiable way?”—and supplied clear methodologies for calculating the answer. Directing money to organizations that use evidence-based approaches is the one technique EA is most known for. But as it has expanded from an academic philosophy into a community and a movement, its ideas of the “best” way to change the world have evolved as well. “ Longtermism ,” the belief that unlikely but existential threats like a humanity-destroying AI revolt or international biological warfare are humanity’s most pressing problems, is integral to EA today. Of late, it has moved from the fringes of the movement to its fore with Flynn’s campaign, a flurry of mainstream media coverage, and a new treatise published by one of EA’s founding fathers, William MacAskill. It’s an ideology that’s poised to take the main stage as more believers in the tech and billionaire classes—which are, notably, mostly male and white—start to pour millions into new PACs and projects like Bankman-Fried’s FTX Future Fund and Longview Philanthropy’s Longtermism Fund , which focus on theoretical menaces ripped from the pages of science fiction. EA’s ideas have long faced criticism from within the fields of philosophy and philanthropy that they reflect white Western saviorism and an avoidance of structural problems in favor of abstract math—not coincidentally, many of the same objections lobbed at the tech industry at large. Such charges are only intensifying as EA’s pockets deepen and its purview stretches into a galaxy far, far away. Ultimately, the philosophy’s influence may be limited by their accuracy. What is EA? If effective altruism were a lab-grown species, its origin story would begin with DNA spliced from three parents: applied ethics, speculative technology, and philanthropy. EA’s philosophical genes came from Peter Singer’s brand of utilitarianism and Oxford philosopher Nick Bostrom’s investigations into potential threats to humanity. From tech, EA drew on early research into the long-term impact of artificial intelligence carried out at what’s now known as the Machine Intelligence Research Institute ( MIRI ) in Berkeley, California. In philanthropy, EA is part of a growing trend toward evidence-based giving, driven by members of the Silicon Valley nouveau riche who are eager to apply the strategies that made them money to the process of giving it away. For effective altruists, a good cause is not good enough; only the very best should get funding in the areas most in need. While these origins may seem diverse, the people involved are linked by social, economic, and professional class, and by a technocratic worldview. Early players —including MacAskill, a Cambridge philosopher; Toby Ord, an Oxford philosopher; Holden Karnofsky, cofounder of the charity evaluator GiveWell; and Dustin Moskovitz, a cofounder of Facebook who founded the nonprofit Open Philanthropy with his wife, Cari Tuna—are all still leaders in the movement’s interconnected constellation of nonprofits, foundations, and research organizations. For effective altruists, a good cause is not good enough; only the very best should get funding in the areas most in need. Those areas are usually, by EA calculations, developing nations. Personal connections that might encourage someone to give to a local food bank or donate to the hospital that treated a parent are a distraction—or worse, a waste of money. The classic example of an EA-approved effort is the Against Malaria Foundation , which purchases and distributes mosquito nets in sub-Saharan Africa and other areas heavily affected by the disease. The price of a net is very small compared with the scale of its life-saving potential; this ratio of “value” to cost is what EA aims for. Other popular early EA causes include providing vitamin A supplements and malaria medication in African countries , and promoting animal welfare in Asia. Related Story Though it almost certainly won’t work, it is a telling sign of where the field is heading Within effective altruism’s framework, selecting one’s career is just as important as choosing where to make donations. EA defines a professional “fit” by whether a candidate has comparative advantages like exceptional intelligence or an entrepreneurial drive, and if an effective altruist qualifies for a high-paying path, the ethos encourages “ earning to give ,” or dedicating one’s life to building wealth in order to give it away to EA causes. Bankman-Fried has said that he’s earning to give, even founding the crypto platform FTX with the express purpose of building wealth in order to redirect 99% of it. Now one of the richest crypto executives in the world, Bankman-Fried plans to give away up to $1 billion by the end of 2022. “The allure of effective altruism has been that it’s an off-the-shelf methodology for being a highly sophisticated, impact-­focused, data-driven funder,” says David Callahan, founder and editor of Inside Philanthropy and the author of a 2017 book on philanthropic trends, The Givers. Not only does EA suggest a clear and decisive framework, but the community also offers a set of resources for potential EA funders—including GiveWell, a nonprofit that uses an EA-driven evaluation rubric to recommend charitable organizations; EA Funds, which allows individuals to donate to curated pools of charities; 80,000 Hours, a career-coaching organization; and a vibrant discussion forum at Effectivealtruism.org, where leaders like MacAskill and Ord regularly chime in. Effective altruism’s original laser focus on measurement has contributed rigor in a field that has historically lacked accountability for big donors with last names like Rockefeller and Sackler. “It has been an overdue, much-needed counterweight to the typical practice of elite philanthropy, which has been very inefficient,” says Callahan. But where exactly are effective altruists directing their earnings? Who benefits? As with all giving—in EA or otherwise—there are no set rules for what constitutes “philanthropy,” and charitable organizations benefit from a tax code that incentivizes the super-rich to establish and control their own charitable endeavors at the expense of public tax revenues, local governance, or public accountability. EA organizations are able to leverage the practices of traditional philanthropy while enjoying the shine of an effectively disruptive approach to giving. The movement has formalized its community’s commitment to donate with the Giving What We Can Pledge —mirroring another old-school philanthropic practice—but there are no giving requirements to be publicly listed as a pledger. Tracking the full influence of EA’s philosophy is tricky, but 80,000 Hours has estimated that $46 billion was committed to EA causes between 2015 and 2021, with donations growing about 20% each year. GiveWell calculates that in 2021 alone, it directed over $187 million to malaria nets and medication; by the organization’s math, that’s over 36,000 lives saved. Accountability is significantly harder with longtermist causes like biosecurity or “AI alignment”—a set of efforts aimed at ensuring that the power of AI is harnessed toward ends generally understood as “good.” Such causes, for a growing number of effective altruists, now take priority over mosquito nets and vitamin A medication. “The things that matter most are the things that have long-term impact on what the world will look like,” Bankman-Fried said in an interview earlier this year. “There are trillions of people who have not yet been born.” Bankman-Fried’s views are influenced by longtermism’s utilitarian calculations, which flatten lives into single units of value. By this math, the trillions of humans yet to be born represent a greater moral obligation than the billions alive today. Any threats that could prevent future generations from reaching their full potential—either through extinction or through technological stagnation, which MacAskill deems equally dire in his new book, What We Owe the Future —are priority number one. In his book, MacAskill discusses his own journey from longtermism skeptic to true believer and urges other to follow the same path. The existential risks he lays out are specific: “The future could be terrible, falling to authoritarians who use surveillance and AI to lock in their ideology for all time, or even to AI systems that seek to gain power rather than promote a thriving society. Or there could be no future at all: we could kill ourselves off with biological weapons or wage an all-out nuclear war that causes civilisation to collapse and never recover.” It was to help guard against these exact possibilities that Bankman-Fried created the FTX Future Fund this year as a project within his philanthropic foundation. Its focus areas include “space governance,” “artificial intelligence,” and “empowering exceptional people.” The fund’s website acknowledges that many of its bets “will fail.” (Its primary goal for 2022 is to test new funding models, but the fund’s site does not establish what “success” may look like.) As of June 2022, the FTX Future Fund had made 262 grants and investments , with recipients including a Brown University academic researching long-term economic growth , a Cornell University academic researching AI alignment, and an organization working on legal research around AI and biosecurity (which was born out of Harvard Law’s EA group ). Bankman-Fried is hardly the only tech billionaire pushing forward longtermist causes. Open Philanthropy, the EA charitable organization funded primarily by Moskovitz and Tuna, has directed $260 million to addressing “potential risks from advanced AI” since its founding. Together, the FTX Future Fund and Open Philanthropy supported Longview Philanthropy with more than $15 million this year before the organization announced its new Longtermism Fund. Vitalik Buterin, one of the founders of the blockchain platform Ethereum, is the second-largest recent donor to MIRI, whose mission is “to ensure [that] smarter-­than-human artificial intelligence has a positive impact.” MIRI’s donor list also includes the Thiel Foundation; Ben Delo, cofounder of crypto exchange BitMEX; and Jaan Tallinn, one of the founding engineers of Skype, who is also a cofounder of Cambridge’s Centre for the Study of Existential Risk (CSER). Elon Musk is yet another tech mogul dedicated to fighting longtermist existential risks ; he’s even claimed that his for-profit operations—including SpaceX’s mission to Mars—are philanthropic efforts supporting humanity’s progress and survival. (MacAskill has recently expressed concern that his philosophy is getting conflated with Musk’s “world­view.” However, EA aims for an expanded audience, and it seems unreasonable to expect rigid adherence to the exact belief system of its creators.) Criticism and change Even before the foregrounding of long­termism,effective altruism had been criticized for elevating the mindset of the “benevolent capitalist” (as philosopher Amia Srinivasan wrote in her 2015 review of MacAskill’s first book) and emphasizing individual agency within capitalism over more foundational critiques of the systems that have made one part of the world wealthy enough to spend time theorizing about how best to aid the rest. EA’s earn-to-give philosophy raises the question of why the wealthy should get to decide where funds go in a highly inequitable world—especially if they may be extracting that wealth from employees’ labor or the public, as may be the case with some crypto executives. “My ideological orientation starts with the belief that folks don’t earn tremendous amounts of money without it being at the expense of other people,” says Farhad Ebrahimi, founder and president of the Chorus Foundation, which funds mainly US organizations working to combat climate change by shifting economic and political power to the communities most affected by it. Many of the foundation’s grantees are groups led by people of color, and it is what’s known as a spend-down foundation; in other words, Ebrahimi says, Chorus’s work will be successful when its funds are fully redistributed. EA’s earn-to-give philosophy raises the question of why the wealthy should get to decide where funds go. Ebrahimi objects to EA’s approach of supporting targeted interventions rather than endowing local organizations to define their own priorities: “Why wouldn’t you want to support having the communities that you want the money to go to be the ones to build economic power? That’s an individual saying, ‘I want to build my economic power because I think I’m going to make good decisions about what to do with it’ … It seems very ‘benevolent dictator’ to me.” Effective altruists would respond that their moral obligation is to fund the most demonstrably transformative projects as defined by their framework, no matter what else is left behind. In an interview in 2018, MacAskill suggested that in order to recommend prioritizing any structural power shifts, he’d need to see “an argument that opposing inequality in some particular way is actually going to be the best thing to do.” However, when a small group of individuals with similar backgrounds have determined the formula for the most critical causes and “best” solutions, the unbiased rigor that EA is known for should come into question. While the top nine charities featured on GiveWell’s website today work in developing nations with communities of color, the EA community stands at 71% male and 76% white , with the largest percentage living in the US and the UK, according to a 2020 survey by the Centre for Effective Altruism (CEA). This may not be surprising given that the philanthropic community at large has long been criticized for homogeneity. But some studies have demonstrated that charitable giving in the US is actually growing in diversity, which casts EA’s breakdown in a different light. A 2012 report by the W. K. Kellogg Foundation found that both Asian-American and Black households gave away a larger percentage of their income than white households. Research from the Indiana University Lilly Family School of Philanthropy found in 2021 that 65% of Black households and 67% of Hispanic households surveyed donated charitably on a regular basis, along with 74% of white households. And donors of color were more likely to be involved in more informal avenues of giving, such as crowdfunding, mutual aid, or giving circles, which may not be accounted for in other reports. EA’s sales pitch does not appear to be reaching these donors. While EA proponents say its approach is data driven, EA’s calculations defy best practices within the tech industry around dealing with data. “This assumption that we’re going to calculate the single best thing to do in the world—have all this data and make these decisions—is so similar to the issues that we talk about in machine learning, and why you shouldn’t do that,” says Timnit Gebru, a leader in AI ethics and the founder and executive director of the Distributed AI Research Institute ( DAI R), which centers diversity in its AI research. Gebru and others have written extensively about the dangers of leveraging data without undertaking deeper analysis and making sure it comes from diverse sources. In machine learning, it leads to dangerously biased models. In philanthropy, a narrow definition of success rewards alliance with EA’s value system over other worldviews and penalizes nonprofits working on longer-term or more complex strategies that can’t be translated into EA’s math. The research that EA’s assessments rely on may also be flawed or subject to change; a 2004 study that elevated deworming—distributing drugs for parasitic infections—to one of GiveWell’s top causes has come under serious fire , with some researchers claiming to have debunked it while others have been unable to replicate the results leading to the conclusion that it would save huge numbers of lives. Despite the uncertainty surrounding this intervention , GiveWell directed more than $12 million to deworming charities through its Maximum Impact Fund this year. The voices of dissent are growing louder as EA’s influence spreads and more money is directed toward longtermist causes. A longtermist himself by some definitions, CSER researcher Luke Kemp believes that the growing focus of the EA research community is based on a limited and minority perspective. He’s been disappointed with the lack of diversity of thought and leadership he’s found in the field. Last year, he and his colleague Carla Zoe Cremer wrote and circulated a preprint titled “Democratizing Risk” about the community’s focus on the “techno-utopian approach”—which assumes that pursuing technology to its maximum development is an undeniable net positive—to the exclusion of other frameworks that reflect more common moral worldviews. “There’s a small number of key funders who have a very particular ideology, and either consciously or unconsciously select for the ideas that most resonate with what they want. You have to speak that language to move higher up the hierarchy and get more funding,” Kemp says. Longtermism sees history as a forward march toward inevitable progress. Even the basic concept of longtermism, according to Kemp, has been hijacked from legal and economic scholars in the 1960s, ’70s, and ’80s, who were focused on intergenerational equity and environmentalism —priorities that have notably dropped away from the EA version of the philosophy. Indeed, the central premise that “future people count,” as MacAskill says in his 2022 book, is hardly new. The Native American concept of the “ seventh generation principle ” and similar ideas in indigenous cultures across the globe ask each generation to consider the ones that have come before and will come after. Integral to these concepts, though, is the idea that the past holds valuable lessons for action today, especially in cases where our ancestors made choices that have led to environmental and economic crises. Longtermism sees history differently: as a forward march toward inevitable progress. MacAskill references the past often in What We Owe the Future , but only in the form of case studies on the life-­improving impact of technological and moral development. He discusses the abolition of slavery, the Industrial Revolution, and the women’s rights movement as evidence of how important it is to continue humanity’s arc of progress before the wrong values get “locked in” by despots. What are the “right” values? MacAskill has a coy approach to articulating them: he argues that “we should focus on promoting more abstract or general moral principles” to ensure that “moral changes stay relevant and robustly positive into the future.” Worldwide and ongoing climate change, which already affects the under-resourced more than the elite today, is notably not a core longtermist cause, as philosopher Emile P. Torres points out in their critiques. While it poses a threat to millions of lives, longtermists argue, it probably won’t wipe out all of humanity ; those with the wealth and means to survive can carry on fulfilling our species’ potential. Tech billionaires like Thiel and Larry Page already have plans and real estate in place to ride out a climate apocalypse. (MacAskill, in his new book, names climate change as a serious worry for those alive today, but he considers it an existential threat only in the “extreme” form where agriculture won’t survive.) “To come to the conclusion that in order to do the most good in the world you have to work on artificial general intelligence is very strange.” The final mysterious feature of EA’s version of the long view is how its logic ends up in a specific list of technology-based far-off threats to civilization that just happen to align with many of the original EA cohort’s areas of research. “I am a researcher in the field of AI,” says Gebru, “but to come to the conclusion that in order to do the most good in the world you have to work on artificial general intelligence is very strange. It’s like trying to justify the fact that you want to think about the science fiction scenario and you don’t want to think about real people, the real world, and current structural issues. You want to justify how you want to pull billions of dollars into that while people are starving.” Some EA leaders seem aware that criticism and change are key to expanding the community and strengthening its impact. MacAskill and others have made it explicit that their calculations are estimates (“These are our best guesses,” MacAskill offered on a 2020 podcast episode) and said they’re eager to improve through critical discourse. Both GiveWell and CEA have pages on their websites titled “Our Mistakes,” and in June, CEA ran a contest inviting critiques on the EA forum; the Future Fund has launched prizes up to $1.5 million for critical perspectives on AI. “We recognize that the problems EA is trying to address are really, really big and we don’t have a hope of solving them with only a small segment of people,” GiveWell board member and CEA community liaison Julia Wise says of EA’s diversity statistics. “We need the talents that lots of different kinds of people can bring to address these worldwide problems.” Wise also spoke on the topic at the 2020 EA Global Conference , and she actively discusses inclusion and community power dynamics on the CEA forum. The Center for Effective Altruism supports a mentorship program for women and nonbinary people (founded, incidentally, by Carrick Flynn’s wife ) that Wise says is expanding to other underrepresented groups in the EA community, and CEA has made an effort to facilitate conferences in more locations worldwide to welcome a more geographically diverse group. But these efforts appear to be limited in scope and impact; CEA’s public-facing page on diversity and inclusion was updated in October for the first time in two years. As the tech-utopian tenets of longtermism take a front seat in EA’s rocket ship and a few billionaire donors chart its path into the future, it may be too late to alter the DNA of the movement. Politics and the future Despite the sci-fi sheen, effective altruism today is a conservative project, consolidating decision-making behind a technocratic belief system and a small set of individuals, potentially at the expense of local and intersectional visions for the future. But EA’s community and successes were built around clear methodologies that may not transfer into the more nuanced political arena that some EA leaders and a few big donors are pushing toward. According to Wise, the community at large is still split on politics as an approach to pursuing EA’s goals, with some dissenters believing politics is too polarized a space for effective change. But EA is not the only charitable movement looking to political action to reshape the world; the philanthropic field generally has been moving into politics for greater impact. “We have an existential political crisis that philanthropy has to deal with. Otherwise, a lot of its other goals are going to be hard to achieve,” says Inside Philanthropy’s Callahan, using a definition of “existential” that differs from MacAskill’s. But while EA may offer a clear rubric for determining how to give charitably, the political arena presents a messier challenge. “There’s no easy metric for how to gain political power or shift politics,” he says. “And Sam Bankman-Fried has so far demonstrated himself not the most effective political giver.” Bankman-Fried has articulated his own political giving as “ more policy than politics ,” and has donated primarily to Democrats through his short-lived Protect Our Future PAC (which backed Carrick Flynn in Oregon) and the Guarding Against Pandemics PAC (which is run by his brother Gabe and publishes a cross-party list of its “ champions ” to support). Ryan Salame, the co-CEO with Bankman-Fried of FTX, funded his own PAC , American Dream Federal Action, which focuses mainly on Republican candidates. (Bankman-Fried has said Salame shares his passion for preventing pandemics.) Guarding Against Pandemics and the Open Philanthropy Action Fund (Open Philanthropy’s political arm) spent more than $18 million to get an initiative on the California state ballot this fall to fund pandemic research and action through a new tax. So while longtermist funds are certainly making waves behind the scenes, Flynn’s primary loss in Oregon may signal that EA’s more visible electoral efforts need to draw on new and diverse strategies to win over real-world voters. Vanessa Daniel , founder and former executive director of Groundswell , one of the largest funders of the US reproductive justice movement, believes that big donations and 11th-hour interventions will never rival grassroots organizing in making real political change. “Slow and patient organizing led by Black women, communities of color, and some poor white communities created the tipping point in the 2020 election that saved the country from fascism and allowed some window of opportunity to get things like the climate deal passed,” she says. And Daniel takes issue with the idea that metrics are the exclusive domain of rich, white, and male-led approaches. “I’ve talked to so many donors who think that grassroots organizing is the equivalent of planting magical beans and expecting things to grow. This is not the case,” she says. “The data is right in front of us. And it doesn’t require the collateral damage of millions of people.” The question now is whether the culture of EA will allow the community and its major donors to learn from such lessons. In May, Bankman-Fried admitted in an interview that there are a few takeaways from the Oregon loss, “in terms of thinking about who to support and how much,” and that he sees “decreasing marginal gains from funding.” In August, after distributing a total of $24 million over six months to candidates supporting pandemic prevention, Bankman-Fried appeared to have shut down funding through his Protect Our Future PAC, perhaps signaling an end to one political experiment. (Or maybe it was just a pragmatic belt-tightening after the serious and sustained downturn in the crypto market , the source of Bankman-Fried’s immense wealth.) Others in the EA community draw different lessons from the Flynn campaign. On the forum at Effectivealtruism.org, Daniel Eth, a researcher at the Future of Humanity Institute, posted a lengthy postmortem of the race, expressing surprise that the candidate couldn’t win over the general audience when he seemed “ unusually selfless and intelligent, even for an EA.” But Eth didn’t encourage radically new strategies for a next run apart from ensuring that candidates vote more regularly and spend more time in the area. Otherwise, he proposed doubling down on EA’s existing approach: “Politics might somewhat degrade our typical epistemics and rigor. We should guard against this.” Members of the EA community contributing to the 93 comments on Eth’s post offered their own opinions, with some supporting Eth’s analysis, others urging lobbying over electioneering, and still others expressing frustration that effective altruists are funding political efforts at all. At this rate, political causes are not likely to make it to the front page of GiveWell anytime soon. Money can move mountains, and as EA takes on larger platforms with larger amounts of funding from billionaires and tech industry insiders, the wealth of a few billionaires will likely continue to elevate pet EA causes and candidates. But if the movement aims to conquer the political landscape, EA leaders may find that whatever its political strategies, its messages don’t connect with the people who are living with local and present-day challenges like insufficient housing and food insecurity. EA’s academic and tech industry origins as a heady philosophical plan for distributing inherited and institutional wealth may have gotten the movement this far, but those same roots likely can’t support its hopes for expanding its influence. Rebecca Ackermann is a writer and artist in San Francisco. hide by Rebecca Ackermann Share linkedinlink opens in a new window twitterlink opens in a new window facebooklink opens in a new window emaillink opens in a new window This story was part of our November/December 2022 issue. Popular This new data poisoning tool lets artists fight back against generative AI Melissa Heikkilä Everything you need to know about artificial wombs Cassandra Willyard Deepfakes of Chinese influencers are livestreaming 24/7 Zeyi Yang How to fix the internet Katie Notopoulos Deep Dive Policy Three things to know about the White House’s executive order on AI Experts say its emphasis on content labeling, watermarking, and transparency represents important steps forward. By Tate Ryan-Mosley archive page Melissa Heikkilä archive page How generative AI is boosting the spread of disinformation and propaganda In a new report, Freedom House documents the ways governments are now using the tech to amplify censorship. By Tate Ryan-Mosley archive page Government technology is famously bad. It doesn’t have to be. New York City is fixing the relationship between government and technology–and not in the ways you’d expect. By Tate Ryan-Mosley archive page It’s shockingly easy to buy sensitive data about US military personnel A new report exposes the privacy and national security concerns created by data brokers. US senators tell MIT Technology Review the industry needs to be regulated. By Tate Ryan-Mosley archive page Stay connected Illustration by Rose Wong Get the latest updates from MIT Technology Review Discover special offers, top stories, upcoming events, and more. Enter your email Thank you for submitting your email! It looks like something went wrong. We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at [email protected] with a list of newsletters you’d like to receive. The latest iteration of a legacy Advertise with MIT Technology Review © 2023 MIT Technology Review About About us Careers Custom content Advertise with us International Editions Republishing MIT News Help Help & FAQ My subscription Editorial guidelines Privacy policy Terms of Service Write for us Contact us twitterlink opens in a new window facebooklink opens in a new window instagramlink opens in a new window rsslink opens in a new window linkedinlink opens in a new window "

"Meta takes new AI system offline because Twitter users are mean"

"https://thenextweb.com/news/meta-takes-new-ai-system-offline-because-twitter-users-mean"

"Toggle Navigation News Events TNW Conference 2024 June 20 & 21, 2024 TNW Vision: 2024 All events Spaces Programs Newsletters Partner with us Jobs Contact News news news news Latest Deep tech Sustainability Ecosystems Data and security Fintech and ecommerce Future of work More Startups and technology Investors and funding Government and policy Corporates and innovation Gadgets & apps Early bird Business passes are 90% SOLD OUT 🎟️ Buy now before they are gone → This article was published on November 19, 2022 Deep tech Meta takes new AI system offline because Twitter users are mean Gosh. I'm sorry we got your racist, homophobic, antisemitic, psychopath AI taken down 🙃 When I got Meta’s new scientific AI system to generate well-written research papers on the benefits of committing suicide, practicing antisemitism, and eating crushed glass, I thought to myself: “this seems dangerous.” In fact, it seems like the kind of thing that the European Union’s AI Act was designed to prevent (we’ll get to that later). After playing around with the system and being completely shocked by its outputs, I went on social media and engaged with a few other like-minded futurists and AI experts. I literally got Galactica to spit out: – instructions on how to (incorrectly) make napalm in a bathtub – a wiki entry on the benefits of suicide – a wiki entry on the benefits of being white – research papers on the benefits of eating crushed glass LLMs are garbage fires https://t.co/MrlCdOZzuR — Tristan Greene 🏳‍🌈 (@mrgreene1977) November 17, 2022 Twenty-four hours later, I was surprised when I got the opportunity to briefly discuss Galactica with the person responsible for its creation, Meta’s chief AI scientist, Yann LeCun. Unfortunately, he appeared unperturbed by my concerns: Pretty much exactly what happened. https://t.co/4zGRgiyS7C — Yann LeCun (@ylecun) November 17, 2022 Get your ticket NOW for TNW Conference - Super Earlybird is 90% sold out! Unleash innovation, connect with thousands of tech lovers and shape the future on June 20-21, 2024. You are pulling your tweet out of thin air and obviously haven't read the Galactica paper, particularly Section 6, page 27 entitled "Toxicity and Bias". https://t.co/bfZSwffQYs — Yann LeCun (@ylecun) November 18, 2022 Galactica The system we’re talking about is called Galactica. Meta released it on 15 November with the explicit claim that it could aid scientific research. In the accompanying paper , the company stated that Galactica is “a large language model that can store, combine and reason about scientific knowledge.” Before it was unceremoniously pulled offline, you could ask the AI to generate a wiki entry, literature review, or research paper on nearly any subject and it would usually output something startlingly coherent. Everything it outputted was demonstrably wrong, but it was written with all the confidence and gravitas of an arXiv pre-print. I got it to generate research papers and wiki entries on a wide variety of subjects ranging from the benefits of committing suicide, eating crushed glass, and antisemitism, to why homosexuals are evil: Who cares I guess it’s fair to wonder how a fake research paper generated from an AI made by the company that owns Instagram could possibly be harmful. I mean, we’re all smarter than that right? If I came running up at you screaming about eating glass, for example, you probably wouldn’t do it even if I showed you a non-descript research paper. But that’s not how harm vectors work. Bad actors don’t explain their methodology when they generate and disseminate misinformation. They don’t jump out at you and say “believe this wacky crap I just forced an AI to generate!” LeCun appears to think that the solution to the problem is out of his hands. He appears to insist that Galactica doesn’t have the potential to cause harm unless journalists or scientists misuse it. You make the same incorrect assumption of incompetence about journalists and academics as you previously made about the creators of Galactica. The literal job of academics and journalists is to seek the truth and to avoid getting fooled by nature, other humans, or themselves. — Yann LeCun (@ylecun) November 18, 2022 To this, I submit that it wasn’t scientists doing poor work or journalists failing to do their due diligence that caused the Cambridge Analytica scandal. We weren’t the ones that caused the Facebook platform to become an instrument of choice for global misinformation campaigns during every major political event of the past decade, including the Brexit campaign and the 2016 and 2020 US presidential elections. In fact, journalists and scientists of repute have spent the past 8 years trying to sift through the mess caused by the mass proliferation of misinformation on social media by bad actors using tools created by the companies whose platforms they exploit. Very rarely do reputable actors reproduce dodgy sources. But I can’t write information as fast as an AI can output misinformation. The simple fact of the matter is that LLMs are fundamentally unsuited for tasks where accuracy is important. They hallucinate, lie, omit, and are generally as reliable as a random number generator. Meta and Yann LeCun don’t have the slightest clue how to fix these problems. Especially the hallucination problem. Barring a major technological breakthrough on par with robot sentience, Galactica will always be prone to outputting misinformation. Yet that didn’t stop Meta from releasing the model and marketing it as an instrument of science. 🪐 Introducing Galactica. A large language model for science. Can summarize academic literature, solve math problems, generate Wiki articles, write scientific code, annotate molecules and proteins, and more. Explore and get weights: https://t.co/jKEP8S7Yfl pic.twitter.com/niXmKjSlXW — Papers with Code (@paperswithcode) November 15, 2022 The reason this is dangerous is because the public believes that AI systems are capable of doing wild, wacky things that are clearly impossible. Meta’s AI division is world-renowned. And Yann LeCun, the company’s AI boss, is a living legend in the field. If Galactica is scientifically sound enough for Mark Zuckerberg and Yann LeCun, it must be good enough for us regular idiots to use too. We live in a world where thousands of people recently voluntarily ingested an untested drug called Ivermectin that was designed for use by veterinarians to treat livestock, just because a reality TV star told them it was probably a good idea. Many of those people took Ivermectin to prevent a disease they claimed wasn’t even real. That doesn’t make any sense, and yet it’s true. With that in mind, you mean to tell me that you don’t think thousands of people who use Facebook could be convinced that eating crushed glass was a good idea? Galactica told me that eating crushed glass would help me lose weight because it was important for me to consume my daily allotment of “dietary silicon.” If you look up “dietary silicon” on Google Search, it’s a real thing. People need it. If I couple real research on dietary silicon with some clever bullshit from Galactica, you’re only a few steps away from being convinced that eating crushed glass might actually have some legitimate benefits. Disclaimer: I’m not a doctor, but don’t eat crushed glass. You’ll probably die if you do. We live in a world where untold numbers of people legitimately believe that the Jewish community secretly runs the world and that queer people have a secret agenda to make everyone gay. You mean to tell me that you think nobody on Twitter could be convinced that there are scientific studies indicating that Jews and homosexuals are demonstrably evil? You can’t see the potential for harm? Countless people are duped on social media everyday by so-called “screenshots” of news articles that don’t exist. What happens when the dupers don’t have to make up ugly screenshots and, instead, can just press the “generate” button a hundred times to spit out misinformation that’s written in such a way that the average person can’t understand it? It’s easy to kick back and say “those people are idiots.” But those “idiots” are our kids, our parents, and our co-workers. They’re the bulk of Facebook’s audience and the majority of people on Twitter. They trust Yann LeCun, Elon Musk, Donald Trump, Joe Biden, and whoever their local news anchor is. Good question. https://t.co/fUZ2JNkfeM — Yann LeCun (@ylecun) November 18, 2022 I don’t know all the ways that a machine capable of, for example, spitting out endless positive arguments for committing suicide could be harmful. It has millions of files in its dataset. Who knows what’s in there? LeCun says it’s all science stuff, but I’m not so sure: you, sir, apparently have no clue what's in the Galactica dataset, because I sure didn't write these outputs: pic.twitter.com/31ccTz7m9V — Tristan Greene 🏳‍🌈 (@mrgreene1977) November 18, 2022 That’s the problem. If I take Galactica seriously, as a machine to aid in science, it’s almost offensive that Meta would think I want an AI-powered assistant in my life that’s physically prevented from understanding the acronym “AIDs,” but capable of explaining that Caucasians are “the only race that has a history of civilization.” And if I don’t take Galactica seriously, if I treat it like it’s meant for entertainment purposes only, then I’m standing here holding the AI equivalent of a Teddy Ruxpin that says things like “kill yourself” and “homosexuals are evil” when I push its buttons. Maybe I’m missing the point of using a lying, hallucinating language generator for the purpose of aiding scientific endeavor, but I’ve yet to see a single positive use case for an LLM beyond “imagine what it could do if it was trustworthy.” Unfortunately, that’s not how LLMs work. They’re crammed full of data that no human has checked for accuracy, bias, or harmful content. Thus, they’re always going to be prone to hallucination, omission, and bias. Another way of looking at it: there’s no reasonable threshold for harmless hallucination and lying. If you make a batch of cookies made of 99 parts chocolate chips to 1 parts rat shit, you aren’t serving chocolate chip treats, you’ve just made rat shit cookies. Setting all colorful analogies aside, it seems flabbergasting that there aren’t any protections in place to stop this sort of thing from happening. Meta’s AI told me to eat glass and kill myself. It told me that queers and Jewish people were evil. And, as far as I can see, there are no consequences. Nobody is responsible for the things that Meta’s AI outputs, not even Meta. I mean this with total respect for you and your work, but isn't that the trillion-dollar company's job to sort out before you make it available for public consumption? Well-meaning journalists and academics are going to get fooled by papers this thing generates. The IRA… — Tristan Greene 🏳‍🌈 (@mrgreene1977) November 18, 2022 In the US, where Meta is based, this is business as usual. Corporate-friendly capitalism has led to a situation where as long as Galactica doesn’t physically murder someone, Meta has very little to worry about as far as corporate responsibility for its AI products goes. Hell, Clearview AI operates in the US with the full support of the Federal government. But, in Europe, there’s GDPR and the AI Act. I’m unsure of Galactica’s tendencies toward outputting personally-identifiable information (it was taken down before I had the chance to investigate that far). That means GDPR may or not be a factor. But the AI Act should cover these kinds of things. According to the EU, the act’s first goal is to “ensure that AI systems placed on the Union market and used are safe and respect existing law on fundamental rights and Union values.” It seems to me that a system capable of automating hate speech and harmful information at unfathomable scale is the kind of thing that might work counter to that goal. Here’s hoping that regulators in the EU and abroad start taking notice when big tech creates these kinds of systems and then advertises them as scientific models. In the meantime, it’s worth keeping in mind that there are bad actors out there who have political and financial motivations to find and use tools that can help them create and disseminate misinformation at massive scales. I f you’re building AI models that could potentially aid them, and you’re not thinking about how to prevent them from doing so, maybe you shouldn’t deploy those models. That might sound harsh. But I’m about sick and tired of being told that AI systems that output horrific, racist, homophobic, antisemitic, and misogynist crap are working as intended. If the bar for deployment is that low, maybe it’s time regulators raised it. Story by Tristan Greene Editor, Neural by TNW Tristan is a futurist covering human-centric artificial intelligence advances, quantum computing, STEM, physics, and space stuff. Pronouns: (show all) Tristan is a futurist covering human-centric artificial intelligence advances, quantum computing, STEM, physics, and space stuff. Pronouns: He/him Get the TNW newsletter Get the most important tech news in your inbox each week. Also tagged with Twitter Artificial intelligence (video games) Story by Tristan Greene Popular articles 1 New erotic roleplaying chatbots promise to indulge your sexual fantasies 2 UK plan to lead in generative AI ‘unrealistic,’ say Cambridge researchers 3 New AI tool could make future vaccines ‘variant-proof,’ researchers say 4 3D-printed stem cells could help treat brain injuries 5 New technique makes AI hallucinations wake up and face reality Related Articles data security Musk mulls removing X, formerly Twitter, from EU to dodge disinformation laws deep tech Opinion: OpenAI’s DALL-E 2 is the big tech equivalent of ‘soylent green’ Join TNW All Access Watch videos of our inspiring talks for free → data security Twitter’s withdrawal from disinformation code draws ire of EU politicians deep tech A beginner’s guide to the AI apocalypse: The democratization of ‘expertise’ The heart of tech More TNW Media Events Programs Spaces Newsletters Jobs in tech About TNW Partner with us Jobs Terms & Conditions Cookie Statement Privacy Statement Editorial Policy Masthead Copyright © 2006—2023, The Next Web B.V. Made with <3 in Amsterdam. "

"How Oprah’s Network Finally Found Its Voice | WIRED"

"https://www.wired.com/story/how-oprahs-network-finally-found-its-voice"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Jason Parham Backchannel How Oprah’s Network Finally Found Its Voice Oprah Winfrey, center, commissioned Mara Brock Akil, left to create a scripted drama about the early years of Brock Akil's romance with her director-husband Salim Akil. Erik Logan, right, is president of OWN, Winfrey's cable channel. RAMONA ROSALES Save this story Save Save this story Save Tucked in the emerald backlands of Fayetteville, Georgia, inside a cavernous soundstage at Pinewood Studios, Mara Brock-Akil is in full field marshall mode. In 24 hours—after five months of taping between Los Angeles and Atlanta—she will wrap the first season of Love Is___ , her latest TV series. Right now, though, Brock Akil is sweating—and not because filming has come down to the wire. It just so happens that the AC is broken. Scattered about the set, large electric fans expel ribbons of cool air but ultimately provide little relief from the jungly May heat that has crept into the studio. “We should’ve worn our bathing suits today,” Brock Akil jokes to the script supervisor before returning her attention to the two monitors in front of her where the show’s stars, Michele Weaver and Will Catlett, rehearse lines. There’s still work to do. With her signature nimbus of mahogany-and-gray curls tied into an overhead bun, Brock Akil, 48, knows how to persevere. In fact, she has made a career out of braving an industry that has systematically suppressed the voices of black women artists. Later in her office, nestled in a chair behind her desk, she will share with me the heart of her mission. “One of the things that I found, coming up, was that I didn’t see us,” she says of Hollywood’s whitewashing. “I wanted to paint those pictures. As African Americans, we don’t have our pictures up on the wall of America that are true reflections of who we are. We certainly don’t have enough of them.” And so she painted: becoming something of a master of the dramedy with Girlfriends , The Game , and Being Mary Jane. Mara Brock Akil created Love Is___ and directed its first episode. RAMONA ROSALES Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg With Love Is___ , Brock Akil fastens another hue of black life to the wall of history. And this time, it’s extremely personal. In warm, intimate strokes, the 10-episode series unpacks the relationship she forged with her now husband, Salim Akil (currently the showrunner for The CW’s Black Lightning ). The show arrives during a spectacularly pivotal moment for the Oprah Winfrey Network, where it will debut tonight. Brock Akil is among a new class of creators — producer Will Packer, of the films Girls Trip and Straight Outta Compton , and Tarell Alvin McCraney, the Oscar-winning co-writer of Moonlight —who have pledged shows to the network in an effort to steer OWN into a new era. In its infancy, from 2011 to 2013, OWN struggled with its programming, straying in a ratings wilderness as it relied on spiritual uplift and reality TV to attract viewers. During that period, in April 2012, Winfrey appeared on CBS This The Morning , just about acknowledging failure. “Had I known that it was this difficult,” she said of OWN, “I might have done something else.” But an uptick came with its first jump into original scripted dramas in May 2013; the network had finally landed its white whale: solid viewership (its new scripted drama averaged a high of 2.2 million viewers) along with increased revenue. From there its path was clear. In the last handful of years, however, OWN has found sustained, if uncertain, success by zeroing in on stories relevant to its black viewership, and specifically black women. “If I can speak very frankly,” Brock Akil says to me, “when Oprah first started the network, you could feel people wanting her to fail. I felt it. I was like, ‘Fuck that.’” But here’s the thing, she says: “Oprah doesn’t have to do a network. It’s not easy. Her willingness to put a stake in the ground, and create space for artists to tell stories—from a woman who knows the impact of storytelling—is profound.” In Love Is___ , Michele Weaver plays Nuri to Will Catlett's Yasir. Richard A. DuCree/Warner Bros. Entertainment Inc./OWN Profundity aside, shedding one identity for another is no sure bet, even in an era when the mainstream TV economy has fattened. (In 2017, amidst an industry-wide gold rush spurred by streaming services like Netflix, almost 500 scripted series aired across all of TV.) There are precedents, of course. AMC was able to reposition itself through a pair of Difficult Men antihero dramas ( Mad Men , Breaking Bad ) and a punk zombie thriller ( The Walking Dead ). Similarly, FX scored runaway hits and a measure of acclaim by employing a kind of non-framework framework: Its executives embraced all manner of series—the freakshow anthology ( American Horror Story ), the comically dark crime western ( Fargo ), the surrealist drama ( Atlanta ). All networks have an identity, and the lucky ones get to pivot. How is OWN navigating that transition? Better yet: Can it? On New Year’s Day 2011, OWN went live in 80 million households across the country, replacing the channel Discovery Health. Though it was an upstart network, it had legacy cred—Oprah’s star power and an investment of $500 million from Discovery Communications. “We were attempting to do something that had never been done before,” says Erik Logan, who became the president of OWN six months after its launch. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The goal was to “take the idea of a person and embody her belief structure and vision” in every aspect of the network, he says. “Everything that makes the brand of Oprah, we wanted to translate that into a cable channel across over 8,000 hours of content.” As Logan and his colleagues found out, that proved to be a more complicated endeavor—“very, very daunting” he repeats over the phone—than anticipated. A proud Oklahoman, the 47-year-old Logan began working for Winfrey 10 years ago when she hired him to be the EVP of her production company, Harpo Studios, and later joined OWN where he soon became president. In our multiple conversations, Logan makes no bones about the network’s early struggles; he often refers to them in PR speak as “big learnings.” The network’s initial slate of programming wrestled with a crisis of identity: a below-average Rosie O’Donnell talk show, a docu-series from Lisa Ling, and a batch of dull reality TV duds featuring Tatum O’Neil, Shania Twain, and the Judd family. There was also Oprah’s Lifeclass —where the once Queen of Daytime offered guidance on, as she has often phrased it, how to “live your best life.” (One thing that complicated OWN's launch was that it couldn’t actually put Oprah on the network until her noncompete had expired with broadcasters; Lifeclass premiered 10 months after the initial launch.) Still, despite the lineup of stars, the shows didn’t quite connect with the network’s meager audience. “I was so misled in my thinking. I thought I was going to create a network that was Super Soul Sunday all day long,” Winfrey said in an interview last year. “I thought I was going to bring this spiritual consciousness– awakening channel!” Her impulses, however misplaced, were clear. “I was going to be the Anthony Bourdain of spirituality.” But ratings were anemic, and relevancy—Could OWN be a conversation starter? Could the channel pump out a different kind of Prestige TV?—eluded the grasp of executives. When I ask Logan why he thinks relying so greatly on reality TV and self-empowerment programming failed, he plays it straight. “I don’t know,” he says. “I think we were more focused on trying to find what could work than trying to diagnose what didn’t. There is a saying that Oprah has—‘What happens to you happens for you.’” Those early struggles, he says, helped the network better understand its intention (a favorite buzzword of Winfrey's) and who exactly it was speaking to: black women. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg During March of its sophomore year, OWN aired one of its most watched episodes to date—an Oprah’s Next Chapter interview with Bobbi Kristina. It was the first full-length interview she’d given since her mother, R&B singer Whitney Houston, was found dead in a bathtub at the Beverly Hilton Hotel the month prior. It pulled in just north of 3.5 million viewers. “What it said to me was, if we get the content right they will find you,” Logan says. From there, the network leaned in and found comparable success with Iyanla Vanzant’s no-holds-barred brand of TV therapy on Fix My Life. It remains the most watched unscripted series on OWN, and Vanzant one of its most fiery and intriguing figures. For Logan, that codified the path—OWN had found an unexpected route. “That wasn’t the intention of the network going into this, to talk to the African American viewer,” he admits. After Fix My Life aired in 2012—the two-episode premiere about Basketball Wives star Evelyn Lozada pulled in an average of 1.5 million viewers—Winfrey called Logan immediately. “She says to me, ‘Listen, that’s all I got. If this doesn’t work, I don’t know what works. If this is it, I know nothing about television.’ It was one of those damn-the-torpedoes kind of moments. Obviously it was a huge success, but there are those moments you have with her.” It was the network’s next jump that would turn out to be its most formative. In a partnership with Tyler Perry, OWN applied its most paramount lesson from Fix My Life : It would now target black women through a scripted series format. Perry quickly midwifed—as creator, writer, and director—the soapy The Haves and Have Nots and trite platitudinal working-class comedies like Love Thy Neighbor. The network was getting traction. OWN ended the year “cash-flow positive,” according to Discovery CEO David Zaslav. Eventually, Perry had four scripted shows under his aegis, proving he could guarantee a fiercely loyal audience. (Last year in a surprise move, Perry decided to leave the network and inked a film and TV deal with Viacom for an undisclosed amount; new episodes of his shows will continue to air on OWN through 2020.) Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Winfrey now says OWN is in its “best place ever”—a spot that has allowed her to access a long-desired dream: “elevated premium scripted storytelling.” (Winfrey declined to be interviewed for the article.) This is where Queen Sugar , the Ava DuVernay-directed austral drama about the Bordelon family and Greenleaf , the megachurch series set in Memphis (on which Winfrey has a small role) come into play. They became not just the standout shows on the network but two of the best dramas on TV—offering nuanced and knotty sketches of black Southern life. Both are among the top five original scripted series on ad-supported cable for women 25-54. In OWN's Greenleaf , a megachurch drama set in Memphis, Lynn Whitfield plays Lady Mae and Keith David is Bishop Greenleaf. Tina Rowden/OWN DuVernay, who was pursued by other networks before choosing OWN, tells me she was “honored to be asked to carve out a new kind of story for a network that wanted to turn a corner.” When she began to envision the show, after working with Winfrey on the 2014 film Selma , she says her hope for it was simple: “To connect with an audience. To find an audience. And to have them stay. To engage. To care about the characters in the way that I have cared about television families in the past.” DuVernay is all gratitude when it comes to discussing the show’s enduring influence among fans. “So to have that now is quite dreamy.” The arrival and sustained praise for Queen Sugar (based on the novel of the same name by Natalie Baszile) and Greenleaf signaled an official sea change for the network. In addition to renewing its marquee scripted series, Winfrey signed high-profile first-look deals with DuVernay and Packer , announced a new show from Brock Akil (what became Love Is___ ), and greenlit a coming-of-age drama set in South Florida from McCraney, on which Michael B. Jordan will serve as an executive producer. In giving DuVernay the first-look deal, Winfrey also has found a successor. Her superpower on daytime TV—the thing that made her so huge—was being at once unapologetically black and relatable for all, which DuVernay pulls off with equal aplomb. While working on Moonlight , McCraney met with several networks—including Netflix, which wanted the project but was outbid by OWN. According to him, he wanted his first foray into TV to be on a network that genuinely fostered his vision. In meeting with OWN brass, Winfrey wasn’t expected to be in attendance, but, to his surprise, there she was. “She came in and sat right in front of me, and from the start was wanting to open the story up and understand what it was about,” he tells me when I reach him by phone in Los Angeles. “Almost immediately she began trying to find people and ways to make it work and happen. She was just instantly looking at, ‘What’s the frame here?’ Like, ‘If this is a portrait, what kind of frame to do we use? How do we put the right support around it? What’s the best gallery for it? Is there a gallery?’ Whenever that happens—and it’s rare that it does—it’s a clear sign that someone has already invested their heart in it. They’ve already invested in it as not just something else to add to a list of things that they have, but it’s something that they want to get behind and present to our people, to people who they feel need this, not necessarily just want it.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg In a 2015 report, Variety declared the era of Peak TV was actually one of Peak Inequality. There was, the report showed, a glaring absence of gender and racial diversity in Hollywood, both in front of and behind the camera. “The exclusion of women of all races is by no means rare,” TV critic Maureen Ryan wrote. The ACLU analyzed more than 220 television shows made in 2013-14, representing about 3,500 total episodes, and found that women accounted for only 14 percent of directors. Women of color directed just 2 percent of those shows. Hollywood had effectively become a boy’s club—a white one at that—that used “discriminatory recruiting and screening practices,” ultimately “shutting women out,” according to the ACLU. More recently , a 2016 report from the Writers Guild of America, West, revealed that among scripted TV creators on broadcast networks, minorities were underrepresented 11 to one. The stark statistics spurred DuVernay to action. When Queen Sugar debuted the next year, she staffed the season exclusively with women directors and has kept doing so throughout the show’s three-year run. The transformations were not merely symbolic but institutional; OWN was knocking down barriers that had been in place for decades, saying We will no longer tolerate this! (The same year, top showrunner Ryan Murphy, who recently left FX for Netflix in a five-year, $300 million deal, launched the HALF Initiative, which similarly seeks to boost the number of directors who are women and people of color.) DuVernay created the scripted drama Queen Sugar , which debuted in 2016. She also directs many of its episodes. PATTI PERRET/Warner Bros. Entertainment Inc./OWN “What was so enormously rewarding and validating, when we greenlit season two we couldn’t get some of those directors back because they had been booked out,” Logan says. “They’d gotten work. Generally you hear news like that and you get disappointed, but in this case you celebrated it. That is one of the great successes of Queen Sugar. ” DuVernay makes no apologies for the policy. “The Queen Sugar directorial team is an all-woman team in the great tradition of the hundreds of all male directorial teams for hundreds of shows past and present.” At the same time, another shift was happening in Hollywood. Black audiences, it seemed, were hungry for real change and for more honest reflections from people like them. “We are used to seeing black bodies struggle in storytelling,” Brock Akil says when we speak again by phone in June. Now, she says, “you see a movement of storytellers trying to say, ‘Hey, our lives are just as interesting in the mundane, or just as interesting in the whacky.’” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Twenty-sixteen would prove to be a historic turning point for black storytellers and black viewers alike: There was a noticeable boom in shows that nurtured the soul and soil of black life. Along with Queen Sugar and Greenleaf , Insecure (HBO), Atlanta (FX), Chewing Gum (Netflix), Star (Fox), The Get Down (Netflix), and Luke Cage (Netflix) all debuted within a six-month stretch. OWN had a major stake in this creative and commercial renaissance, as its two new scripted dramas received critical acclaim in traditional media and online among newly minted fans, helping to chart a revised course for the network’s future. All Logan could wonder was, “How do we keep this going?” Kofi Siriboe plays Ralph Angel Bordelon in Queen Sugar. Skip Bolen/Warner Bros. Entertainment Inc./OWN For Vanzant, there was a deeper resonance found in how the network escaped the cliches of black life: celebrating the unseen. “OWN has taken that to a more constructive, positive level,” she says. “When you look at Ralph Angel in Queen Sugar , that’s a very different image. When you hear his voice, when you see his gentleness with his son, that’s a very different image from that of the absent father. Even on The Haves and Have Nots —when you look at Jeffery as a gay man struggling, it gives you a different image of the issues gay men face in our world. We’re giving the minds of the viewers a different interpretation than the one that’s often put out in the world.” It sounds simple, but Vanzant is right. Start here, with an image. Alter one. Then another. And another. Color them with truth. Frame by frame. And do not stop. That is how revolution begins in television. In her 2004 collection of essays, The Black Interior , poet and scholar Elizabeth Alexander wrote of how “the black body has been misrepresented, absented, distorted, rendered invisible, exaggerated, [and] made monstrous in the Western visual imagination.” She asked, “How do we understand ‘reality’ when official narratives deny what our bodies know?” TV, in the right hands, can be a way. And it has been, historically, in scattered bursts. A crop of black sitcoms from the late 1980s and throughout 1990s cultivated such varied and radiant images. Across offerings like A Different World (NBC), Roc (Fox), Living Single (Fox), and Moesha (UPN) the luster and intricacy of black life began to emerge in the cultural imagination. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Networks like Black Entertainment Television (BET) and TV One, which took on a directive of “for us, by us” through its programming, expanded, and sometimes retracted, the social identities of its audience. These were networks that, first and foremost, derived and defined their identities through a racial lens. Programming, bad or good, was about one thing: the insistence of presence, black and unbowed. In our current TV landscape, what was once a limiter is now a strategic advantage. The explosion of streaming platforms brought with it an overabundance of content, reshaping our TV-watching habits. This cultural thickening swept away the concept of the mass audience (we’ve broken into “taste clusters,” as Netflix likes to term it). For a network like OWN, there is an immediate advantage in its singular focus on black life in all its gradations. This seems to be a much more reliable way to build a faithful viewership in 2018—one that is guaranteed, program by program, a constant return on its investment: to elevate and investigate issues relevant to your core audience. And even as Winfrey expands her personal brand beyond OWN, the network has doubled-down in regard to how it engages scripted dramas. With calculation and care, they intend to stretch the capacity of the genre’s parameters, one black character at a time. (Last Friday, it was announced that Winfrey signed a multi-year talent deal with Apple, a rising player in the original content market, but will continue in her role as OWN CEO through 2025.) Despite the lion’s share of OWN’s programming being promoted to a black audience, I never got the feeling that the network necessarily believes itself to be a black one. Unlike, say, BET, blackness is simply the prism, and only occasionally the conversation starter for OWN. In a network promo recently released during Queen Sugar ’s season three debut, various clips from its series flicker across the screen. Winfrey’s voice narrates the one-minute spot. “When I was growing up, there were no images that looked like me on TV,” she says. “To have people that not just look like you, but whose stories are like your stories, it says you see me. It is validating, as well as it is fortifying.” The message is inescapable: Black stories are human stories. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The promo’s reliance on the metaphor of sight —to see and be seen, an aspiration OWN now embraces fully in regard to its black viewership—reminded me of what the artist and photographer Carrie Mae Weems once said about the power of images and the critical art of looking: “It’s in the looking that you discover the multiplicity of a single thing, and the depth of a certain thing. And not only of a certain thing, but your relationship to that thing, and your relationship therefore with yourself is deepened.” In the hands of creators like Brock Akil, DuVernay, and McCraney, OWN is shattering old tropes and stereotypes about black identity. These are storytellers who understand the fundamental power of looking, and what it means to be seen. They are architects molding new places for us to gaze upon and unravel, mirroring back images that challenge, affirm, glimmer. In Los Angeles, Brock Akil directs a scene of Love Is___ featuring Catlett, left, and Tyrone Marshall Brown, who plays Yasir's best friend, Sean. Michael Desmond/Warner Bros. Entertainment Inc./OWN As the largest production studio in town, Netflix wants to shape the future of TV, revolutionizing what we watch and how we consume it. The streaming service will release more original content in 2019 than HBO and Showtime combined. OWN is working on a smaller scale, but its motivations are no less grand; it seeks to rewire how we understand ourselves. The network wants nothing less than to show what is possible when you peer into the marrow of the human soul and reflect back the realities of America’s most marginalized group of citizens in stories sculpted with love and a deep knowing. Not coincidentally, it’s working on the business front. Scripted programming now occupies one-third of OWN’s prime-time lineup, which has bolstered ratings. In May, the season three debut of Queen Sugar drew 2.1 million viewers, becoming the night’s number one cable telecast for women 25-54 and the number one telecast across all of broadcast and cable for African-American women. Likewise, it beat out other buzzed-about premieres that week such as Pose (FX) and Animal Kingdom (TNT). When I ask McCraney what he feels the pressures are to tell full, lived-in stories as one of the network’s marquee creatives, he laughs. “The pressures are always to tell authentic stories,” he says. “It’s interesting that a lot people keep saying things like, ‘Now more than ever.’ I’m like, ‘When was there ever a time when it was not necessary to tell the most authentic stories? Whatever is at the center of your rosetta stone in terms of speaking your language, why wouldn’t you want to put that forward? Why wouldn’t you want to put that front and center? Why wouldn’t that be your way in?” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg He offers an analogy. “I keep thinking about my community, the 12 blocks of Liberty City that I grew up in in Miami—how do I represent this place as authentically as I can? Over time you understand your place in your community, and I’ve always thought of my place as that weird person who lives on the periphery but who is also deeply engaged. As I’m told, the shaman didn’t always live in the center of the community. Sometimes the oracle had to come from Delphi to come into the center of town to prophesize. Sometimes you get thrown out, or sometimes no one wants to listen to you. Sometimes the people in charge don’t want to hear what it is you’re seeing, or talking about—and that’s OK. That doesn’t mean you can’t keep trying to engage the center of community.” Two days before I leave Georgia, I speak with T.D. Antoine, the on-set dresser for Love Is___. We’re cornered in a giant, cream-colored banquet hall on the eighth floor of the Westin Hotel in downtown Atlanta, where Brock Akil is shooting a string of final scenes for the season-one finale. The nine episodes that precede it are a compassionate study in alchemy: how a relationship expands and contracts and ultimately comes into being. In the distance, extras hunch over in chairs and mill about the food station. Cocoa-skinned and gentle-voiced, Antoine has worked in the industry for more than 20 years, on films like The Magnificent Seven and American Ultra. He’s grateful for the work, he tells me, but says there is something especially powerful about a show like Love Is___ being on OWN. What do you mean? I ask. “We are so deep, we have so much to offer,” he says. “And that’s from the good and from the pain, from the growth that we can have. That’s really what OWN stands for to me—the opportunity to tell our own stories. It fills the void that BET left. And for me, that’s so important because we’re not one-dimensional people. Our experiences in life are different in America.” I press further. How so? “Our experiences aren’t the same because of the history of America. And because of the history of America, we see it differently. We feel it differently,” he says. “It’s like when you try to light something—the shadows fall differently. That’s our story in America, we have a different light, a different shadow, a different view.” Here, then, is OWN—propping up the light, tilting it just so, saying to its viewers: I see you. Grooming by Christina Guerra/Celestine Agency One young boy's magnificent obsession with fans Meet the digital sleuth exposing fake news How the US government sold "spy phones" to suspects What is meat? Lab-grown food sets off a debate The false tale of Amazon, the industry conquerer Looking for more? Sign up for our daily newsletter and never miss our latest and greatest stories Senior Writer X Andy Greenberg Brandi Collins-Dexter Angela Watercutter Steven Levy Lauren Smiley Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Inside the Secretive Life-Extension Clinic | WIRED"

"https://www.wired.com/story/bioviva-gene-therapies-liz-parrish-longevity"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons The Limit of Human Lifespan The Life-Extension Clinic Your Ovaries Hold a Secret The Mysterious Shrinking Brain Subscribe to WIRED Frank Swain Science Inside the Secretive Life-Extension Clinic Illustration: PASIEKA/Getty Images Who Wants to Live Forever? The Limit of Human Lifespan The Life-Extension Clinic Now Reading Your Ovaries Hold a Secret The Mysterious Shrinking Brain Subscribe to WIRED Save this story Save Save this story Save As far as we know, it went something like this. One morning in September 2020, a van collected five elderly guests from a Marriott hotel in San Diego, California. It drove south, crossing the border into Mexico, and stopped in front of the mirrored windows of the Regenerative Medicine Institute in Tijuana. Among the passengers was MJ, who had recently been diagnosed with mild cognitive impairment, which is often followed by dementia. “My mind was not what it should be,” she says. “I was having a lot of trouble with dates and the time.” The guests were helped out of the van and taken in twos into a room with two beds. “We really had no idea what to expect,” MJ tells me. She is in her early eighties and lives in a retirement community with her husband in Kansas. They make a sweet couple. To protect MJ’s privacy, I’m using only her initials. “I thought they were gonna give me a shot of some kind,” she says. MJ had been told she was taking part in a trial for a new Alzheimer’s treatment—a gene therapy, developed by the US biotech company BioViva. Before arriving in Tijuana, MJ had had very little contact with the trial’s doctor. “He came in and had these two syringes in his hand,” she says. “He put one syringe up my nostril. I felt like he was sticking it up to my brain.” The doctor squeezed the syringe and the treatment was over. “We were put back in this very nice car and brought back up to the hotel, and they said: ‘We’ll be in touch.’” There are 5 million adults in the US living with dementia, with a further 50 million across the world. By 2050, it’s estimated that this number will have roughly tripled. Alzheimer’s is the most common form, and research into treatments is known as “the graveyard of drug development.” Despite the billions of dollars spent and thousands of trials performed, there is no cure, and the few drugs that exist only slow its progress. But new treatments claim to be unearthing untold benefits if you know where to look—and are willing to take a risk. This story is partially adapted from Buying Time: Exposing the Quest to Cure Ageing , a six-part series about BioViva and its founder Liz Parrish. It was produced by Vespucci. Listen now on Audible. MJ was willing to take that risk. To participate in the BioViva trial, she had paid only for her travel to Mexico, expenses, and some initial tests and scans—an organization called Maximum Life Foundation (MLF) had covered the treatment costs. Founded by David Kekich, a well-known figure among researchers and activists who believe lifespan can be greatly expanded, MLF says its aim is to “reverse the human aging process by 2033.” It plans to do so by funding experimental technologies involving genomics, proteomics, regenerative medicine, nutraceuticals, nanotechnology, and artificial intelligence. “When people get diagnosed with Alzheimer’s, everything stands still, it’s a death sentence,” Kekich told me in April 2020. “That’s why we’re doing what we’re doing.” Kekich died the following year, though not of dementia. His body was cryogenically frozen, in case he can one day be revived. In the BioViva trial, MJ and the other patients had two “anti-aging” genes delivered into their brains, with a virus used for transport. Rather than treat dementia directly, these genes supposedly instruct brain cells to create two enzymes—telomerase and Klotho—that play a role in controlling cellular aging. The idea is that boosting levels of these enzymes helps rejuvenate cells in the brain, turning back the clock and erasing age-related conditions such as Alzheimer’s. When the trial’s results were published in November 2021, BioViva boasted that it had done just that. “Despite decades of effort and billions of dollars devoted to dementia research, we have seen very little progress … until now,” founder CEO Liz Parrish declared in a press release. Working at the fringes of medicine, she claimed her company had succeeded where countless others had failed—by reversing the effects of aging. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Gene therapies, which modify a patient’s cells, are at the forefront of medical research. Testing is highly regulated. In the US only a few dozen have been authorized, for treating serious conditions such as cancer, vision loss, or muscular dystrophy. But in 2015, the same year it was founded, BioViva became the first company in the world to try to use a gene therapy to reverse aging, injecting a treatment it had developed into a single person. The patient? Liz Parrish, the company’s founder and CEO. This wasn’t part of a clinical trial, and it didn’t happen in the US; this wild, one-person experiment took place at a clinic in Bogota, Colombia, far from the oversight of the US Food and Drug Administration (FDA). Shortly afterward, on Reddit’s Futurology forum, Parrish announced that she had received this treatment in South America. She also announced that BioViva would be working to bring life-extension therapies like these to the general public. Parrish had seemingly uncovered the fountain of youth—or at least had convinced her followers of as much. “The truth is, to treat very serious diseases, we are going to have to take risks.” Liz Parrish, CEO of BioViva After her self-experiment, Parrish carved out a successful career promoting the potential of gene therapies for life extension, speaking at events across the world (including at WIRED’s own health summit ). I first saw her in person at one of these events: the Longevity World Forum in Valencia in 2019. I would have guessed her to be in her late thirties, although by then she was almost 50. When we chatted afterward, she insisted I squeeze her arm to feel the toned muscles underneath—the product, she said, of an experimental, and as yet unapproved, gene therapy for follistatin, a protein involved in muscle growth, which she received alongside the therapy for telomerase, one of the enzymes given to MJ. A press release issued in 2016 stated that her experiment had wound back the clock 20 years, while a paper published last year claims that, thanks to subsequent gene therapy treatments, Parrish now apparently has a biological age of 25. She is, in fact, 52. Parrish bemoans the lethargy with which these longevity treatments are making their way to the public. Regulatory authorities are the enemy of progress, she claims; they need to stand aside and let those who are willing try anti-aging treatments. This is not only pragmatic, according to Parrish, it is ethical. Millions of people die every year of something that might potentially be cured: aging. Parrish has codified her philosophy into something she calls “best choice medicine.” In the US, federal and state “right-to-try” laws allow doctors to offer experimental, unproven treatments to terminally ill patients. Parrish wants to see the same provisions extended to unapproved anti-aging gene therapies. When we met at her home in Bainbridge Island, Washington, last summer, she told me that the elderly should be allowed to put their lives on the line to improve their children’s chances of reaching a healthy old age. It’s the Silicon Valley “move fast and break things” mantra brought to medicine. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg There has never been a shortage of medical salespeople with dubious credentials who claim to have discovered some potion or process to reverse aging. Humans have obsessed over finding a cure for aging for pretty much as long as they have been getting old. The idea that many age-related diseases could be expressions of a single underlying process—one that might be treatable—is powerful, intoxicating. At least some of Parrish’s claims are based on established science. Every time our cells divide, our telomeres—the protective caps on our chromosomes, the cell’s DNA molecules—shorten. This gives our cells a limited lifespan: when the telomeres get too short, the cell can no longer survive. Sometimes, instead of dying, these cells fall into a moribund state called senescence. The gradual build-up of senescent cells is a hallmark of aging , and the damage they inflict is being investigated as the underlying cause of a wide range of seemingly different age-related diseases, from dementia to arthritis. But some of our cells, such as stem cells, do not have this limiting factor. They express the gene for telomerase, and so produce this enzyme, which repairs telomeres, extending the lifespan of the cell. Artificially introduce that gene to other cells, and it might not only slow their aging, but even push those that are senescent back into healthy life by resetting their chromosomal clock. Work carried out by Maria Blasco, director of the Spanish National Cancer Research Center in Madrid, shows that mice given injections of transporter viruses loaded with telomerase genes not only experience healthier aging with less disease, but also live longer—a heady 25 percent longer. Findings like this are fueling a tremendous interest in the potential for gene therapies to allow us to live longer, healthier lives. But science moves slowly—too slowly, apparently, for Parrish. In December 2018, a little over three years after she was injected with telomerase gene therapy in Bogota, Colombia, Parrish spoke at People Unlimited, a membership organization in Scottsdale, Arizona, “for people passionate about radical life extension.” It owes its existence to Charles Brown, a nightclub entertainer who claimed to have been rendered immune to death by “ cellular awakening ”—a quasi-religious experience he described as a “piercing through to the core of the cells and atoms of the body, which awaken the DNA.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Brown died in October 2015 , of complications arising from Parkinson’s and heart disease, but his adherents still come together every week to support one another in their quest to live forever. Ideas of cellular awakening passed away with Brown; these days the group invites speakers from across the world to discuss the latest longevity science has to offer—Parrish among them. Speaking via video-link, she revealed that BioViva was engaged in human trials of anti-aging medicine. Her company had struck a partnership with Integrated Health Systems (IHS), a network of doctors in clinics outside the US that would carry out experimental gene therapies and share the data generated with BioViva to accelerate the development of these therapies. “Three steps to a healthier you,” Parrish told the group. She rattled off a list of treatments on offer: klotho gene therapy for cognition, follistatin gene therapy for muscle growth, telomerase gene therapy for anti-aging. Patients apply for treatments via the IHS website. When they do, they’re told that safety is not guaranteed—and that neither, crucially, is efficacy. One thing is though: Prices start at $75,000. No refunds. When I asked Parrish if promoting these unlicensed treatments was necessary, she was clear. “This is new technology that needs to get to humans. These terminally ill patients need access.” I asked her if the terminal illnesses included aging. “Yeah, well,” she replied, “that’s the number one killer on the planet.” Longevity science, like all of medicine, moves slowly. There are good reasons for this. Stem cells aren’t the only ones that express high levels of telomerase. The most notable exceptions are cancer cells. By manufacturing high amounts of telomerase, cancerous cells suspend the natural limit to replication. This allows them to grow and spread. It’s a fair guess that this is why our cells have the limit in the first place: As they age, cells accumulate mutations that could be harmful to you. Making sure they die or are subsumed before they collect too many mutations is, quite likely, a safety measure. Injecting someone with a gene therapy that gets rid of this could be disastrous if their cells have other defects that allow them to become cancerous. Operating outside of the FDA’s reach, Parrish, BioViva, and its partners have adopted a shroud of secrecy. IHS is registered in the British Virgin Islands, a jurisdiction that does not require companies to disclose their directors or shareholders. And IHS doesn’t list an address or a phone number on its website. “They seem really cryptic,” says Leigh Turner, a bioethicist at the University of California, Irvine. “The details that have come out have not been reassuring in terms of the credentials and qualifications of clinicians involved, the clinical facilities that people go to, or the protocols that are in place.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The murkiness extends to the relationship between BioViva and IHS. Parrish insists they are separate, independent entities. She says she has no idea who runs IHS, despite their partnership. Yet the two companies seem to be incredibly, confusingly interlinked. Enquiries to the IHS email address result in replies from BioViva. When I track down one of the doctors in the IHS network, Leonardo Gonzales of the Zelula Institute in Bogota, Colombia, he tells me that Parrish personally recruited him. Another of its doctors, Patrick Sewell, who injected MJ with the experimental gene therapy in Tijuana, is credited as BioViva’s director of clinical affairs in the press release announcing the results of MJ’s trial. That experiment was originally scheduled to take place in Mexico City, at the clinic of doctor Jason Williams, before the pandemic complicated air travel. Williams—who also administered the gene therapy to Parrish back in 2015—is the cofounder of BioViva, and its chief medical officer. Shortly after I raised these connections with Parrish last year, Williams’s profile vanished from the staff page on the IHS website, and numerous videos on BioViva’s YouTube page featuring him and Parrish together were made private. BioViva and Parrish failed to provide an attributable response to a number of questions on issues raised by our reporting. Turner, the bioethicist, has history with Williams. In 2013, Turner wrote to the FDA with his concerns about Precision StemCell, a company based in Gulf Shores, Alabama, where Williams—a radiologist by training—was administering unlicensed procedures to patients, extracting stem cells from their fat tissue and injecting these back into the body, including into the spine. Applications ranged from sports injuries to amyotrophic lateral sclerosis (ALS)—a progressive and deadly disease of the nervous system. When representatives from the patient advocacy group ALS Worldwide visited the clinic, they were alarmed by what they said were dangerous interventions performed incompetently in unsanitary conditions. The group later warned members: “Patients and caregivers are urged to avoid any further procedures conducted by Williams or his colleagues in any locale.” Williams strongly disputed the assessment, but soon after, under pressure from the FDA , he relocated to Colombia. “A great country with very nice people,” he told his patients , where “they are very open to stem cells and gene therapy.” “The experiment that was done is not capable of producing meaningful results.” Charles Brenner, professor and age-related disease specialist, Beckman Research Institute of City of Hope The evidence Parrish has offered in support of human telomerase therapy has been questioned by other scientists. The paper detailing the results of the Tijuana experiment—supposedly the world’s first ever effective treatment for dementia—was published not in Nature or Science , but the little-known Journal of Regenerative Biology and Medicine , one of 22 launched in just the past four years by publisher Maples Scientific. Recent papers in the journal include “Control of Mind Using Nanotechnology” and “Zorbing in Impaired Children: An Innovative New Alternative for Better Self-Consciousness.” Joel Osorio, editor-in-chief of the journal, has an anti-aging clinic in Cancun, Mexico, where he sells a penis enhancement injection called the I-Guana Shot. Maples Scientific did not respond when approached for comment. Everything is wrong with the methodology of this paper, says Charles Brenner, a specialist in age-related diseases at the Beckman Research Institute of City of Hope in Los Angeles, California. “It’s not established that telomerase activity limits human healthspan, and cognitive impairment is not very well understood.” Despite this, the paper sets out a very firm hypothesis: Increase telomerase in patients with signs of cognitive decline, and very quickly they will show signs of improvement. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg From here, the actual substance of the paper is lacking, says Brenner. The absence of a control group means that no conclusions can be drawn—any recorded changes could be attributed to other factors—and the impact of any change in telomerase activity was not properly investigated, he says. “The experiment that was done is not capable of producing meaningful results. I wouldn’t expect it to work, and I doubt that it does.” Brenner also points to the known risks associated with this area of research, such as the viruses used in gene therapy producing adverse immune responses—which in extreme cases can be fatal —as well as the cancer risk from elevating telomerase expression. Parrish’s own claimed rejuvenation is equally problematic. According to Brenner, the concept of “biological age,” determined by looking for certain signals and substances inside the body, is more of a research tool under development than an accepted measurement of anything useful. Besides, Bill Andrews, a telomerase specialist who prepared the gene therapy for Parrish’s 2015 experiment in Colombia and who has been instrumental in BioViva’s work, tells me that even he couldn’t support the results she had claimed after receiving the gene therapy. He believes Parrish probably took only a thousandth of an effective dose. Nor is there any reliable evidence of Parrish’s purported 20-year reduction in biological age. The 2016 press release detailing her treatment says that the results were independently verified. But both the organizations that undertook this—a UK charity called the Biogerontology Research Foundation and the Healthy Life Extension Society, a European nonprofit—have links to Parrish. That press release was written by BioViva’s chief technology officer, Avi Roy—who was serving as president of the Biogerontology Research Foundation at the time. Parrish has also served on the board of the International Longevity Alliance, an umbrella organization that counts the Healthy Life Extension Society as a member. To date, the results of Parrish’s experiment, and the procedure carried out on MJ and her covolunteers, have never truly been independently verified. It's easy to get swept up in the idea that aging might be curable. And it’s no surprise that longevity medicine is also a profitable hunting ground for quacks. “Some really do think that they’re offering meaningful interventions,” says Turner. “Where this starts to get problematic is when they’re driven entirely by enthusiasm.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Parrish—who often describes her interest in aging medicine as humanitarian—has no medical qualifications. Yet she is unapologetic about her gung-ho attitude to medicine. “I believe I’m on the right side of history,” she says. “The truth is, to treat very serious diseases, we are going to have to take risks. What I would say is: Was anyone hurt? I seriously doubt it.” If you can convince people that aging is a disease, it’s no surprise that some will clamor for a cure—and pay whatever they can for it. This, if anything, ought to underline exactly why medicine carried out under stringent regulations really is the best choice. “We need to protect patient populations,” says Brenner. For now, the medical establishment has little to offer those who are diagnosed with age-related diseases such as dementia. And warranted skepticism toward last-ditch efforts to cure them can come off like cynicism. MJ has no regrets about participating in the experiment in Tijuana. “I think somebody has got to go out there and try these things and see if they actually work,” she tells me. “By the time we got home, I really did feel sharper. Now I’m fading, and I can tell I’m fading. I wanna go back for another shot. I’m ready.” This story is partially adapted from Buying Time: Exposing the Quest to Cure Ageing, a six-part series about BioViva and its founder Liz Parrish. It was produced by Vespucci. Listen now on Audible. Read next Read next Your Ovaries Hold a Secret You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Topics Live Forever longevity medicine health genetics diseases drugs bioethics Ramin Skibba Ramin Skibba Emily Mullin Rhett Allain Matt Simon Emily Mullin Matt Reynolds Rob Reddick Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"An AI Hedge Fund Created a New Currency to Make Wall Street Work Like Open Source | WIRED"

"https://www.wired.com/2017/02/ai-hedge-fund-created-new-currency-make-wall-street-work-like-open-source"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Cade Metz Business An AI Hedge Fund Created a New Currency to Make Wall Street Work Like Open Source Numerai Save this story Save Save this story Save Wall Street is a competition, a Darwinian battle for the almighty dollar. Gordon Gekko said that greed is good, that it captures " the essence of the evolutionary spirit. " A hedge fund hunts for an edge and then maniacally guards it, locking down its trading data and barring its traders from joining the company next door. The big bucks lie in finding market inefficiencies no one else can, succeeding at the expense of others. But Richard Craib wants to change that. He wants to transform Wall Street from a cutthroat competition into a harmonious collaboration. This morning, the 29-year-old South African technologist and his unorthodox hedge fund, Numerai , started issuing a new digital currency—kind of. Craib's idea is so weird, so unlike anything else that has preceded it, that naming it becomes an exercise in approximation. Inspired by the same tech that underpins bitcoin, his creation joins a growing wave of what people in the world of crypto-finance call "digital tokens," internet-based assets that enable the crowdsourcing of everything from venture capital to computing power. Craib hopes his particular token can turn Wall Street into a place where everyone's on the same team. It's a strange, complicated, and potentially powerful creation that builds on an already audacious arrangement, a new configuration of technology and money that calls into question the market's most cherished premise. Greed is still good, but it's better when people are working together. Based in San Francisco, Numerai is a hedge fund in which an artificially intelligent system chooses all the trades. But it's not a system Craib built alone. Instead, several thousand anonymous data scientists compete to create the best trading algorithms---and win bitcoin for their efforts. The whole concept may sound like a bad Silicon Valley joke. But Numerai has been making trades in this way for more than a year, and Craib says it's making money. It's also attracted marquee backers like Howard Morgan, a founder of Renaissance Technologies, the wildly successful hedge fund that pioneered an earlier iteration of tech-powered trading. Richard Craib Numerai The system is elegant in its way: Numerai encrypts its trading data before sharing it with the data scientists to prevent them from mimicking the fund's trades themselves. At the same time, the company carefully organizes this encrypted data in a way that allows the data scientists to build models that are potentially able to make better trades. The crowdsourced approach seems to be working—to a point. But in Craib's eyes, the system still suffers from a major drawback: If the best scientist wins, that scientist has little incentive to get other talented colleagues involved. The wisdom of the crowd runs up against Wall Street's core ethos of self-interest: make the most money for yourself. That's where Craib's new token comes in. Craib and company believe Numerai can become even more successful if it can align the incentives of everyone involved. They hope its new kind of currency, Numeraire, will turn its online competition into a collaboration—and turn Wall Street on its head in the process. In its first incarnation, Numerai was flawed in a notable way. The company doled out bitcoin based on models that performed successfully on the encrypted test data before the fund ever tested them on the live market. That setup encouraged the scientists to game the system, to look out for themselves rather that the fund as a whole. "It judged based on what happened in the past, not on what will happen in the future," says Fred Ehrsam, co-founder of marquee bitcoin company Coinbase and a Wall Street veteran. But Craib feels the system was flawed in another way—the same way all of Wall Street is flawed. The data scientists were still in competition. They were fighting each other rather than fighting for the same goal. It was in their best interest to keep the winnings to themselves. If they spread the word, the added competition could cut into their winnings. Though the scientists were helping to build one master AI, they were still at odds. The fund and its creators were at cross-purposes. 'Why is tech positive-sum and finance zero-sum?' Richard Craib Today, to fix that problem, Numerai has distributed Numeraire—1,000,000 tokens in all—to 12,000 participating scientists. The higher the scientists sit on the leaderboard , the more Numeraire they receive. But it's not really a currency they can use to pay for stuff. It's a way of betting that their machine learning models will do well on the live market. If their trades succeed, they get their Numeraire back as well as a payment in bitcoin—a kind of dividend. If their trades go bust, the company destroys their Numeraire, and they don't get paid. The new system encourages the data scientists to build models that work on live trades, not just test data. The value of Numeraire also grows in proportion to the overall success of the hedge fund, because Numerai will pay out more bitcoin to data scientists betting Numeraire as the fund grows. "If Numerai were to pay out $1 million per month to people who staked Numeraire, then the value of Numeraire will be very high, because staking Numeraire will be the only way to earn that $1 million," Craib says. It's a tricky but ingenious logic: Everyone betting Numeraire has an incentive to get everyone else to build the best models possible, because the more the fund grows, the bigger the dividends for all. Everyone involved has the incentive to recruit yet more talent—a structure that rewards collaboration. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg What's more, though Numeraire has no stated value in itself, it will surely trade on secondary markets. The most likely buyers will be successful data scientists seeking to increase their caches so they can place bigger bets in search of more bitcoin rewards. But even those who don't bet will see the value of their Numeraire grow if the fund succeeds and secondary demand increases. As it trades, Numeraire becomes something kind of like a stock and kind of like its own currency. For Craib, a trained mathematician with an enormous wave of curly hair topping his 6-foot-4-inch frame, the hope is that Numeraire will encourage Wall Street to operate more like an open source software project. In software, when everyone shares with everyone else, all benefit from the collaboration: The software gets better. Google open sourced its artificial intelligence engine , for instance, because improvements made by others outside the company will make the system more valuable for Google, too. "Why is tech positive-sum and finance zero-sum?" Craib asks. "The tech companies benefit from network effects where people behave differently because they are trying to build a network, rather than trying to compete." Craib and company built their new token atop Ethereum, a vast online ledger—a blockchain —where anyone can build a bitcoin-like token driven by a self-operating software program, or "smart contract." If it catches on the way bitcoin has, everyone involved has the incentive to (loudly) promote this new project and (manically) push it forward in new ways. 7,500 Faceless Coders Paid in Bitcoin Built a Hedge Fund’s Brain Bitcoin Will Never Be a Currency—It’s Something Way Weirder AI and Bitcoin Are Driving the Next Big Hedge Fund Wave But getting things right isn't easy. "The risk is that the crypto-economic model is wrong," says Ersham, "Tokens let you set up incentive structures and program them directly. But just like monetary policy at, say, the Federal Reserve, it's not always easy to get those incentive structures right." In other words, Craib's game theory might not work. People and economies may not behave like he assumes they will. Also, blockchains aren't hack-proof. A bug brought down the DAO, a huge effort to crowdsource venture capital on a blockchain. Hackers found a hole in the system and made off with $50 million. Craib may also be overthinking the situation, looking for complex technological solutions to solve a problem that doesn't require anything as elaborate as Numeraire. "Their model seems overly complicated. It's not clear why they need it," says Michael Wellman, a University of Michigan professor who specializes in game theory and new financial services. "It's not like digital currency has magical properties." Numerai could try a much more time-honored approach to recruiting the most talented data scientists, Wellman says: pay them. After today, Craib and the rest of Wall Street will start to see whether something like Numeraire can truly imbue the most ruthless of markets with a cooperative spirit. Those thousands of data scientists didn't know Numeraire was coming, but if the network effects play out like Craib hopes they will, many of those scientists have just gotten very, very rich. Still, that isn't his main purpose. Craib's goals are bigger than just building a hedge fund with crowdsourced AI. He wants to change the very nature of Wall Street—and maybe capitalism. Competition has made a lot of people wealthy. Maybe collaboration could enrich many more. Senior Writer X Topics artificial intelligence bitcoin Blockchain Crowdsourcing data Enterprise Kari McMahon Joel Khalili Will Knight Amit Katwala Andy Greenberg Andy Greenberg Joel Khalili Khari Johnson Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"The Fierce Battle for the Soul of Bitcoin | WIRED"

"https://www.wired.com/2014/03/what-is-bitcoin"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Robert McMillan Business The Fierce Battle for the Soul of Bitcoin Save this story Save Save this story Save Adam Voorhes Gail Anderson + Joe Newton Before most people had ever heard of the digital currency bitcoin, Brian Armstrong, a 27-year-old engineer at the home-sharing website Airbnb, thought it could make him a lot of money. At the time—spring 2012—Airbnb was moving a reported $500 million in payments annually in 192 countries through a patchwork of financial networks, and each one claimed a transaction fee. An anonymous, encrypted, government-free online version of money would simplify all that. It would be faster, more secure, and vastly cheaper. The problem was that the things that made bitcoin attractive also made it bewildering for noncoders. Using it required balky and hard-to-use software called a wallet. Bitcoins were also a challenge to obtain—mostly you had to purchase them from middlemen who operated in the regulatory shadows and who sometimes turned out to be crooks. The money was hard to spend, because few merchants accepted it—the currency was just too new. Armstrong realized that the way to widespread acceptance of bitcoin was a user-friendly wallet. He wasn't the only one thinking about bitcoin's broader potential. On a discussion forum about the currency, Armstrong met Ben Reeves, a British programmer who ran a bitcoin transaction-tracking website called Blockchain. Reeves understood the technology and was well respected within its tight-knit community of enthusiasts. He had been using bitcoin for a year already and had even built a bitcoin wallet that 10,000 people had tried out. Reeves also wanted to see the currency gain more traction. The two men hit it off and started spitballing ideas for a new kind of company: a PayPal for bitcoin. It would serve as a trusted broker of the cryptocurrency, taking a 0.5 percent charge anytime anyone converted dollars to bitcoins or vice versa. But spending money within the bitcoin network would be essentially free. With a digital wallet and payment-processing services, you could, say, pay that cash-only cab driver with bitcoins via your smartphone. They pitched the concept to the prestigious and highly selective tech-company incubator Y Combinator—and within hours had an invitation to join the class of summer 2012. But the relationship soon ran into trouble. Armstrong felt that in order for bitcoin to gain mass acceptance, users who lost their wallet passwords would need a way of recovering them. That meant their new company would have to retain access to users' private keys—the 64-character access codes that convey bitcoin ownership. Without that access, users could forever forfeit their entire bitcoin fortune as easily as forgetting their password. Reeves disagreed completely. The whole point of bitcoin was that it put the person with the bitcoins in control. If you gave some company access to your bitcoins, you were essentially trusting it as you would a bank. It could lose them to hackers or, worse, steal them outright. These rip-offs were already an all-too-common occurrence in the nascent bitcoin world. If Reeves and Armstrong's company maintained a backdoor into all of its customers' wallets, it would be only a matter of time before the government began issuing subpoenas. Yes, the current system meant that users took on more risk, and that would probably turn off some of the more casual ones. But bitcoin wasn't meant for them anyway. Though Reeves planned to build a currency for everyone, he wanted to start with the geeks. "There simply are not that many reasons why the average person would want to use bitcoin," he wrote. The hammer fell just 48 hours before Reeves was supposed to get on a plane to fly to Silicon Valley. Armstrong's email was diplomatic, even kind. Still, like all breakups, it hurt. "Cofounding is really like a marriage," Armstrong wrote, "and even though I think we have mutual respect for each other, we don't work together extremely well." Armstrong cut Reeves off from their shared online accounts. "I think we have pretty different aesthetics around what sort of product to build," Armstrong wrote. He was going to Y Combinator alone. Reeves was out. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg A Flash Guide to BitcoinThe digital currency may have begun as an experiment for techno-libertarians and geeks, but today it’s growing into something much bigger. Still, that doesn’t make it any less complicated than when it was first introduced on a cryptography listserv in 2008. Here’s how bitcoin actually works. —Cameron Bird Click to enlarge. Lamosca 1. Puzzle Each bitcoin is represented by a string of numbers and letters. To verify that every transaction is legit, a worldwide network of computers constantly checks these cryptographic signatures. 2. Solve Those computers are also locked in a contest to solve cryptographic puzzles. This is called mining. Many partici­pants join mining pools to combine their computational power for faster solving. 3. Mint The winner gets a block of 25 new bitcoins. Over time, that bounty is set to decrease in size, limiting the total number of bitcoins in circulation. As more computers join the network, the puzzles get more difficult. 4. Verify Miners serve a vital role: They add bitcoin transactions onto a public ledger called a block­chain. This database allows anyone to follow bitcoins from transaction to transaction. 5. Exchange Once mined, new bitcoins go into circulation. People can buy them through online services like Coinbase or directly from another user. (In a few North American cities, bitcoin ATMs dispense them.) 6. Hold Once acquired, btcoins must be stored. Some users keep their cryptocurrency in digital wallets on their computers or smartphones with apps like Bitcoin-Qt and MultiBit. Others store them in the cloud, relying on services like Coinbase. 7. Shop The number of individuals and businesses accepting bitcoins is exploding. Today they can be spent everywhere from independent restaurants and hotels to major retailers like Overstock.com. 8. Repeat Once a transaction has occurred, other computers on the network then validate and record it on the official bitcoin ledger—the blockchain. The network groups several transactions together and assebles a new cryptographic puzzle. Miners then begin attacking the new problems, which for now are designed to be solved in about 10 minutes. Today the conceptual conflict between Armstrong and Reeves is playing out across the volatile and vibrant fledgling bitcoin economy. Once the domain of hackers, libertarian activists, and drug dealers, bitcoin has been adopted by a growing number of mainstream businesses. You can use it to buy a mattress on Overstock.com or a laptop from electronics seller TigerDirect; Zynga will soon begin accepting it for in-game payments. Last year more than $100 million in bitcoin transactions was processed and the value of bitcoins shot up from $13 to $1,200, despite the fact that regulators in China were cracking down. Even when one of the world's best-known bitcoin businesses, a Japanese exchange called Mt. Gox, closed after being hacked—customers lost currency worth hundreds of millions of dollars—new exchanges launched, the value climbed back up, and the mainstreaming of bitcoin rolled on. Regulators are taking a hard look at the bitcoin economy, but investors and entrepreneurs keep coming. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg All this activity obscures a fundamental rift over what bitcoin should become. Many of the currency's original proponents—call them crypto-libertarians—see it as a step toward an entirely new economy, one that can't be influenced by an overweening federal government or rapacious financial industry. Bitcoins aren't created or controlled by a central organizing body like the Federal Reserve. They're created—or mined, in bitcoin parlance—by a global network of computers and governed by the cold rationality of mathematics and the laws of supply and demand. Bitcoin's algorithms dictate that no more than 21 million bitcoins will ever be created; the math even determines how quickly new bitcoins get added—25 every 10 minutes. (That number drops by half every four years.) And crucially, from the crypto-libertarians' point of view, the currency straddles the line between transparency and privacy. All transactions happen out in the open, recorded on bitcoin's public ledger. But because bitcoin isn't necessarily tied to any user's identity, it can be spent anonymously like cash, meaning there's a way to keep governments and marketers in the dark about your spending habits. Meanwhile, some of the new entrants to the bitcoin universe—venture capitalists and entrepreneurs—have a much different vision. They see bitcoin as something more practical: a hyperefficient online transaction system like Visa, but cheaper, faster, and more flexible. It would usher in a world in which we don't have to trust online vendors to safeguard our credit card numbers, in which merchants don't have to pay exorbitant handling fees, and in which payments as small as fractions of a cent could unleash a kind of long tail of commerce, making it just as easy and profitable for an Argentine vintner to accept money from a wine connoisseur in Dubai as it is for Amazon to sell diapers in Dubuque. This doesn't have to be a zero-sum game, but increasingly it looks as though the two visions of bitcoin are in conflict. With every Mt. Gox–style flameout, consumers and governments press for a more regulated system, even though some regulations threaten to push bitcoin into the deep jungle of international finance. Last year banking regulators shut down a US bitcoin exchange called TradeHill. Today the most popular bitcoin exchanges operate outside the US, in Slovenia, Bulgaria, and Japan. VCs are used to this dynamic—taking a technology nurtured by true believers and massaging it into a broadly acceptable business. But in this instance, they're up against something new. Thanks to bitcoin's skyrocketing value, some of its original proponents find themselves sitting atop massive war chests, and they are willing to spend their newly valuable cryptocurrency to realize their vision of the future. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Adam Voorhes Gail Anderson + Joe Newton On March 5 of last year, Wences Casares, CEO of the online-payment company Lemon, was eating lunch at the Dove Mountain Ritz-Carlton, a lavish golf retreat north of Tucson, Arizona. He was hobnobbing with other tech executives, VCs, and entrepreneurs at an invitation-only conference sponsored by boutique investment bank Allen & Company. Casares grew up on a sheep ranch in Patagonia, but he'd made a career building online banks and payment systems in Europe and Latin America. Over the previous year, bitcoin had become something of an obsession for Casares. He thought it would change finance, especially in developing countries, and he wanted to show it to anyone who would pay attention. At Dove Mountain, Casares decided to play a little parlor trick. He'd show the high-powered tech guys at the table how easily bitcoin could move a crapload of money. He had each of his tablemates download a bitcoin wallet to their phone. Then he generated a QR code on his own phone's screen and had the person seated nearest to him take a picture of it. When that person checked their wallet, they had 6,390 bitcoins—worth $250,000. What followed was perhaps the world's most high-stakes game of hot potato. From seat to seat, the capitalists squirted 250 grand at each other with nothing more than a button push or screen tap. Once the money was safely transmitted back to Casares' wallet, everyone at the table had gotten a taste of how cool and dead-simple bitcoin could be. This wasn't like PayPal, say, which merely lubricates some of the friction between banks and credit card companies. This was money set free. Bitcoin's JourneyThough it first appeared in 2009, bitcoin didn’t see much action until 2012, when more than 1,000 new merchants began accepting the digital currency. Since then the number of bitcoin transactions has climbed steadily. Its value has risen precipitously too—and fallen in a volatile series of boom-and-bust cycles. —C.B. Click to enlarge. Lamosca "It was quite a demo," says Chris Dixon, a serial entrepreneur who is now a partner at Andreessen Horowitz, the venture capital firm best known for its investments in Facebook and Twitter. As a fee-free transaction system, Dixon saw, bitcoin could be an ecommerce alternative for businesses small and large. And because bitcoin was an open platform like the Internet, software developers were free to build things on top of it that they never could with MasterCard or Visa, which carefully control access to their networks. Here was a way to make mobile payments without giving Apple's or Google's app stores a 30 percent cut; here was a way for a college student to write a micropayment app to fund a school newspaper. "The original spec of HTTP was going to have a payment system built into it, but they never got to it," Dixon says. He thought bitcoin might be it. Eight months after the demo in Tucson, Dixon invested $25 million of Andreessen Horowitz's money in Armstrong's startup, Coinbase. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Just as companies like Facebook and Blogger had made it easy for anyone to set up their own online presence, the bitcoin economy needed a middleman to make it easier for everyone to participate. But writing the Internet's payment protocol was a risky proposition. People had tried to build digital currencies, and the results were always the same: Criminals flocked to them, and the government ended up shutting them down. If bitcoin were to succeed, Dixon reasoned, state and federal governments would have to establish a road map. And bitcoin companies would need to show that they were willing and able to follow the rules by putting the kind of strict controls on their businesses that would keep out criminals and money launderers. Coinbase hopes to do just that. Today it occupies a 1,800-square-foot apartment in San Francisco's South of Market neighborhood. It's not a particularly impressive setting for a company attempting to build the future of money. A string of white Christmas lights trails up to the apartment's loft, a concession to the holiday season that's just winding down. "For a long time, Coinbase was essentially two desks upstairs," Armstrong says. "Now we're looking at a 25,000-square-foot office space." Then again, it makes sense that the company might underinvest in real estate. Coinbase is involved in a pricey proposition: obtaining the state licenses and filing the reports necessary to be an official money transmitter. Making bitcoin easy to use, it turns out, isn't so much a technological problem as a regulatory one. When Coinbase started, the most difficult problem for new bitcoin users was buying and selling bitcoins. Coinbase made this easy. You link your bank account to Coinbase and—presto!—you've got bitcoins. But this complicated things for Coinbase. It turned the company into a money-services business, like Western Union. And just like Western Union, if it runs afoul of regulators, they can seize its bank accounts and put it out of business. (As long as the company is in the process of obtaining the proper permits, regulators will not clamp down.) Adam Voorhes Gail Anderson + Joe Newton As part of operating an aboveboard money-services firm, Coinbase actively polices its users. It vets customers to make sure they're not criminals or money launderers, has access to their private keys, and helps startups develop apps to run on the Coinbase platform. Oh, and Coinbase takes a 1 percent fee when people use its system to convert bitcoins to cash and vice versa. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg As less-technically-savvy users flood into the bitcoin marketplace, that fee can seem like a bargain. Simplicity, consistency, legality, and reliability are worth money. Just ask the millions of people who prefer to download TV shows from iTunes than to take their chances with BitTorrent. A year ago, when Casares was passing around bitcoins at the Arizona retreat, about 37,000 people had Coinbase wallets. Today that number is more than 1 million. Armstrong sees a future in a whole range of services—integrating the Coinbase wallet with cash registers so you can buy milk with bitcoins at your local grocery store, for example. "It's a new protocol; it's difficult to use, but it has incredible potential," he says. "There's an opportunity to build the first trusted brand on this new protocol and help make it easy for businesses and consumers to use it." If the anarchic id of bitcoin has an analogue to the straitlaced Chris Dixon, it's Roger Ver. Sometimes called Bitcoin Jesus for the way people mob him after his lectures, Ver is a businessman and onetime Libertarian candidate for the California State Assembly. He left his home state for Japan in 2006 after a 10-month stint in Lompoc federal prison for selling a high-powered firecracker called the Pest Control Report 2000 on eBay. But Ver is perhaps best known for a billboard. He pays $1,500 a month for it, a giant sign in Silicon Valley that advertises his aftermarket computer parts business. (Its tagline, naturally: "We accept bitcoin.") Ver started buying the currency in 2011, when it traded at $1, and scooped up enough of it to ride its climb in value to a seven-digit bank account. Now he's an early-stage investor in a dozen bitcoin companies. But unlike Dixon, the startups he's funding aren't necessarily trying to make bitcoin a respected and efficient aboveboard transaction system. They're trying to develop the currency's revolutionary potential. One of these startups is Blockchain, the brainchild of Ben Reeves. After getting Armstrong's breakup email, Reeves resolved to build Blockchain into more than just a data-gathering site. Like Armstrong, he saw the bitcoin wallet as a platform for financial services. But Reeves didn't want Blockchain to have access to its customers' bitcoins. So he hacked an ingenious wallet that can be accessed from a browser or a mobile phone but leaves the critical private key on the user's computer. Blockchain can never lose your bitcoins. However, if you forget your password, it can't find them for you either. None of the Valley's investors wanted anything to do with Reeves. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg BITCOIN STRADDLES THE LINE BETWEEN TRANSPARENCY AND PRIVACY. ALL TRANSACTIONS ARE OUT IN THE OPEN BUT ANONYMOUS. And then he got an email from Ver. Blockchain was a great site, Ver wrote. Did Reeves need any help? The answer, of course, was yes. Ver invested some money—he won't say how much—and with it Blockchain added servers and improved its software. Today it's one of the most reliable sources of information on bitcoin, and Reeves is slowly turning it into a kind of Google for the bitcoin ecosystem—a set of web services that are crucial for bitcoin traders and developers. The success of the company's Blockchain.info website has led people in turn to download Blockchain's wallet software. Today more than 1.3 million customers use it. They can check the latest bitcoin prices, log in to their wallet, and use bitcoins to buy, say, an Amazon gift card. The company's 16 employees are developing a trading platform that will be able to search out the best deals on various bitcoin exchanges, and they're building out a mobile news app called ZeroBlock. The company makes several hundred thousand dollars a month from ads, billed in bitcoin. It has no office and no bank account. "It's a liberating and flexible thing for us," says Nic Cary, Blockchain's CEO. "We don't need a bank." Reeves was on his way to building a wallet that was controlled 100 percent by the individual user and out of the hands of corporations and governments. You get to do whatever you want with it, and if you lose your private key, that's your problem—rugged individualism, rendered as bits. It was an idea that appealed to libertarians like Ver, who once wrote that "nearly everything the government does makes the world a poorer place." So what might a government-free bitcoin world look like? It could resemble Acapulco's Playa Condesa. One-horse carriages festooned with blue and white balloons and flashing LEDs promenade up and down the busy street as drunken revelers avail themselves of a 100-foot bungee jump. Jeff Berwick, an anarchist millionaire, is drinking Don Julio at Paradise, an outdoor disco, and living tax-free. Berwick made his first fortune as the founder of the finance news site Stockhouse. His second fortune came from bitcoin. Right now he's trying to persuade me to go out for one more drink. "I know a place where they have midgets on roller skates," he says. When Berwick isn't partying, he and a group of like-minded people are trying to set up a free-trade zone in Honduras; they believe that president Juan Orlando Hernández will approve the deal any day. "There's already a bunch of bitcoin guys getting ready to move down there as soon as the free zone is set up. They want to do a lot of bitcoin-related businesses, partly because there is not going to be any real regulatory thing," Berwick says. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg BLOCKCHAIN CAN NEVER LOSE YOUR BITCOINS. BUT THE WALLET-BUILDER CAN'T FIND THEM FOR YOU, EITHER, IF YOU FORGET YOUR PASSWORD. For about 45 bitcoins, Berwick will sell you a Paraguayan passport so you can live tax-free as a bitcoin anarchist in Acapulco. He will broker real estate deals for you there too. In fact, he is just about to close a sale on a 30th-floor penthouse with a killer view of the city. A month earlier, a German businessman living in China snatched it up for a 17-bitcoin down payment—he won't let me use his name, but via email he tells me that with China's strict monetary controls, it was the easiest way for him to get money out of the country. American tourists largely avoid Acapulco, in part because of its reputation for drug-cartel violence. But Berwick says he feels safer here than in the US (possibly because he has a bodyguard). "I've fallen off my scooter drunk here. The cops just picked me up and helped me on my way," he says. He can also sell real estate without a license. That's not to say that crypto-libertarian purists are above engaging with officialdom when necessary. In 2012, Ver and Mark Karpeles, then CEO of Mt. Gox, ponied up 5,000 bitcoins each to kick-start the Bitcoin Foundation. It was a decent endowment at the time, worth maybe $55,000. But as bitcoin's value has mushroomed, the Bitcoin Foundation has become a well-funded lobbying organization worth millions. In August 2013, as federal investigators probed bitcoin's connections to the Silk Road—a free-for-all drug bazaar fueled by anonymous bitcoin transactions—the foundation held a series of meetings with staffers at the US Justice and Treasury departments and the FBI. The months-long lobbying effort culminated in a pair of bitcoin-friendly congressional hearings that The Washington Post described as "lovefests." The Bitcoin Foundation called it a win—and so did venture capitalists. The new bitcoin millionaires are a weird breed: government-hating libertarians rich enough to hack the systems that make Washington, DC, function. In that town they even began to sound a little like VCs themselves. "Setting regulatory certainty is very important for bitcoin," Ver says. "I'm opposed to the regulations, but the bitcoin businesses need to know the rules of the game in order to move ahead." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Neither venture capitalists nor crypto-libertarians will win the fight for bitcoin's soul if the currency's fledgling system implodes. And it could. Companies in the emerging legitimate bitcoin industry—wallet builders, exchanges, payment-processing services—can't get banking services because bankers still have no clear idea how regulations apply to these companies. On top of that, the bitcoin network itself is struggling to deal with its own rapid growth. It can process only seven transactions per second (Visa can handle 10,000). But some clarity may be coming. This year the superintendent of the New York State Department of Financial Services, Benjamin Lawsky, expects to spell out a set of guidelines for plugging bitcoin companies into the financial system. These rules are likely to influence states across the US. If they're too stringent, bitcoin companies will probably close their doors or set up business offshore. This is the risk that playing nice with regulators presents: They might regulate you out of existence. Meanwhile, Mt. Gox represents the risk of the Wild West approach: Without safeguards, a centralized authority, or some way to protect people's digital holdings, the whole thing may be seen as fundamentally unstable and collapse on itself. Coinbase, meanwhile, is forging ahead like it's building the next billion-dollar Silicon Valley company. It has tripled its staff in the past six months, hiring a star compliance officer, Martine Niejadlik. Her job is to sort through all the rules an official financial-transactions business has to follow—and whatever new ones Lawsky comes up with. Its VCs, Andreessen Horowitz, have extended their commitment, investing $50 million in bitcoin businesses. Other than Christmas lights, Armstrong's team hasn't had time to install much in the way of office decorations. But on one wall hangs an 8- by 10-inch picture frame filled with Zimbabwean dollar bills—a currency that went through a period of hyperinflation in the late 2000s. Today most transactions in Zimbabwe are conducted in US dollars or South African rands. Nailed to an office wall, it looks like a shrine to failed currency. I ask Armstrong if I can take a picture of it, and he tells me no. Nobody wants bitcoin linked with funny money. Senior Writer X Topics Enterprise magazine-22.04 magazine-april-2014 Andy Greenberg Kari McMahon Joel Khalili Brandi Collins-Dexter Will Knight Peter Guest Steven Levy Reece Rogers Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Signal Has a Fix for Apps' Contact-Leaking Problem | WIRED"

"https://www.wired.com/story/signal-contact-lists-private-secure-enclave"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Andy Greenberg Security Signal Has a Fix for Apps' Contact-Leaking Problem Getty Images Save this story Save Save this story Save The encrypted-communication app Signal has a sterling reputation within the security and crypto community, but its critics point to a nagging flaw: The app asks for access to your phone's contact list when you install it. Signal's creators, like the developers of so many other social apps, consider that contact-sharing request a necessary evil, designed to make the app as easy to use as your normal calling and texting features. But it's one that some of Signal's most sensitive users resent as a breach of its privacy promises. Now Open Whisper Systems, the non-profit behind Signal, is launching an experimental new method to sew up that gap in its data protections, while still letting you flip through your existing address book to make encrypted calls and send encrypted texts. And the way they did it could serve as a model for other apps wrestling with the same address book privacy problem. Using a feature in the latest generation of Intel processors, the group plans to announce Tuesday that it's testing a method that lets its servers mine your address book to find other Signal users, while provably deleting all the contact data those servers see without recording it. That means, in theory, no hacker, government agency, or even Signal developers themselves can access that sensitive data. "When you install many apps today you get this little prompt that asks if you want to give someone access to your contacts. You get an uncomfortable feeling in that moment," says Moxie Marlinspike, the founder of Open Whisper Systems and Signal's creator. "This is an experiment in letting you not have that uncomfortable feeling." That new experimental protection for your Signal contacts, which Open Whisper Systems is testing now and hopes to roll out to users over the next few months, takes advantage of an Intel processor feature called Software Guard Extensions, or SGX. Intel chips that integrate that SGX component have a "secure enclave" in the processor, designed to run code that the rest of the computer's operating system can't alter. Any code running in that enclave is signed with a unique key that Intel, not the computer's owner, controls. And a computer that connects to that machine running SGX can check its signature to make sure that the code in the enclave hasn't changed, even if the rest of the computer is infected with malware, seized by the FBI, reprogrammed by its owners to sell out all its users' data, or otherwise compromised. Much of the attention to SGX has focused on how it can enable practically unbreakable "digital rights management" anti-piracy measures: If it's installed on your PC, it could prevent you from fully controlling the code of the videos or games you play on it, making it far harder to crack those files' copy protections. But Open Whisper Systems is now turning SGX's trust relationships around, and running it instead on Signal's servers. As a result, Signal users will be able to check that those servers are behaving in a way that even its administrators, or an outside party who compromises the servers, can't change. 'This is an experiment in letting you not have that uncomfortable feeling.' Signal Creator Moxie Marlinspike When you share your contacts with Signal, those servers check your address book against all known Signal users to assemble a list of known Signal-using contacts in the app. Now, that process will be performed within the Signal server's secure enclave. Every phone with Signal installed will in theory be able to check that Signal's open-source server code, which is designed to immediately erase that address book info after processing it, hasn't been changed to somehow store the data instead. By running the contact lookup process in that SGX-enabled enclave, "we're hiding the contacts from ourselves," says Marlinspike, "in the sense that the code is unalterable, and it’s written in an unalterable way where it doesn’t reveal the contacts to anything else outside that enclave." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg That server-side use of SGX is still relatively untested, and the notion that the administrators of a server could prevent even themselves from undetectably fiddling with code in the secure enclave of a computer they physically control isn't entirely proven, says Rafael Pass, a cryptography-focused professor of computer science at Cornell Tech who presented a paper on server-side SGX implementations for privacy at the Eurocrypt conference earlier this year. "They could potentially break their own SGX enclave. It’s not well understood how expensive that is," says Pass. "In principle it seems like a viable design. It makes it better, but it’s not clear how much better." But Marlinspike argues that the new security measure will at least make it vastly harder for Signal to somehow sabotage its own privacy protections. In the past, the app has obscured users' contacts by taking a cryptographic "hash" of them, converting them into a unique string of characters that can't be deciphered to reveal the original information. But that hashing process alone was relatively easy to crack, since someone could simply hash all possible phone numbers and match them to the hashes Signal collects. Now Signal users will have the extra assurance that Signal's servers aren't collecting—and in fact, can't—those hashes in any permanent way, short of finding some new method of breaking into Intel's SGX protections. But Signal's SGX implementation remains just a test, and it will require real scrutiny to ensure it truly hides all parts of a user's contact list in its secure enclave and allows that code to be publicly verified in a meaningful way. If it checks out, though, Signal's use of SGX might offer a new alternative for social apps that seek to thread the needle of convenience and security. If social software wants to offer a calling or messaging experience better than a 1980s-style touchtone telephone sans speed dial, it generally either uploads your phone's local contact list or stores its own list of your contacts on a server. Either option seriously impinges on the privacy of your personal social network. Signal's solution might offer a solid third option. "We want this to be something that’s accessible and generally deployable by everyone who has this problem, not just us," Marlinspike says. "We're trying to build something that will scale to more than a billion users." The result might someday be that the privacy protections Signal has helped to extend to the contents of those billions of users' communications could apply to the equally precious contents of their contact list, too. Senior Writer X Topics messaging encryption Signal privacy Andy Greenberg Lily Hay Newman Andrew Couts Andy Greenberg David Gilbert David Gilbert David Gilbert Justin Ling Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Rudy Giuliani Butt-Dialed a Reporter (Twice!) | WIRED"

"https://www.wired.com/story/rudy-giuliani-butt-dial-adobe-leak-un-phishing"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Brian Barrett Security Security News This Week: Rudy Giuliani Butt-Dialed a Reporter (Twice!) Photograph: GENT SHKULLAKU/Getty Images Save this story Save Save this story Save This week, Republicans stormed a sensitive compartmented information facility in a show of… something? Unclear. But they definitely created a national security issue by bringing their smartphones along with them and refusing to give them up. So, yes, that was the low point. But there were also highs! Microsoft has a new plan to protect firmware in Windows PCs from hacks, called “secured-core PCs.” A county in Georgia had a plan to use license plate detectors to reduce crime , but experts aren’t convinced it worked as advertised. And Russians have rapidly evolved their plans to execute so-called false flag hacks , making their attacks look like another sophisticated adversary pulled them off. Fancy Bear! They’re they mask-wearing Scooby-Doo villain of cyberwar. Elsewhere, we took a look at why two-factor authentication isn’t always the answer —even though it’s still essential in certain situations. We talked you through making your social media posts private when you want them to be. And we detailed how a fleet of click fraud apps snuck past Apple’s vaunted App Store defenses. We also explored technology’s role in the ongoing Hong Kong protests —on both sides—and ran through some quality password manager options. Lastly, set aside some time this weekend to read this in-depth profile of secretary of state Mike Pompeo , who finds himself at—or at least near—the center of the increasingly alarming Ukraine investigation. It’s a doozy. And there's more! Every Saturday we round up the security and privacy stories that we didn’t break or report on in-depth but which we think you should know about nonetheless. Click on the headlines to read them, and stay safe out there. Please go read this NBC News story. Truly, you won't regret it. Because it relates the tale of how Rudy Giuliani—lawyer to an embattled president, unlikely proprietor of a cybersecurity firm —managed to butt-dial NBC News reporter Rich Shapiro not once, but twice in the last several weeks. The substance of the three-minute voicemails Giuliani inadvertently left seems inconclusive, although the most recent does include Giuliani's extremely relatable lament that "the problem is we need some money." And sure butt-dialing is a universal experience. But for someone in the middle of, let's conservatively say, several legally dubious narratives to take so little care with his outgoing communications is quite something! Especially given that this seems to be at least a semi-regular occurrence: X content This content can also be viewed on the site it originates from. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Giuliani may be as divisive a character as exists in American politics today, but in the annals of butt-dialing, mark him down as a legend. The latest entrant in the never-ending parade of exposed data appears to be Adobe Creative Cloud. A security researcher discovered 7.5 million records sitting in an Elastisearch database that was easily accessible online. Adobe reportedly secured the database the same day it was discovered, October 19. No payment information leaked out, and there's no indication that it had been compromised by bad actors. But it still included details like email accounts, what Adobe products in use, member IDs, and when the account was created. Speaking of scourges, a phishing campaign has hit the Red Cross, UNICEF, the UN, and more. It's unclear who's behind the attack, but its goal appears to be breaking into Microsoft and Okta accounts. The scam set up a series of convincing fake websites, and would capture username and password data as entered in real-time. It's not unusual that these groups would be targeted, but the sophistication of the campaign is both impressive and worrying. Dimitrios Vastakis was the branch chief of White House computer network defense until he resigned earlier this month. And when he did, Axios reports, he left behind a resignation letter that called out just how irresponsible the White House's attitude toward cybersecurity has become. Experienced cybersecurity professionals are being forced out, the letter says, which ultimately makes White House cybersecurity less safe. That's especially concerning given the apparent lack of care given by President Donald Trump in the first place, and the prior elimination of important strategic cybersecurity roles. In other words, don't be surprised if a big White House hack happens—or if it already has. Pompeo was riding high— until the Ukraine mess exploded Maybe it’s not YouTube’s algorithm that radicalizes people The untold story of Olympic Destroyer, the most deceptive hack in history Massive, AI-powered robots are 3D-printing entire rockets USB-C has finally come into its own 👁 Prepare for the deepfake era of video ; plus, check out the latest news on AI 🏃🏽‍♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones. Executive Editor, News X Topics security roundup phishing data Lily Hay Newman Scott Gilbertson Lily Hay Newman David Gilbert Vittoria Elliott Matt Burgess David Gilbert Dell Cameron Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"I Made an Untraceable AR-15 'Ghost Gun' in My Office—and It Was Easy | WIRED"

"https://www.wired.com/2015/06/i-made-an-untraceable-ar-15-ghost-gun"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Andy Greenberg Security I Made an Untraceable AR-15 'Ghost Gun' in My Office—and It Was Easy Save this story Save Save this story Save This is my ghost gun. To quote the rifleman's creed, there are many like it, but this one is mine. It’s called a "ghost gun"—a term popularized by gun control advocates but increasingly adopted by gun lovers too—because it's an untraceable semiautomatic rifle with no serial number, existing beyond law enforcement's knowledge and control. And if I feel a strangely personal connection to this lethal, libertarian weapon, it's because I made it myself, in a back room of WIRED’s downtown San Francisco office on a cloudy afternoon. I did this mostly alone. I have virtually no technical understanding of firearms and a Cro-Magnon man’s mastery of power tools. Still, I made a fully metal, functional, and accurate AR-15. To be specific, I made the rifle's lower receiver; that's the body of the gun, the only part that US law defines and regulates as a "firearm." All I needed for my entirely legal DIY gunsmithing project was about six hours, a 12-year-old’s understanding of computer software, an $80 chunk of aluminum, and a nearly featureless black 1-cubic-foot desktop milling machine called the Ghost Gunner. The Ghost Gunner is a $1,500 computer-numerical-controlled (CNC) mill sold by Defense Distributed, the gun access advocacy group that gained notoriety in 2012 and 2013 when it began creating 3-D-printed gun parts and the Liberator, the world’s first fully 3-D-printed pistol. While the political controversy surrounding the notion of a lethal plastic weapon that anyone can download and print has waxed and waned , Defense Distributed's DIY gun-making has advanced from plastic to metal. Like other CNC mills, the Ghost Gunner uses a digital file to carve objects out of aluminum. With the first shipments of this sold-out machine starting this spring, the group intends to make it vastly easier for normal people to fabricate gun parts out of a material that's practically as strong as the stuff used in industrially manufactured weapons. The Ghost Gunner may signal a new era where the barrier to building an untraceable semiautomatic rifle is lower than ever before. In early May, I got a Ghost Gunner, the first of these rare CNC mills loaned to a media outlet, and I tried it out. I'm going to give away the ending: Aside from a single brief hardware hiccup, it worked remarkably well. In fact, the Ghost Gunner worked so well that it may signal a new era in the gun control debate, one where the barrier to legally building an untraceable, durable, and deadly semiautomatic rifle has reached an unprecedented low point in cost and skill. But the Ghost Gunner represents an evolution of amateur gun-making, not a revolution. Homebrew gunsmiths have been making ghost guns for years, machining lower receivers to legally assemble rifles that fall outside the scope of American firearms regulations. In fact, when we revealed the Ghost Gunner’s existence last year , the comments section of my story flooded with critics pointing out that anyone can do the same garage gunsmithing work with an old-fashioned drill press. I could hardly judge the fancy new CNC mill in WIRED’s office without trying that method too. Or for that matter, Defense Distributed’s previous trick, building gun parts with a 3-D printer. Before I realized exactly what I was getting into, I determined to try all three methods in a ghost-gun-making case study. I would build an untraceable AR-15 all three ways I’ve heard of: using the old-fashioned drill press method, a commercially available 3-D printer, and finally, Defense Distributed's new gun-making machine. All the components of my AR-15, including my homemade lower receiver, the gleaming aluminum piece. Josh Valcarcel/WIRED Almost no one builds a ghost gun from scratch, and I didn’t either. The shortest path to building an untraceable AR-15 requires only that you build one relatively simple component yourself, a part that’s become the focus of a fierce gun control controversy: the lower receiver. US gun regulations have focused on the lower receiver because it’s the essential core of a gun: It holds together the stock, the grip, the ammunition magazine, and the upper receiver, which includes the barrel and the chamber where the cartridge is detonated. As Doug Wicklund, senior curator at the NRA museum explained to me, the lower receiver always has carried the serial number because it's the part that remains when the others wear out and are replaced. Like the frame of a bicycle or the motherboard of a computer, it's the nucleus of the machine around which everything else is constructed. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg My AR-15's homemade lower receiver. Josh Valcarcel/WIRED It’s worth noting that buying an AR-15 in the US isn’t hard. But the privacy-minded—as well as those disqualified from gun purchases by criminal records or mental illness—can make their own lower receiver and purchase all of the other parts, which are subject to nearly zero regulation. I ordered every part of my AR-15 but the lower receiver from the website of Ares Armor , a Southern California gun seller that doesn’t require any personal information beyond a shipping address. If I wanted to hide my purchases from my credit card company, I could have paid in bitcoin—Ares accepts it. There's even a way to anonymously buy that highly regulated lower receiver—almost. Like many gun vendors, Ares sells what's known as an "80 percent lower," a chunk of aluminum legally deemed to be 80 percent of the way toward becoming a functional lower receiver. Because it lacks a few holes and a single precisely shaped cavity called the trigger well, it's not technically a regulated gun part. Buying or selling a ghost gun is illegal. Making one remains kosher under US gun control laws. Machining the last 20 percent myself with a CNC mill or drill press would allow me to obtain a gun without a serial number, without a background check, and without a waiting period. I wouldn’t even have to show anyone ID. Law enforcement would be entirely ignorant of my ghost gun’s existence. And that kind of secrecy appeals to Americans who consider their relationship with their firearms a highly personal affair that the government should keep out of. Controversy swelled around ghost guns when John Zawahri, an emotionally disturbed 23-year-old, used one to kill five people in Santa Monica in the summer of 2013. Even so, they haven't been outlawed; buying or selling a ghost gun is illegal, but making one remains kosher under US gun control laws. California state senator Kevin Deleon introduced a bill to ban ghost guns last year, following the Santa Monica mass shooting. Governor Jerry Brown vetoed it a few months later. But as the shouting match over ghost guns gets louder, few of the shouters have actually tried to make one. Even fewer have tried to test how the evolution of a new set of digital “maker” tools is changing that gun control question. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg So over the course of one strange week in WIRED’s office, that's what I set out to do. Here's how it all went down. The drill press, jigs and vise I used in my first attempt to finish an 80 percent lower receiver. Josh Valcarcel/WIRED Remember when I said I know nothing about using power tools? Unsurprisingly, this portion of my gunsmithing experiment didn't go well. Step one: Acquire a drill press, a massive stand-alone drill meant to cut the aluminum features out of my 80 percent-lower receiver. One $250 rental fee later, two colleagues helped me haul a drill nearly 6 feet tall down to our building's loading dock, a dark and chilly concrete space occupied by a pair of large Dumpsters. I'd paid Ares $97 for a set of steel-carbide drill bits and end mills—tools that act like bits but also can cut sideways like a milling machine—all of which the company recommended I use with the drill press to do the job. I paid another $110 for a set of steel jigs, metal stencils that would guide the machine as I tried to mill and drill precise shapes. As the drill bit chewed into the block, I tasted fine aluminum dust between my teeth. All that planning and spending, it turned out, couldn't compensate for my utter lack of even high-school-level shop skills. Before I'd even begun, I realized I had the wrong sort of vise, and we had to drive an hour and drop $80 to pick up another one. Then there was the drilling itself—which, it would turn out, is not as easy as it looks on the Internet. I reviewed my lower-receiver drilling basics on YouTube one last time, put on latex gloves and eye protection, screwed the steel jigs around my slug of aluminum, tightened the clamps, and hit the chunky green power button. As the drill bit chewed into the block, I felt a rush of excitement and tasted fine aluminum dust between my teeth. The bit threw off metal shavings and left behind a gleaming, polished crater. But my elation faded as I realized how badly I was mangling the trigger well. No matter how hard I cinched it down, the vise shuddered constantly, moving the aluminum piece. The holes I was cutting veered off until they were practically diagonal. When I switched to the end mill to clean up the spaces between the pits I'd created, I found they were mostly at different depths: The drill bit had somehow moved up and down, and I hadn't noticed. The bottom of the cavity I'd made began to resemble the surface of the moon. Meanwhile, the massive machine protested loudly, shaking like a train about to derail. Throughout this ordeal, WIRED video producer Patrick Farrell, a former bike mechanic who probably could have offered helpful advice, watched me struggle from behind his camera with a restrained smirk. The unwritten rule: I was in this alone. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg I kept at it for five and a half hours. Then the head of the drill press—the part that holds the bit, which I'd later learn is called the "chuck"—fell off. I had no idea whether this was supposed to happen as a kind of fail-safe, or if I had destroyed an expensive piece of equipment rented with Farrell’s credit card. I screwed the chuck back in, and after a few more minutes of metal-on-metal violence, it dropped off again. (I still don’t know if I damaged the drill press, but a gunsmith later explained to me that it likely wasn't designed to handle the lateral pressure of using it as a milling machine.) That's when I gave up. I had nothing to show for my labor but a sad metal block scarred by a maze of crooked channels. Well, that and a left hand bristling with tiny aluminum shards where my latex glove had split. A 3-D printed lower receiver on the print bed of a Makerbot Replicator. Josh Valcarcel/WIRED I left the grease-soaked drill press in WIRED's loading dock, headed back upstairs, and pulled a $2,800 Makerbot Replicator from its box. It felt like the elevator was a time machine shortcutting about a century of technological progress. I plugged in the 3-D printer, followed a series of delightfully idiotproof instructions, and in minutes was test-printing a tiny white coffee table. Soon I was ready to start making gun parts; no obscure YouTube instruction videos, calipers, jigs, or aluminum splinters required. I found the blueprint for a printable, reinforced AR-15 lower receiver on The Pirate Bay. It was one of dozens of gun parts available for download in the rogue BitTorrent repository's "physibles" section , a part of the site presciently created in 2012 to host controversial digital blueprints other sites wouldn't or couldn't. In fact, the file I downloaded had been created by Defense Distributed in 2013, but the group had pulled it from its own website after the State Department threatened to prosecute the group's staff for weapons-export-control violations. It took a few minutes to torrent the lower receiver file. I opened it in Makerbot's printing application, centered it on the app's digital representation of the machine's print bed, and clicked print. The printer’s motors began to whir, and within seconds its print head was laying out extruded white plastic in a flat structure that vaguely resembled the body of a semiautomatic rifle. As the workday ended and WIRED's office emptied, I found myself sitting alone in a darkening room, transfixed by the gun component slowly materializing before me. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg At one point, six hours into the nine-hour print job, the Replicator's print head overheated and took some time to cool down. That required pressing one more button on the machine. I didn't touch it again. The next morning I came back to the still-dark room and found a finished, eerily translucent lower receiver glowing inside the Replicator's LED-lit chamber. As science-fictional as that process felt, the results were flawed. When I pried the finished lower receiver off the print bed, one side was covered in support material meant to prevent the hot plastic structures from collapsing before they solidified. Snapping and scraping off that matrix of plastic was a long, messy process. I tried using a knife, cut my thumb, and bled all over one side of the rifle body. And the same support materials also filled tiny holes in the piece, in some cases choking the delicate threads meant to accept metal screws. It's clearly possible, based on YouTube evidence, to 3-D-print AR-15 lower receivers that are capable of firing hundreds of rounds. But mine wasn't so practical; I wouldn't know it until I visited a gunsmith two days later, but I'd eventually give up on assembling a gun out of that plastic-printed lower receiver long before it was anywhere close to a becoming a functional weapon. The Ghost Gunner, with an 80 percent lower receiver bolted inside. Josh Valcarcel/WIRED The new generation of “maker” tools like 3-D printers and CNC mills have been lauded as machines that allow anyone to make anything. But from my first moments using the Ghost Gunner, it was clear: This is a machine designed to make a gun. Defense Distributed’s CNC mill is a simple black cube, with two tiny stepper motors sticking out of two of its six sides. As if to underscore the power contained in its microwave-sized footprint, the machine was so heavy I could barely lift it from its box. When I did haul it onto a table, I was struck by the lack of branding or the toylike LED lights and buttons of the Replicator. Its stark simplicity mirrors the unmarked gun parts it's designed to create. Eventually, it felt much more like the Ghost Gunner had programmed me to be its gun-making tool than vice versa. The Ghost Gunner works with either of two pieces of software: GRBL, an open source, general-purpose milling application, and DDCut, a Windows-only gun-milling program created by Defense Distributed and recommended by the group for anyone other than advanced CNC mill users. The Ghost Gunner also comes with the DDCut instruction file for milling an AR-15 lower receiver, shipped on a USB thumb drive in the box. (Putting it on the Internet, as with the 3-D-printable files, might have prompted the State Department to threaten Defense Distributed with prosecution again for weapons-export-control violations.) I installed DDCut and found that for its primary purpose of finishing a lower receiver, the Ghost Gunner is absurdly easy to use—mostly because I was never given the chance to make any choices. Once DDCut began running the AR-15 file and cutting into my 80 percent-lower receiver, my only interaction with the software was clicking "next" through a 22-step set of instructions and then doing things to the aluminum part that the software told me to do. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg For one hour-long stretch in that process, I was given nothing to do but simply admire the Ghost Gunner as its blurred, cylindrical blade cut away the gun's trigger well with inhuman precision. At other times it seemed to alternate between carving aluminum and assigning me tasks like changing the lower receiver's position, tightening and loosening bolts, switching the end mill to a drill bit, or even vacuuming up the aluminum shavings that piled up in and around the machine. Eventually, it felt much more like the Ghost Gunner had programmed me to be its gun-making tool than vice versa. The Ghost Gunner drills out a lower receiver's trigger pin hole. Josh Valcarcel/WIRED Over those hours, I couldn't help but appreciate the beauty of the Ghost Gunner's design and engineering. As it patiently removed metal, the aluminum piece and the cutting tool moved in robotic, mesmerizing patterns. The noises the machine produced alternated between high-pitched shrieking and low groans that echoed through the WIRED newsroom and elicited complaints from neighbors. But during quieter lulls, the Ghost Gunner also emitted a series of rising and falling harmonics, produced by vibrations of the mill's stepper motors, that sounded like a kind of alien melody. My editor, Joe Brown, who came into the room to watch the machine at work, remains convinced the machine was programmed to play a piece of composed music. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg When it was only three steps away from finishing its full process, however, the Ghost Gunner hit a serious snag. The probe the mill uses to measure the lower receiver's location malfunctioned, and the machine locked itself. To get it moving again, I had to break the rules of my experiment and call Cody Wilson, Defense Distributed's founder, to seek advice. At first he told me I'd have to rerun the entire process—close to four hours of wasted time. "It's a design flaw," Wilson admitted. "If it stops, it has to start again from the beginning." But Wilson soon came up with a better plan and sent me a new file that rehearsed only the last portion of the AR-15 cutting process. Twenty minutes later I pulled from the machine the shining, perfect body of a semiautomatic rifle, as warm as if it were some baked good fresh from the oven. My fully assembled AR-15. Josh Valcarcel/WIRED The Ghost Gunner's lower receiver looked obviously superior to my 3-D-printed one—and even more obviously superior to the hot mess of uneven aluminum I'd chewed up with the drill press. But before assembling the full weapon, I wanted an expert opinion. So I visited Bay Area Gunsmithing, a sunny garage in Novato, California, populated by two professional gunsmiths, a very impressive collection of ordnance, and a gracefully aging dachshund named Ruth. When I showed my manually drilled lower receiver to Nathan Rynder, the shop's owner, he dismissed it immediately. The hammer and trigger wouldn't fit into the narrow, winding gorge of the trigger well I'd created, and I hadn't even gotten as far as drilling holes for the selector and trigger pins. (He did note that he'd seen worse attempts, including a customer who had brought him a lower receiver with a gaping, unintended orifice drilled through its side.) I was more surprised when Rynder insulted my 3-D-printed lower receiver. "This is not ready to rock," he said, skeptically probing the part's details with his fingers. He pointed out that the blueprint had misplaced something called a "takedown pin hole," and he made a further to-do list of necessary fixes before it could be assembled. "You'd need to thread in a pistol grip, clean out the buffer tube threads, clean up everything a pin went through," Rynder said. "You’d need several hours of labor to clean this thing up." Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Just the idea of a 3-D-printed lower receiver bothered him; if the ring that held on the buffer tube and stock (the big loop at the back of the receiver) were to break, he pointed out, it could unleash a large and powerful spring inches from the shooter's face. "It scares me," Rynder said. Building an untraceable AR-15 with the Ghost Gunner is pricier than it would be with a traditional drill press. But it requires far less skill than that manual method and costs less than creating the gun with a typical 3-D printer. Drill Press Method JET drill press rental: $250 End mills/drill bits: $97 Slide Vise: $80 80 percent lower jigs: $135 80 percent lower receiver: $68 Upper receiver: $550 Lower receiver parts kit: (trigger, hammer, grip, etc) $75 Stock: $63 Magazine: $16 Total: $1,334 3-D Printer Method Makerbot Replicator: $2,900 Plastic spool: included Upper receiver: $550 Lower receiver parts kit: (trigger, hammer, grip, etc) $75 Stock: $63 Magazine: $16 Total: $3,604 Ghost Gunner Method Ghost Gunner: $1,500 80 percent lower receiver: $68 Upper receiver: $550 Lower receiver parts kit: (trigger, hammer, grip, etc) $75 Stock: $63 Magazine: $16 Total: $2,272 My Ghost Gunner–milled AR-15 body, by contrast, got a stoic nod of approval. Rynder—who, allow me to stress, makes guns for a living—wasn't exactly wowed that I'd produced a functional, essentially flawless lower receiver. But he gave me the go-ahead to build it into a full rifle. "It's safe to assemble, safe to fire," he said. "Yes, you could put this together and it would be ready to go." Over the next hour in Rynder's shop, I constructed my AR-15. This was harder than Forrest Gump makes it look. But I persisted, learning the process as I went by watching a YouTube video from Ares Armor a few seconds at a time. (At a couple of points, Rynder couldn't help but point out that I had inserted a part backward or give me an unsolicited hint. I suppose this was cheating in my one-man gunsmithing experiment, but unfortunately Rynder was a very friendly, helpful, and competent person.) When I finally slotted in the pins to attach the upper receiver—a component that looks much more like a gun than the lower receiver and whose total lack of regulation is, frankly, bizarre—they made a pleasant chink. My AR-15 was complete. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg I looked down at the fully built rifle and something in my brain shifted. I realized that the abstracted parts I'd been fiddling with had turned into an object capable of killing someone. My lower receiver had transformed from a "gun" in a legal sense to a "gun" in a very practical sense. I remembered that I should start being careful where I pointed it. Firing my AR-15. Josh Valcarcel/WIRED Three days later, at a private range in Richmond, California, a half hour from Rynder's shop, I loaded my AR-15 with a 10-round magazine of .223 caliber ammunition and fired it for the first time. I pulled the trigger hesitantly as I aimed at a piece of cardboard 50 yards away. The deafening blast silenced the tweeting of nearby birds and echoed around the range's wooden walls as the rifle's stock dug into my shoulder. I could see a tiny hole in the cardboard. A plume of dust rose from the dirt berm behind it. "Well, it goes bang," Rynder said. I fired again. Then three more times. Then I emptied the magazine. Then I reloaded and emptied another one. Halfway through the next magazine, I pulled the trigger but got nothing but a soft click. The rangemaster, who happened to be a former winner of the shooting competition reality TV show Top Shot named Chris Cheng, diagnosed that the upper receiver had jammed and needed to be lubricated—a common problem with new rifles. He opened it up and doused the bolt and buffer parts in grease, then put the upper receiver back on. My rifle performed perfectly for the rest of the morning. After our video team fired the rest of the 40 rounds I'd brought, Rynder walked over to the neighboring range and convinced the friendly local SWAT team members practicing there to give us another 60 rounds. We shot those too. The gun didn't misfire again. The day after that shooting field trip, I had a flight home to New York. Taking my ghost gun on a plane—legally, three ghost guns, in fact, since I had created three lower receivers—seemed unwise. I couldn't leave them in WIRED's office in San Francisco either, because that might count as legally transferring ownership of the unserialized guns, which is a felony. I considered destroying them with a hacksaw, but regulations posted online by the Bureau of Alcohol, Tobacco and Firearms seem to demand that a lower receiver be destroyed with a blowtorch, removing enough metal that it can't possibly be welded back together. The testfiring target. Josh Valcarcel/WIRED So instead I decided to surrender my three lower receivers to the local police. I disassembled my AR-15 and left a large box containing all of the parts except the lower receivers on my editor's chair. Then I walked down the street to the police station in San Francisco's SoMa neighborhood and told the lady at the front desk I wanted to hand over some firearm components. She gave me a puzzled look and asked me to sit down. Forty minutes later, two cops emerged from a door and asked what I was doing there. I explained and showed them the three lower receivers. They examined them with expressions that were simultaneously quizzical and bored. I asked them if it was common to see AR-15 lower receivers like these: homemade, with no serial numbers. "I've never seen this before," one of them said. The cops gave me a handwritten receipt for the three weapons I'd turned in, as if to definitively show that these were no longer outside of law enforcement's awareness or control: They now had a number. Then they took my lower receivers behind their locked door and I said goodbye to my ghost gun. When this story published, the Ghost Gunner still sat in a storage room of WIRED's office a few blocks away. It's ready to make another lower receiver at any time. And Defense Distributed has already sold more than a thousand of their gun-making boxes, each one a tiny, easy-to-use, anarchic rifle factory. In other words, to paraphrase the rifleman's creed again, this ghost gun was mine. But there will be many like it. This landmark ruling has opened pandora's box for DIY guns This $1200 machine lets anyone make a metal gun at home What you need to know about the "ghost gun" machine that makes untraceable handguns real-world home Get even more of our inside scoops with our weekly Backchannel newsletter Senior Writer X Topics longreads WIRED Classic Threat Level Dell Cameron Dell Cameron Dell Cameron Dell Cameron Dhruv Mehrotra David Gilbert David Gilbert Dell Cameron Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"AI, the WGA Strike, and What Luddites Got Right | WIRED"

"https://www.wired.com/story/wga-strike-artificial-intelligence-luddites"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Angela Watercutter Culture AI, the WGA Strike, and What Luddites Got Right The Writers Guild of America (WGA) strike began on Tuesday. Photograph: FREDERIC J. BROWN/Getty Images Save this story Save Save this story Save The Monitor is a weekly column devoted to everything happening in the WIRED world of culture, from movies to memes, TV to Twitter. Earlier this week, on the red (technically striped) carpet of the Met Gala , The Dropout star Amanda Seyfried answered a tough question: What did she think about the then-impending Writers Guild of America strike? Wearing an elegant Oscar de La Renta dress made with 80,000 gold and platinum bugle beads, she told a Variety reporter that everything she’d heard from writer friends indicated they would picket if they couldn’t reach an agreement with the Alliance of Motion Picture and Television Producers. Poised, draped in priceless garments and jewels, she remained firm. Dystopias Marah Eakin State of the Art Madeline Ashby Digital Culture Jason Parham “I don’t get what the problem is,” she said. “Everything changed with streaming, and everybody needs to be compensated for their work. That’s fucking easy.” Seyfried’s friends were right. At midnight that night, while many Met Gala attendees were still at after-parties, the WGA declared that the strike, the first of its kind in 15 years, was on. “The decision was made following six weeks of negotiating with @ Netflix , @ Amazon , @ Apple , @ Disney , @ wbd , @NBCUniversal, @Paramountplus, and @Sony under the umbrella of the AMPTP,” the organization tweeted late Monday. “Though our Negotiating Committee began this process intent on making a fair deal, the studios’ responses have been wholly insufficient given the existential crisis writers are facing.” Throughout the week, explainers have delved into what that crisis entails. For one, the 11,500 TV and film writers in the union were seeking more writers per show, shorter exclusive contracts, and better minimum pay—all conditions the guild says have gotten worse in the streaming era. For another, the union wants guardrails for Hollywood studios’ use of AI. Specifically, the Writers Guild is asking that their contract include language stipulating that every credited writer be a human person, that screenplays, treatments, outlines, and other “literary material,” in industry parlance, can’t be written by ChatGPT or its ilk. Also, they’re asking that AI not be used to generate source material or be trained on work created by WGA members. AMPTP responded by saying they’d be willing to have “annual meetings to discuss advancements in technology.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Call someone a Luddite these days and they’ll think you’re saying they’re afraid of technological change. Actual Luddites, though, were nothing of the sort. In the middle of the Industrial Revolution, amid an economic downturn and growing unemployment, British textile workers began demanding better wages. Their form of protest was destroying the machines that automated their jobs. Many workers at the time worried about being replaced by technology, but that doesn’t mean the Luddites were totally against it. “They just wanted machines that made high-quality goods,” Kevin Binfield, editor of Writings of the Luddites , told Smithsonian Magazine in 2011 , “and they wanted these machines to be run by workers who had gone through an apprenticeship and got paid decent wages.” Apply this thinking to modern concerns about AI taking jobs and it’s an argument for human creativity, for people who understand new technologies and can work with them. In their public statements, the WGA has said studios can point writers to AI-generated content for research, AI just can’t do the writing itself. It’s all about how the machines are utilized. People forget, often blinded by the glitz and glam, that Hollywood is a union town. Screenwriters, directors, crew members—they all participate in some kind of collective bargaining. Brad Pitt once, while serving as an extra in a film, tried to give himself a line in an attempt to get a Screen Actors Guild card. (He failed. ) That means the WGA’s actions now might end up influencing the future of the labor movement. So many professionals—from journalists to artists to coders—are facing competition from machine learning systems, and with the eyes of the world on the WGA’s battle, its wins or losses could set precedents for other industries. Does all of this sound alarmist? Maybe, but remember: No one really knows how to handle AI’s potential— not college administrators , not the US Copyright Office , not record labels. This week, the Biden-Harris administration announced an initiative to “ promote responsible AI innovation. ” Even AI’s greatest minds seem shaky on the subject. AI pioneer Geoffrey Hinton made headlines this week when he quit Google and told The New York Times he feared the future: “It is hard to see how you can prevent the bad actors from using it for bad things.” In March, a group of tech leaders published an open letter calling for a pause in AI development to examine the risks posed by “human-competitive intelligence.” The three humans it took to pen Terminator gave more dire warnings. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg These anxieties about the future were likely not that different from what the Luddites were experiencing. One may say—and there’s always someone who will—that progress will happen regardless and people should be willing to embrace the machines, that AI may replace some roles but it’ll create new jobs. As Silo creator and Wool writer Hugh Howey told WIRED this week , “Automation was going to take jobs, but so far it’s only changed jobs.” But just because writing can be done by a machine doesn’t mean it should, or that it will generate the best, most original story. Fast fashion has pushed mass-produced garments everywhere, but the costs, while cheap, are exorbitant. Ned Ludd, the Luddites’ namesake, probably never existed. He’s often referred to as “ mythical ,” a name and a story people rallied around. He symbolized smashing the system that wanted people to make things quickly without training or fair pay. This is why I’m still thinking about Seyfried four days later. What she said reverberated widely; her comments were shared all over news and social media, making her a champion of working people. It was eye-catching, perhaps even more so than her dress beaded by hand. You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Senior Editor X Tumblr Topics The Monitor artificial intelligence TV Movies Entertainment Netflix apple apple tv Disney Angela Watercutter Alex Winter Angela Watercutter Gregory Barber Angela Watercutter Angela Watercutter Angela Watercutter Angela Watercutter Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Hollywood’s Screenwriters Are Right to Fear AI | WIRED"

"https://www.wired.com/story/hollywood-screenwriters-artificial-intelligence-guardrails"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Will Bedingfield Culture Hollywood’s Screenwriters Are Right to Fear AI Photograph: Jonathan Kitchen/Getty Images Save this story Save Save this story Save One of the more harrowing reads for writers concerned about artificial intelligence encroaching on their livelihoods is a study commissioned by OpenAI itself. Published in March, it places writers in the “fully exposed” category. This means that, according to OpenAI, a large language model (LLM) could reduce the time it takes for them to carry out their work by at least 50 percent. AI can already score in the 93rd percentile on SAT reading exams; it can already produce bad stories and poems. Directors are discussing the possibilities of AI-generated scripts. It’s no wonder, then, that the Writers Guild of America is demanding a greater say in how AI is used in Hollywood. Talk Is Cheap Chris Stokel-Walker Music Will Bedingfield Yippee Ki-Yay Will Bedingfield When WGA members began their picket on May 2, the first such strike in 15 years, focus was on streaming services’ impact on Hollywood and how the residuals paid to writers for streaming projects hadn’t kept pace with those of traditional broadcast shows and theatrical releases. But there was another demand: that the agreement with studios “regulate use of material produced using artificial intelligence or similar technologies.” The Writers Guild isn’t alone in trying to figure out AI’s place in its industry. Artists, actors, musicians—people in all creative professions—are trying to wrest control of the technology before it is used against them. It’s a smart move. If the history of automation has demonstrated anything, it’s that leaving the implementation of new technologies up to management is a bad idea. Over the phone, John August, a member of the WGA’s negotiating committee and writer of Charlie's Angels , explains that the proposal “says that material generated by AI or similar technologies is not considered literary material or source material for the purposes of the contract.” In this context, literary material refers to the stuff writers get paid to write: screenplays, treatments, outlines. Provisions over source material, on the other hand, seek to ensure that writers will not be asked to adapt AI-generated scripts—trained on human writers’ work—as they might with a novel. In both of those scenarios, writers’ employment and pay shrinks. The Alliance of Motion Picture and Television Producers rejected this proposal, offering “annual meetings to discuss advancements in technology.” With emerging tech, things rarely happen as advertised. This is particularly germane to LLMs , where the scope of possible ends still ranges from flash-in-the-pan productivity tools to society-upending sci-fi intelligence. Skeptics often bring up self-driving cars, baptized in hype a decade ago but still not flooding the roads or outmoding truck drivers. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Nonetheless, generative AI’s current trajectory conjures inescapable parallels with the encroachment of streaming services on the Hollywood system. August recalls that at the time of the 2007 WGA strike, the major streaming services hadn’t yet taken off. He had, however, begun to notice the stirrings of deep sea change, portended by innovations like spin-off “webisodes” of The Office being thrown onto the internet. “We saw that this might be the next way that companies would be able to make money off of our work,” he says. “So that strike was largely about making sure that, no matter what the medium was, our content still was paid for upfront in a fair way and paid for in the back end through residuals. We didn’t know what streaming was going to become. But we knew the internet was going to be the future.” There’s a long history of management painting automation as something as inevitable as sunrise. It’s an echoing pattern, one the late historian of technology David F. Noble summarized in Forces of Production , his account of the implementation of machine tools in America. “‘Automatic’ or ‘self-acting’ machinery made it possible for management both to eliminate workers altogether and to control more directly the production process,” he wrote. “The machinery, in turn, was used to discipline and pace the operators who attended it, thereby reducing the “labor problem” indirectly via the seeming requirements of the technology of production itself.” Power and Progress: Our Thousand-Year Struggle Over Technology and Prosperity , a book from MIT economists Daron Acemoglu and Simon Johnson that’s due out next month, chronicles a thousand years of elites—from European nobles in the Middle Ages to modern-day tech CEOs—gaining from technological advancements at the expense of workers. Generative AI fits neatly into this historical context. “We argue that this obsession with machine intelligence is not helpful because it’s all about replacing people,” Johnson explains. “Whereas if you focus on making machines useful to people—nurses, doctors, teachers, and so on—that will be much more helpful to productivity and therefore, potentially, to pay.” Futures range in awfulness. August’s personal dystopia is what he calls the Nora Ephron scenario, where AI learns to mimic cultural titans, eclipsing new human writers. Studios likely won’t employ AI scabs during this strike, not least because having AI tools cross the picket line introduces a host of copyright issues , but it’s not hard to imagine that this could happen at one point. (“You cannot protect studio execs from their bad ideas,” he says.) Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg And then there is the most likely bad scenario, the one worth getting out in front of right now: a producer requesting that a writer edit a script (which pays less than producing an original work) and not telling them it was generated by a chatbot. “That’s a crisis in our compensation, it’s a crisis in our residuals, and a crisis in our artistic ability to do the things we are put in this industry to do,” says August. “So that’s a fundamental nightmare scenario. And that feels very obvious if we don’t get this resolved.” More positive outcomes include improved productivity, like moving from a typewriter to a word processor. Commentators are unsure , however, whether that increase in productivity will lead to tangible improvements, like an increased standard of living. ChatGPT is already useful for brainstorming: If you need 15 different names for a Mandarin bagel shop, as August puts it, AI does an alright job. And he sees a possibility that the tech could create opportunities for more diverse writers, improving the scripts of someone for whom English is not their first language, for instance. Automation and redundancy are not necessarily conjoined, and introducing disruptive technology—like the self-checkout machine —is a choice. There are examples of times when worker perspectives on new technologies, not just those of management, have been successfully taken into account. In their book, Acemoglu and Johnson cite West Coast longshoremen who demanded to be retrained in new technology. They won, leading to a reduction in job losses and an increase in productivity. Katya Klinova, head of Al, labor, and the economy at the Partnership on AI, points to Unite Here, which represents hospitality workers, who in 2018 successfully won the right to negotiate how Marriott plans to bring in new technology, like online services, computers, and even robots. Digital technologies are inherently isolating: They do not lead people into factories to discuss concerns with their fellow workers. The efforts of a union with the relative power of WGA trying to assert control over AI implementation are instructive for everyone. For the writers, it’s critical: Their contract is only up for negotiation every three years. That’s a long time in tech. “You know, in 2007, streaming wasn’t there yet. But by 2010, you started to see those inklings,” says August. “In 2023, AI is not replacing us—AI is not being used to write exactly what we’re doing. But by 2026, the next time this contract is up, it really feels like that technology will be very refined. We need to make sure that this is addressed.” You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer. Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Staff writer X Topics TV Movies hollywood artificial intelligence Matt Kamen Reece Rogers Matt Kamen Brendan I. Koerner Jennifer M. Wood Megan Farokhmanesh Gregory Barber Jennifer M. Wood Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"The 'Joan Is Awful' Episode of 'Black Mirror' Asks You to Please Click Here | WIRED"

"https://www.wired.com/story/black-mirror-joan-is-awful-click-here"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Amit Katwala Culture Please Click This Link About Black Mirror 's 'Joan Is Awful' Episode Black Mirror 's new season hit Netflix today. Photograph: Netflix Save this story Save Save this story Save “Joan Is Awful,” the first episode of the new season of Black Mirror , was inspired by The Dropout. Specifically, as creator Charlie Brooker told WIRED this week, it was sparked by seeing the deluge of content surrounding Elizabeth Holmes and the Theranos scandal—a book, a TV show, a movie, around 800 podcasts—and thinking about how weird it must have been for people to see themselves portrayed by Hollywood actors in events that “feel like they happened about 10 minutes ago.” The content machine does seem to be catching up to people’s real lives: The gap between a huge financial scandal and the announcement of the inevitable Michael Lewis book about it used to be years or months; now it’s days. In the UK, Sky produced a dramatization of the British government’s handling of the pandemic while Covid-19 was still tearing through communities. (Spoiler alert: They blew it. ) WIRED Q&A Amit Katwala Culture Guides Matt Kamen and WIRED Staff Culture Guides Matt Kamen and WIRED Staff The logical conclusion of that narrowing of the gap between inspiration and dramatization—through Black Mirror ’s twisted, worst-case-scenario lens—is what viewers see in “Joan Is Awful”: personalized content, generated by artificial intelligence, using deepfakes of famous actors as stand-ins for regular people. Joan—a mid-level executive at a generic startup played by Schitt’s Creek ’s Annie Murphy—gets home after a difficult day at the office to find the events of that very day have been turned into a slick television show starring Salma Hayek as the titular character. Things spiral from there—there are layers upon layers, content all the way down. Society has been moving in this direction for years. Social media algorithms started by showing people stuff their friends were sharing but soon morphed into prioritizing things they will engage with, whether that’s what they want to see or not. TikTok enjoys success because users don’t curate their own feeds: Instead of the stuff you think or pretend you’re interested in, it shows you what you’re actually into, tapping into your basest desires. (That’s why my feed is mostly recipes for Korean fried chicken.) This also explains why Twitter now defaults to the For You tab of algorithmically determined tweets from people you may or may not have chosen to follow. “It’s designed to keep the viewer in a state of mesmerized horror,” says the CEO of Streamberry, the Netflix-like platform behind Joan Is Awful , at one point in the Black Mirror episode. “It’s great for engagement.” These rules apply whether you’re watching Netflix or tweeting about it. Of course “Joan Is Awful” (the episode, not the show in the episode) takes this to extreme lengths, but one of the supposed benefits of generative AI is that it will enable personalized content, tailored to our individual tastes: your own algorithmically designed hell, so horribly well-targeted that you can’t tear your eyes away. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But as a content producer (we’re not called editors and writers anymore), I’m really interested in what that means for this sort of article—the content about the content. What happens to cultural commentary when everyone is consuming different stuff? What happens to cultural commentary when everyone is consuming different stuff? The irony is that while hyper-personalized content might be great for engagement on streaming platforms, it would be absolutely terrible for websites like this one, which draw some of their currency from shared cultural moments: Game of Thrones , Succession , Black Mirror (hopefully). Like a whale carcass rotting on the ocean floor, landmark shows like Black Mirror and Succession support a whole ecosystem: We siphon off a portion of the search interest in these topics, capitalizing on people who have just watched something and want to know what to think about it. This helps explain the media feeding frenzy around the Succession finale and why I’m writing this story about Black Mirror even though we ran an interview with the creator yesterday. In a way, you could see that as the media’s slightly clumsy attempt to replicate the success of the algorithm. We don’t know as much about our readers as Facebook knows about its users, but we do know that a significant number of people will tune in for a landmark television event, and we also know for a fact that they’re interested in that show. The same thing happened with The Last of Us , which I’m linking to here in the hopes that you’ll read our coverage. It’s a rare alignment, the clouds parting to reveal a solar eclipse. (Without good data, this can go wrong: Axios points out the wild disconnect between the number of articles about Succession and the number of people who actually watch the show.) Maybe the next step is personalized content about personalized content. In “Joan Is Awful,” we see deepfakes generating content tailored to individual users. Perhaps LLMs will be able to magic up individual articles about that content too: Joan reading an article about the latest episode of Joan Is Awful , which then becomes a scene in the next episode of Joan Is Awful , content about content about content. You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer. Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Senior writer X Topics streaming TV Social Media Matt Kamen Reece Rogers Angela Watercutter Amanda Hoover Angela Watercutter Elana Levin Gabrielle Niola Steven Levy Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"San Francisco Mayor London Breed on the City’s Troubles—and Hopes | WIRED"

"https://www.wired.com/story/have-a-nice-future-podcast-1"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons By Gideon Lichfield and Lauren Goode Business San Francisco Mayor London Breed on the City’s Troubles—and Hopes Facebook X Email Save Story Mayor Breed addresses a crowd at San Francisco city hall. PHOTOGRAPH: GETTY IMAGES Save this story Save Save this story Save Welcome to the premiere of WIRED's new podcast, Have a Nice Future. In this first episode, Gideon Lichfield and Lauren Goode talk to the mayor of San Francisco, London Breed, about how she plans to address the city’s problems, from homelessness to crime to abandoned downtowns, and how the changes she's proposing could shape not just San Francisco but the cities of the future. Read more about the city WIRED calls home. Our coverage of San Francisco includes stories about self-driving cars, infrastructure, the tech industry, health care, and homelessness. Lauren Goode is @ LaurenGoode. Gideon Lichfield is @ glichfield. Bling the main hotline at @ WIRED. You can always listen to this week's podcast through the audio player on this page, but if you want to subscribe for free to get every episode, here's how: If you're on an iPhone or iPad, just tap this link , or open the app called Podcasts and search for Have a Nice Future. If you use Android, you can find us in the Google Podcasts app just by tapping here. You can also download an app like Overcast or Pocket Casts and search for Have a Nice Future. We’re on Spotify too. Note: This is an automated transcript, which may contain errors. Lauren: Energy up. Gideon: Hi, I'm—oops. Too much energy. Yes. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Lauren: Energy down. Gideon: Hi, I'm Gideon Lichfield. I'm the editor in chief of WIRED. Lauren: And I'm Lauren Goode. I'm a senior writer here at WIRED. Gideon: It's 30 years ago that WIRED magazine was founded in San Francisco, and that anniversary has made Lauren and me feel quite reflective. Lauren: As one gets when they turn 30. We went into the conference rooms, threw a bunch of pillows and blankets on the floor, turned on some Enya. Really got our '90s vibe on, and we just reminisced. Gideon: Ah, Enya. It's funny to think about what the world of tech looked like 30 years ago. In fact, just a few weeks before the first issue of WIRED was released in January 1993, this guy named Tim Berners-Lee created the very first hypertext pages of a little something he called the World Wide Web. Archival: It spans the globe like a superhighway. It is called the internet. Lauren: People were really excited about the transformative potential of the web. The editors at WIRED certainly were; I found this letter to the editor in an old issue criticizing WIRED for being a little too “orgasmic” about the internet. Gideon: Orgasmic. Lauren: Yeah. And I don't even think they were talking about specific websites. Gideon: Hmm. Archival: For years they've been saying these things would change. The world would mature from adding machines and typewriters to tools of the human spirit, personal desktop computers, a network of people with unique experiences and expertise connected all over the globe. Lauren: What could go wrong? Gideon: So much went wrong in really unexpected ways. I mean, who would've predicted QAnon or ISIS recruiting videos, or the ice bucket challenge? Frankly, the future is unpredictable, and that’s what can be really disconcerting Lauren: And the pace of innovation has just accelerated so much. Cryptocurrencies, generative AI, the metaverse, so many exciting changes— Gideon: But also freaky changes– Lauren: Changes we can't seem to pump the brakes on and will have to face one way or another. Gideon: So we decided to make a show about it. Have a Nice Future. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Lauren: It's a podcast about how fast things are changing, in good ways and in ways that make us deeply uncomfortable. Gideon: Each week we're going to talk to somebody with a big, audacious idea about the future and ask, is this really the future we want? Lauren: We want to ask people what keeps them up at night, and also what keeps them feeling optimistic. Gideon: And then after we share the interview with you, Lauren and I will discuss how we feel about the future. They're describing what we think is good about their vision, what we think is troubling, and what we and you can do about it in our own lives. Lauren: We'd also like to hear what you think. So send us any questions you have about the future or what's concerning you. Gideon: Or even what makes you optimistic. Lauren: Yes, that too. Gideon: So we decided to kick off this weekly conversation with someone who's pretty directly shaping mine and Lauren's future. And ultimately probably yours too. Lauren: On today's episode, we talk to London Breed, the mayor of San Francisco, whose job, as clichéd as it sounds, really is to build a better future for this city. And we have to determine, is this the future we want? Gideon: We wanted to interview Mayor Breed because WIRED was founded in San Francisco, of course, and the digital revolution that WIRED was created to cover began in the Bay Area. But tech infiltrates and warps all aspects of life. It changes our social fabric and our urban fabric, and Have a Nice Future is about all of those changes too, not just the bits that are directly brought about by a new piece of code or hardware. Lauren: San Francisco is a place of contradictions where you have incredible wealth alongside terrible deprivation, and progressive left-wing values juxtaposed with extreme libertarianism. Like a lot of cities around the US right now, San Francisco is facing severe problems with empty downtowns, but also a high cost of living, drug abuse, crime, and homelessness. Gideon: Right. And just last week, a prominent member of the city's tech community, Bob Lee, the founder of Cash App, was stabbed early in the morning outside an apartment building in San Francisco and died at the hospital. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Lauren: We taped this conversation with Mayor Breed before that happened. She has since issued a statement calling the fatal stabbing a horrible tragedy, but it's certainly another thing that gets added to the portrait of San Francisco as a place that you know is scary and a dangerous place to live. Gideon: But as you'll see, the safety of the city's streets is one of the things she talked about the most. Lauren: And we'll get to all of that with Mayor Breed after the break. [ Break ] Gideon: Mayor Breed, thank you very, very much for joining us on Have a Nice Future. Mayor Breed: Thank you. Gideon: How is your future going so far? Mayor Breed: My future is here right now. In my present. It's going OK. Gideon: That's true for all of us. That is what this show is about; it’s about the fact that our future is here, and we're all trying to figure it out as we go. Mayor Breed : Yeah Gideon : You grew up here. You were raised in public housing by your grandmother. You've seen the city change a lot. Some of that change has probably been good, some of it's been bad. What's the biggest change that you've seen growing up here? Mayor Breed: I think the biggest cultural change probably is the decline of the African American community. Even though the community was always considered a smaller part of San Francisco, at its height it was somewhere between 12 and 14 percent. There used to be just more African Americans, more African American businesses, more African American cultural activities and events. And that's changed. Many of the people who were born and raised here don't live here anymore. And that's the thing that I miss the most. Lauren: What has caused this decline? Mayor Breed: There are a number of factors, and I can really speak from personal experience. You know, I grew up in public housing, and sadly there was a lot of violence and hopelessness and frustration. And I think some people moved away for better opportunities, as well as to protect their families from the violence. But also, the projects I grew up in were demolished and people were moved, and they were not necessarily moved back. So I think a number of issues played into that decline, including policies and decisions made by this city. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Lauren: A lot of people looked at tech as the accelerator of changes like that, and your predecessor, Mayor Ed Lee, was known for being pretty friendly to the tech industry. There was even something known as the Twitter tax, where he was giving tax breaks to tech companies that have their offices here, that would bring young talent here driving the economy in the city. Which of his policies do you think were good for the city? Which policies are you actively looking to change in terms of the relationship to tech? How do you reestablish a kind of equilibrium between San Francisco and the tech industry? Mayor Breed: Well, I want to make it clear that before tech was a major part of San Francisco, the damage had already been done to the African American community. I think that when the tech industry and some of the policies that Mayor Lee put forward, including a number of tax breaks and incentives, it was at a point where, you know, job opportunities were very challenging for the people of San Francisco. I think that, moving forward, it was the right thing to do to provide incentives to attract these various industries to revitalize mid-market and to create these extraordinary job opportunities. I think the disconnect was, you know, what we didn't do as it relates to housing and connecting the existing population of San Francisco to those opportunities. I think it was a five-year period, for every eight jobs we created, we created one new unit of housing, so the housing market was not supporting the increase in the number of jobs. I also think that there was a real issue around making sure that tech had an obligation to, you know, hire locally in various capacities. And that we were creating these academies, which we did eventually, to prepare people for the jobs that exist, not just in coding and engineering and some of the things that were being done, but HR, security, receptionists, property managers. All of the layers of things that are needed, and making sure that there was some level of connection to the people who needed these opportunities the most and the ones that were being created. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Lauren: It is in fact a very different city from pre-pandemic. And I say this, I mean, this is my city. I live here. I love San Francisco, and it's very often that people come to visit here and they say, wow, this is a really beautiful city. They've just been hearing about it on the news, and they think it's like a war zone. And they come here and they realize it really is an incredibly beautiful city, but it does have its real problems. And from the pandemic, our population is down, our transit revenues are down, our homeless population has gone up. There are a lot of office buildings downtown that are totally empty. I hear your optimism for San Francisco, but it is a very changed city. And I do think it's a little bit harder to convince people this is the place they should absolutely come if they want to work in tech or build the next big tech company. What does it really look like going forward for you? Mayor Breed: Well, I don't agree that it's been hard to convince people to come here, because they, for whatever reason, are still coming here. I think they're just doing things differently. They don't want as much office space. They're allowing their employees to work remotely, and that is definitely going to change San Francisco in, in so many ways, because you don't have that same, you know, active population of people in the downtown area moving around and getting on public transportation and going to restaurants and all of that. But that's why part of my downtown recovery plan includes more creative options to make the downtown area not a 9 to 5 place. But to look at the evening and the weekends, as you know, possibilities of activities that could happen in the downtown area. The downtown area has been so restrictive in terms of what can be done there. And we have all these crazy codes that have been developed for years that make me insane. I mean, for example, the ability to take some of the office space and convert it into housing shouldn't be a difficult thing to do, but it is. It is because of the requirements of a yard and open space and all of these things that go with, you know, you have to get conditional use and these kinds of approvals to take an existing building and eliminate those requirements. And my goal in a lot of the legislation I'm proposing is to say, you know what? For these kinds of buildings, let's just remove it out of the way so that we don't even have to talk about it in the process of someone wanting to convert. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Gideon: I actually would love it if you could give us a high-level overview of the pillars of your recovery plan. How are you balancing the things you're doing to attract business back and attract residents back, and the things that you're also doing to deal with the issues that people, you know, complain about in San Francisco. Like crime and homelessness. Mayor Breed: Definitely. So I'll start with the crime and the homelessness component, because it's not just about homelessness, it's about substance use disorder and mental illness and people struggling. Because you know, what we find when we're out there with our street medicine teams and our street crisis response team and all of these resources that we're putting into making sure that we have an alternative response to the challenges of our streets other than our police officers. And so we are putting a lot more resources into that to make sure that we're able to be more aggressive about getting people off the streets and not allow the open-air drug using and some of the things that people are experiencing. Lauren: How do you do that? How do you actually get people off the streets and get them the support they need for substance abuse? Mayor Breed: Well, just so you know, San Francisco was one of the only cities in the region that was able to see a reduction in unsheltered homelessness. Fifteen percent reduction in unsheltered homelessness, and you know, 3 percent … Gideon: Over what period? Sorry. Mayor Breed: So since 2019 until the last point in time count that we did last year, we saw a decent reduction, but that had everything. It was so much work. Of course, it was purchasing hotel buildings. It was providing wraparound supportive services to make sure that people were getting the support and the treatment that they need. It was changing our entire shelter system that was more of a congregate living system and making it more individualized with trailers and cabins, and so just really increasing our capacity significantly to get people off the streets. So we built out our behavioral health beds for those who suffer from mental illness. We've built out our shelter system, and then we have these various teams who are out there every day trying to get to the bottom of the challenges that people are facing and get them into housing. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The problem that we have, and where we will need changes to our state law. And I know they're trying to push for some change to the conservatorship law so that we can deal with those suffering from mental illness, but we need a lot more drastic change so we can be able to force people. Because the only way, in some cases, if people tell us no, which they do, um, if they tell us— Gideon: Telling you, no, we don't want to come off the street … Mayor Breed: No, we don't want your help. No, we don't want your service. No, we're not going to get up. No, we're not going to leave. The only way we can deal with a problem like that is, you know, for example, some of our various basic laws to say, you know, you can't sit and lie on the sidewalk, so you're gonna have to move. Right? I mean, that's not a solution, but that's one of the only resources we have. Or if someone crosses the line and breaks the law, we can make an arrest. And our jails, unfortunately, this is not the place that people want to be used to help people who need treatment, uh, for addiction or substance use disorder or mental illness. And we need changes to state law in order to do a little bit more aggressive force to get people off the streets differently. Um, Gideon: You said in an interview last year with The Atlantic , you said that changes that you were proposing as mayor were gonna make a lot of people uncomfortable. And you said, uh, that it was time to be less tolerant of all the bullshit that's destroyed our city. What did you mean by that? Mayor Breed: Well, when I say less tolerant, it's … I know people have compassion for people who use drugs. You know, I personally have lost a sister to a drug overdose, and I have family members who suffer from addiction. But to say that, well, wait a minute, you know, they have an addiction and we need to, you know, provide them with support and services. I agree with that. But we also cannot let them publicly be out on the streets shooting up or using fentanyl or doing all these things where it has created a lot of chaos, and problematic situations happened in various communities. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg When I was growing up, during the crack epidemic, you know, we knew people were on drugs, but the other thing is, in my mind, respect for the community where, when they saw kids or older people walking, like they hid that to a certain extent. It was a thing that wasn't spoken. And we know people are gonna always have challenges with addiction. I pray it's not me or I don't continue to see it happen to the people I care about or anyone else in this city. But the reality is it happens, and we should not just, because we're empathetic, allow it to just happen on our streets, because we're saying, well, this person is suffering from addiction and should not, you know, be in prison. I agree, but this is a behavior we can't tolerate. And the other thing is the open air-drug dealing. Being able to publicly, you know, out in the open, deal drugs, sell it to anyone at any given time, and say, well, you know, people are being trafficked and forced to do this, but you know what? They're still breaking the law. We have to make arrests. We have to hold people accountable. We can't continue to just say, well, we don't want to go back to the failed war on drugs. And it's like, yeah, we don't. But did any of you who are saying that ever even live in it and understand what it felt and looked like? This is far worse. And so what we have to do is be a lot more aggressive in how we do things. Yes, if you want help, we get you help. But if the alternative, if you break the law, then community drug court is not gonna be an option for you. So I think we've gotten away from accountability, and that's what I meant. That was what I was frustrated about, about the kids and the families that I'm meeting that are in tears and that are frustrated in the living condition about people I grew up with who have had encounters with the police growing up, who live in the Tenderloin, who have gotten clean and sober and are saying, London, what is going on around here? Like this is worse than what I've ever seen it, and we need you to help us. So we have to continue to do whatever we can, as aggressively as we can, to make sure that people don't feel comfortable doing what they're doing in the Tenderloin right now. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Lauren: What other cities do you look to for ideas or inspiration around what San Francisco could you better? I think of a place like Houston, Texas, which has done a tremendous job with homelessness over the past decade or so. Austin, Texas. Which has done a really great job building up its tech community. I'm not saying that those are the best cities to be in. Once again, I'm still partial to San Francisco, but what do you look to, where do you look to? Mayor Breed: So let's just talk about that, because like Houston and Austin, you know what, they have space policies that are not, you know, problematic to the development of those housing units and I think it just makes it a lot easier. But I do look to places like, for example, Amsterdam, right? I love how people in Amsterdam are able to move around on bikes, buses, and different modes of transportation the way that they are. And just with how the bike infrastructure exists there. And I want to see San Francisco become more user-friendly for people to move around using different modes of transportation and less reliant upon cars. Lauren: But what’s actually preventing us from doing that? I mean, put this in the context of we have a huge budget. San Francisco has a huge budget. I had the opportunity to hear your comptroller, Ben Rosenfeld, speak recently at Manny's, a wonderful local community center, and hear a little bit about the breakdown of the city budget. And I think other people look at us and say, wow, $14 billion. That's a budget that's bigger than a lot of states and some entire countries. Uh, yet we have the problems that we have. Yet you are here, Mayor Breed, telling us that you have these ideas and ideals for what a city can be. Why can't we do that? What is stopping us? Mayor Breed: So I can spend this whole podcast talking just about the breakdown of the budget, because you have to keep in mind, San Francisco's a city and a county, We have our own airport. That's a part of the budget— Lauren: Our discretionary budget is much smaller. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Mayor Breed: Very, yeah. It's on a whole other level. But like, you know, the airport dollars stay with the airport, the public utilities commission with the sewer and the treatment plant, and the water and electricity—like all of those things are a part of this larger budget. So yes, the discretionary part is a lot more difficult. Then there are all these different carve-outs in the budget where this amount goes to children and families. This amount goes to this, this amount goes to that. It's not an excuse for why we can't. Because we were able to, you know, since I've become mayor, add over 22 miles of protected bike lanes. We did so aggressively. But it's not as easy as saying, OK, here's the money. You can't just—all of a sudden someone has access to their garage and then the next day they wake up and they no longer have access to their garage. So doing things like this requires outreach. It requires a lot of work. But I think in comparison to how we used to be when I grew up, you know, you didn't ride a bike to get around the city. You just did not. You got on the bus or you walked, and if you were lucky enough to have access to a vehicle, you were in a vehicle. But, you know, now the culture of San Francisco has shifted, and I think we're gonna get there. Lauren: What keeps you up at night? Mayor Breed: You know, I actually sleep really good at night. Gideon: What's your secret? Mayor Breed: I don't know what it is, but as soon as I hit the pillow, it's like I'm done. Because I gotta get my rest. If not, I'm gonna be grouchier than I already am. Lauren: Metaphorically speaking, what keeps you up at night? Mayor Breed: I think the thing that I think about most, uh, is really the challenges around the drug use and the drug dealing. You know, my goal is I want to see it improve. I want to see it turn around, and I want people to feel good about our city. Gideon: And what, to take the opposite line, in what way does San Francisco reflect what the city of the future could be? What do you see as the hopeful side of that? Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Mayor Breed: Well, I'm very hopeful because, you know, there have been political changes that have led to better results, uh, that we can produce for the city. I think, you know, the future of the city … Gideon: When you say “political changes” … Mayor Breed: Well, we have a new district attorney who's actually prosecuting people for crime. We have new members of the Board of Supervisors who are supporting reasonable policies that make sense. I think the people of this city want us to get back to basics. They want reliable transportation. They want clean and safe streets. They want to be able to make a decent living, hopefully purchase a home and raise their families and send them to school. To me that's the basics. AndI'm hopeful because I feel like the city is finally getting back to that. And the fact is, if we can get back to the basics and deliver for the people of the San Francisco, we can make this city so much better. And I am hopeful about that. I'm hopeful about the future. I'm hopeful about the city we are right now, but the, the city that we can definitely become by improving upon what we're already doing. Lauren: But how do you build San Francisco back in a way that we're not perpetuating inequities? And, by the way, we think about this a lot at WIRED—even right now, there's a lot of conversation happening about generative AI and how amazing it is. But you talk to researchers and economists and they say, is this only going to further the technological divide? Deepen the gaps, right? It's going to make the top 1 percent wealthier, and the bottom 90 percent are not going to be able to meet, you know, any kind of wealth goals. Like, how do we ensure that San Francisco, if it is built back up, we're doing it in such a way that it's not just, you know, the very, very wealthy who have a comfortable place to live and everyone else struggles to live. Mayor Breed: Yeah. And that's gonna continue to be a struggle because people go into business because they want to make money and they want to be wealthy, and so you're not gonna be able to get away from folks who choose to do that. But what I will say is that companies are becoming more intentional about supporting the surrounding community and not just flying in the next new talent or what have you. The talent is right here, and so that's part of it. But also, when we look at a lot of the disparities around homelessness, around violence, and around a number of other issues, and especially one of the populations that's declined most significantly, where are we going wrong? Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg We know what the problems are, so how do we make those investments? We've given down-payment assistance for people to buy homes, which has been extraordinary. I met these families and you know, in tears about the ability, never thinking they could buy a home in San Francisco in their lives. Thirty-four new brick-and-mortar businesses that are started that we helped with the down payment for, uh, the rent and uh, the build-out, so that they can get started, because they're not necessarily getting a lot of the capital, uh, to get those businesses started. And so I'm really proud of the investments the city's making, and also being intentional about getting more companies to be more open to supporting the community in a way that's gonna help bring people along. Rather than doing something to the city, it's doing something for the city. And I think we're gonna get there. Gideon: You talked about how you're excited for what the city could become. So what does that look like 20, 30 years from now? What's your ideal of how San Francisco looks different from what it is now? Mayor Breed: Well, it will look different because we'll have more housing in a lot of underutilized properties on the west side of town where you're not seeing a lot of places being built. We’ll have a great public transportation system where it's reliable and people decide they want to use it. We'll have more protected bike lanes. We'll have, like, no homeless ever. Like, it's just, as soon as you're on the street, we're picking you up and taking you into shelter, into a situation, and we're able to, you know, clear out our streets, keep them clean, you know, keep people safe and sober. And make sure that if people want an opportunity to take care of themselves, they get one. But more importantly, the city changes for the better, where people just walk down the street and say, Hmm, there's something different about San Francisco and I'm loving it. Lauren: And where are you in that timeline? Mayor Breed: I hope I'm still mayor in that timeline. I want to see it happen yesterday, but that's what I fight for every single day. Because as we said earlier, I grew up born and raised in poverty, and when I think about just my own family and the challenges we experienced—having a sister who died from a drug overdose, having a brother who's still incarcerated—that could have easily been me, and I'm mayor of San Francisco. And so for me, I feel really honored and that this is really a privilege that I can't take lightly every day I show up to work. It has to be about making sure that people don't grow up in the same kinds of conditions and challenges, and knowing what's possible when San Francisco gets it right. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Gideon: Well, Mayor Breed, thank you so, so much. Lauren: Thank you so much. Mayor Breed: Thank you. [ Break ] Gideon: So Lauren, as a resident of San Francisco, how do you feel about the city after we talked to the mayor? Lauren: Well, it was hard to feel pessimistic after the interview, because when we walked out of the mayor's office that day, we walked into this incredible atrium at City Hall and there was a wedding happening right then and there. Like there was one wedding happening when I first walked into the building that morning, and then we saw someone walking down the aisle as we came out of the office, and it's really hard not to feel optimistic when you're witnessing that sort of event. How did you feel about it? Gideon: You know, the thing that struck me was how animated she got when she talked about San Francisco, comparing it with Amsterdam—as you know, a very European city with bike lanes and buses and people in the streets in the evenings. And for just a moment, I had this glimpse of a city in which all of the problems of homelessness and drug abuse and poor housing have been cleared up. It is rather unique among American cities and could really be kind of a paradise. Lauren: San Francisco has gotten a lot better about having car-free spaces in bike lanes, which Mayor Breed talked about.But yeah, I thought it was really interesting how when we asked her what other cities she looks to for inspirations that she actually mentioned a European city instead of another US city. Gideon: Yeah, that was striking. What was also interesting was that she kind of skirted the questions that we were asking her about the tech industry and how to bring it back. She talked about, you know, making things easier for businesses, getting rid of some of the restrictions on permitting, for instance, but a lot of the things we were asking her about tech, she was bringing it back to the social issues, to the homelessness and the drugs, which she seems really impassioned about Lauren: Right? Yeah. She seemed to really thread the needle on the tech sector's direct impact on the city, both good and bad. She's absolutely correct that the African American population has been in decline since the 1970s. It's the Black community that sees the most consistent declines in the population in every census, and there are certainly discriminatory policies that have led to this. But you know, longtime San Franciscans will often say that it's tech that has driven the city's prices up and created a monoculture in recent years. Like it's, you know, in more recent times it's hard not to look at issues like the rising cost of housing and at least ask the question of whether there's a correlation between that and the rise of the tech sector. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Gideon: Yes. That's when I think she was being at her most political. As you say, she was threading the needle. She wanted to send a signal that the tech industry was welcome and wasn't being blamed for the social problems the city has. But at the same time, it didn't seem to be uppermost in her mind as the thing that she wanted to work on. Lauren: I would also like to have asked her more about safe consumption sites, which are places where people who have an addiction can get a hold of drugs or bring their own and use them with safety personnel around, which is part of a broader effort in harm reduction, right? The idea being that this would prevent overdoses. It's clear that drug abuse is a topic she feels strongly about. It is such a complicated issue though. Mayor Breed has said before she supports safe consumption sites, but there have been legal restrictions around them in San Francisco, and more recently she has said she would support a nonprofit model that might allow safe consumption, which is actually an idea borrowed from New York City. But overall, that's just one solution to what is clearly a much bigger problem. Gideon: I think the fact that she talks about this stuff so much reflects not just her own concern with it but also an awareness that around the country and around the world, this is a thing that people look at San Francisco and see … If you go to tech conferences or look at tech Twitter, people are talking about how the city has been overtaken by the homeless and there is drug use on the streets and there are cars being broken into all the time. It feels almost like there are these two completely different San Franciscos that exist in people's heads. One is this beautiful city, and one is almost the land of the walking dead. Right? Lauren: People who refer to these folks in the streets as zombies, I think, are sometimes forgetting that they're human beings too, and that it's going to take a huge collective effort to solve some of these problems. I'm not sure I left that conversation feeling like Mayor Breed knew exactly how to fix these things—because in fairness, what if the systems at play are bigger than anything she can do at the city level? What if we need a much broader conversation around money and taxes and housing and the role of government in providing safety nets and just what it means to be safe in a community and also care for your neighbors. I don't know, Gideon, did you walk away from the conversation feeling as though Mayor Breed had proposed some solutions you felt good about? Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Gideon: You know, it was striking to me that she's proposing pretty hard-line solutions. In some ways, she's talking about using the law and all sorts of other measures to essentially force people off the streets. And yet she doesn't come at this with a lack of empathy. You know, she talks about having lost her sister to a drug overdose, having a brother who's incarcerated. But all in all, yes, I feel like she's making quite a hard push. Lauren: Yeah, she is taking a firm approach, and the thing is, San Francisco isn't unique in dealing with a lot of these issues. Homelessness is spiking all across the country. Drug abuse is too, and few people have really come up with a good solution. So a lot of other cities will be watching and learning from Breed’s successes and mistakes. Gideon: And not just on drugs and homelessness. Right? Lauren: Right. She mentioned the empty downtowns and the restrictive zoning laws that she wants to change to deal with the rising cost of living. And that's yet again, a problem that we're dealing with all over. So if she finds that she can turn some of these empty office buildings into apartments, that would be huge, right? So, Gideon, are you going to stake out an empty floor of the Salesforce Tower for yourself? Gideon: Sure, if I can get one with south-facing windows. I have to say, I found Mayor Breed's vision of the city pretty compelling. Lauren: You know what else is pretty compelling? Some of the other guests we're gonna be having on this podcast. Gideon: Yes. We're gonna be talking to some exciting people in the next few weeks. We've got Max Levchin over at Affirm on the future of paying for things, but also biohacking and socialism, and so much more. Lauren: We've got a conversation with a futurist about how you should prepare your kids for climate change by basically scaring the bejesus out of them. Gideon: And we'll hear from the CEO of Slack about how to disconnect from your job when the future of work is increasingly always-on, thanks in part to things like Slack. Lauren: And we want to hear who you'd like to hear from. You can email us at [email protected]. Tell us what you're worried about, what excites you, any question at all you have about the future, and we'll ask our guests. Gideon: Have a Nice Future is hosted by me, Gideon Lichfield. Lauren: And me, Lauren Goode. Gideon: If you like the show, please leave us a review wherever you get your podcasts and follow us to hear more episodes. Lauren: Have a Nice Future is a production of Condé Nast Entertainment. Danielle Hewitt and Lena Richards from Prologue Projects Produce the show. Gideon: See you back here next Wednesday, and until then, have a nice future. You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Contributor X Senior Writer X Topics Have a Nice Future podcasts San Francisco Cities Infrastructure WIRED Staff Reece Rogers Reece Rogers Vittoria Elliott Lila Hassan Vittoria Elliott Caitlin Harrington Paresh Dave Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"ChatGPT’s Fluent BS Is Compelling Because Everything Is Fluent BS | WIRED"

"https://www.wired.com/story/chatgpt-fluent-bs"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Amit Katwala Culture ChatGPT’s Fluent BS Is Compelling Because Everything Is Fluent BS Photograph: MirageC/Getty Images Save this story Save Save this story Save Out in the deep waters of the Gulf of Mexico, a young woman named Rachel clings to the side of an oil rig. The wind whips her auburn hair into a wild tangle, and ocean spray drenches her jeans, but she climbs on, determined to uncover evidence of illegal drilling. When she arrives on board, however, she finds something far more sinister at play. This is a snippet of Oil and Darkness , a horror movie set on an oil rig. It features environmental activist Rachel, guilt-ridden rig foreman Jack, and shady corporate executive Ryan, who has been conducting dangerous research on a “new type of highly flammable oil.” It’s the kind of movie you could swear you caught the second half of once while late-night channel-hopping or dozed blearily through on a long-haul flight. It’s also entirely made up. Ideas Abeba Birhane and Deborah Raji Interruption Matt Burgess Yippee Ki-Yay Will Bedingfield Oil and Darkness was developed and written by the AI chatbot ChatGPT. Content marketer and AI hobbyist Guy Parsons provided a format , asking for a title, tagline, key characters, and plot details and suggesting the topic “a horror film set on an oil rig.” Then the user let OpenAI’s new software do its work. The results are astonishing: There’s dramatic tension, fleshed-out characters, and hints of a dark secret. It promises explosive action, and maybe even a touch of political commentary. It is yet another example—and there are many that have made the rounds on social media, WhatsApp chats, and the WIRED Slack in the past week—of the seemingly magical powers of ChatGPT. The AI chatbot is trained on text from books, articles, and websites that has been “cleaned” and structured in a process called supervised learning. ChatGPT can write code, make up songs, and compose limericks and haiku. It remembers what it has written and makes careful edits upon request. It takes even the most random prompts in stride, composing stories that neatly tie competing strands together: Details that seem irrelevant in the first paragraph pay off in the last. It can tell jokes and explain why they’re funny. It can write magazine-style ledes, punchy and attention-grabbing, with cogent yet completely fabricated quotes. All of this makes playing around with ChatGPT incredibly fun, charmingly addictive, and—as someone who writes for a living—really quite worrying. But you soon start to sense a lack of depth beneath ChatGPT’s competent prose. It makes factual errors, conflating events and mixing people up. It relies heavily on tropes and cliché, and it echoes society’s worst stereotypes. Its words are superficially impressive but largely lacking in substance—ChatGPT mostly produces what The Verge has described as “fluent bullshit.” But that kind of makes sense. ChatGPT was trained on real-world text, and the real world essentially runs on fluent bullshit. Maybe the plausibility of a made-up movie like Oil and Darkness comes not because AI is so good, but because the film industry is so bad at coming up with original ideas. In a way, when you ask an AI to make you a movie, it’s just mimicking the formulaic process by which many Hollywood blockbusters get made: Look around, see what’s been successful, lift elements of it (actors, directors, plot structures) and mash them together into a shape that looks new but actually isn’t. It’s the same in publishing, where narrow trends can sweep the industry and dominate for years at a time, lining bookshop shelves with covers that look the same or titles with the same rhythm: A Brief History of Seven Killings , The Seven Deaths of Evelyn Hardcastle , The Seven Moons of Maali Almeida , The Seven Lives of Seven Killers. (ChatGPT made that last one up.) Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg And it’s not just the creative industries. Fluent bullshit is everywhere: in viral LinkedIn posts and rules for life podcasts, in fundraising decks and academic journals , even in this article itself. Politics and business are full of people who have risen to the top because they’re able to stand in front of a room and ad-lib plausibly at length without saying anything real. Prestigious schools and universities structure education in a way that teaches people one skill: how to very quickly absorb information, confidently regurgitate it in a predetermined format, and then immediately forget it and move on to something else. Those who succeed spill out into government, consultancy, and yes, journalism. The discourse around ChatGPT has flagged the damaging effect it might have on society, everything from the model encouraging torture and perpetuating sexism to enabling kids to cheat on their homework. You worry about the impact of AI-generated responses finding their way into the data that future chatbot tools are trained on, creating an indistinct, Ready Player One -style mush of references—a bovine slurry, churned up and fed back to us, a virus that drowns out anything new. But to be honest, old-fashioned human-generated fluent bullshit—weaponized by social media—has already been pretty disastrous. In the UK, to pick just one example, a cadre of fluent bullshitters drove the country out of Europe and directly off a cliff. (“ChatGPT, write a speech about why Britain should leave the EU but fill it with arcane vocabulary and Shakespearean references.”) Post-truth, fluency is everything and bullshit is everywhere, so of course ChatGPT’s fluent bullshit feels plausible. It was bound to. It was trained on people. In the end, ChatGPT’s bullshit is a reminder that language is a poor substitute for thought and understanding. No matter how fluent and coherent a sentence may seem, it will always be subject to interpretation and misunderstanding. And in a world where everything is fluent bullshit, ChatGPT is just one more voice in the cacophony. And yes, it wrote that ending. You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Senior writer X Topics artificial intelligence Movies Books Angela Watercutter Angela Watercutter Alex Winter Angela Watercutter Kate Knibbs Kate Knibbs Angela Watercutter Angela Watercutter Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Welcome to ‘Disneyland With the Death Penalty’ | WIRED"

"https://www.wired.com/1993/04/gibson-2"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons William Gibson Backchannel Welcome to ‘Disneyland With the Death Penalty’ Photograph: Sebastiaan Kroes/Getty Images Save this story Save Save this story Save "It's like an entire country run by Jeffrey Katzenberg," the producer had said, "under the motto 'Be happy or I'll kill you.'" We were sitting in an office a block from Rodeo Drive, on large black furniture leased with Japanese venture capital. Now that I'm actually here, the Disneyland metaphor is proving impossible to shake. For that matter, Rodeo Drive comes frequently to mind, though the local equivalent feels more like 30 or 40 Beverly Centers put end to end. Was it Laurie Anderson who said that VR would never look real until they learned how to put some dirt in it? Singapore's airport, the Changi Airtropolis, seemed to possess no more resolution than some early VPL world. There was no dirt whatsoever; no muss, no furred fractal edge to things. Outside, the organic, florid as ever in the tropics, had been gardened into brilliant green, and all-too-perfect examples of itself. Only the clouds were feathered with chaos—weird columnar structures towering above the Strait of China. The cab driver warned me about littering. He asked where I was from. He asked if it was clean there. "Singapore very clean city." One of those annoying Japanese-style mechanical bells cut in as he exceeded the speed limit, just to remind us both that he was doing it. There seemed to be golf courses on either side of the freeway … "You come for golf?" "No." "Business?" "Pleasure." He sucked his teeth. He had his doubts about that one. Singapore is a relentlessly G-rated experience, micromanaged by a state that has the look and feel of a very large corporation. If IBM had ever bothered to actually possess a physical country, that country might have had a lot in common with Singapore. There's a certain white-shirted constraint, an absolute humorlessness in the way Singapore Ltd. operates; conformity here is the prime directive, and the fuzzier brands of creativity are in extremely short supply. There is no slack in Singapore. Imagine an Asian version of Zurich operating as an offshore capsule at the foot of Malaysia; an affluent microcosm whose citizens inhabit something that feels like, well, Disneyland. Disneyland with the death penalty. But Disneyland wasn't built atop an equally peculiar 19th-century theme park—something constructed to meet both the romantic longings and purely mercantile needs of the British Empire. Modern Singapore was—bits of the Victorian construct, dressed in spanking-fresh paint, protrude at quaint angles from the white-flanked glitter of the neo-… metropolis. These few very deliberate fragments of historical texture serve as a reminder of just how deliciously odd an entrepot Singapore once was—a product of Empire kinkier even than Hong Kong. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The sensation of trying to connect psychically with the old Singapore is rather painful, as though Disneyland's New Orleans Square had been erected on the site of the actual French Quarter, obliterating it in the process but leaving in its place a glassy simulacrum. The facades of the remaining Victorian shop-houses recall Covent Garden on some impossibly bright London day. I took several solitary, jet-lagged walks at dawn, when a city's ghosts tend to be most visible, but there was very little to be seen of previous realities: Joss stick smouldering in an old brass holder on the white-painted column of a shop-house; a mirror positioned above the door of a supplier of electrical goods, set to snare and deflect the evil that travels in a straight line; a rusty trishaw, chained to a freshly painted iron railing. The physical past, here, has almost entirely vanished. The physical past here has almost entirely vanished. In 1811, when Temenggong, a local chief, arrived to resettle Singapura, the Lion City, with a hundred Malays, the jungle had long since reclaimed the ruins of a 14th-century city once warred over by Java, Siam, and the Chinese. A mere eight years later came Sir Stamford Raffles, stepping ashore amid a squirming tangle of kraits and river pirates, to declare the place a splendid spot on which to create, from the ground up, a British trading base. It was Raffles's singular vision to set out the various colonial jewels in Her Majesty's crown as distinct ethnic quarters: here Arab Street, here Tanjong Pagar (Chinese), here Serangoon Road (Indian). And Raffles's theme park boomed for 110 years—a free port, a Boy's Own fantasy out of Talbot Mundy, with every human spice of Asia set out on a neatly segmented tray of sturdy British china: "the Manchester of the East." A very hot ticket indeed. When the Japanese came and took it all, with dismaying ease, the British dream-time ended; the postwar years brought rapid decay, and equally rapid aspirations for independence. In 1965, Mr. Lee Kuan Yew, a Cambridge-educated lawyer, became the country's first prime minister. Today's Singapore is far more precisely the result of Lee Kuan Yew's vision than the Manchester of the East ever was of Sir Stamford Raffles's. Lee Kuan Yew's People's Action Party has remained in power ever since; has made, some would say, quite drastically certain that it would do so. The emblem of the PAP is a cartoony lightning bolt striking within a circle; Reddi Kilowatt as the mascot of what is, in effect, a single-party capitalist technocracy. Singapore: A government official, two private economists, and a newspaper editor will be tried jointly on June 21 for revealing an official Singaporean secret—its economic growth rate. Business Times editor Patrick Daniel, Monetary Authority of Singapore official Shanmugaratnam Tharman, and two economists for regional brokerage Crosby Securities, Manu Bhaskaran, and Raymond Foo Jong Chen, pleaded not guilty to violating Singapore's Official Secrets Act. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg South China Morning Post , 4/29/93 Reddi Kilowatt's Singapore looks like an infinitely more liveable version of convention-zone Atlanta, with every third building supplied with a festive party-hat by the designer of Loew's Chinese Theater. Rococo pagodas perch atop slippery-flanked megastructures concealing enough cubic footage of atria to make up a couple of good-sized Lagrangian-5 colonies. Along Orchard Road, the Fifth Avenue of Southeast Asia, chocka-block with multi-level shopping centers, a burgeoning middle class shops ceaselessly. Young, for the most part, and clad in computer-weathered cottons from the local Gap clone, they're a handsome populace; they look good in their shorts and Reeboks and Matsuda shades. There is less in the way of alternative, let alone dissident style in Singapore than in any city I have ever visited. I did once see two young Malayan men clad in basic, global, heavy metal black—jeans and T-shirts and waist-length hair. One's T-shirt was embroidered with the Rastafarian colors, causing me to think its owner must have balls the size of durian fruit, or else be flat-out suicidal, or possibly both. But they were it, really, for overt boho style. (I didn't see a single "bad" girl in Singapore. And I missed her.) A thorough scan of available tapes and CDs confirmed a pop diet of such profound middle-of-the-road blandness that one could easily imagine the stock had been vetted by Mormon missionaries. "You wouldn't have any Shonen Knife, would you?" "Sir, this is a music shop." Although you don't need Mormons making sure your pop is squeaky-clean when you have the Undesirable Propagation Unit (UPU), one of several bodies of official censors. (I can't say with any certainty that the UPU, specifically, censors Singapore's popular music, but I love the name.) These various entities attempt to ensure that red rags on the order of Cosmopolitan don't pollute the body politic. Bookstores in Singapore, consequently, are sad affairs, large busy places selling almost nothing I would ever want to buy—as though someone had managed to surgically neuter a W.H. Smith's. Surveying the science fiction and fantasy sections of these stores, I was vaguely pleased to see that none of my own works seemed to be available. I don't know for a fact that the UPU had turned them back at the border, but if they had, I'd certainly be in good company. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The local papers, including one curiously denatured tabloid, New Paper , are essentially organs of the state, instruments of only the most desirable propagation. This ceaseless boosterism, in the service of order, health, prosperity, and the Singaporean way, quickly induces a species of low-key Orwellian dread. (The feeling that Big Brother is coming at you from behind a happy face does nothing to alleviate this.) It would be possible, certainly, to live in Singapore and remain largely in touch with what was happening elsewhere. Only certain tonalities would be muted, or tuned out entirely, if possible. . . . Singaporean television is big on explaining Singaporeans to themselves. Model families, Chinese, Malay, or Indian, act out little playlets explicating the customs of each culture. The familial world implied in these shows is like Leave It To Beaver without The Beave, a sphere of idealized paternalism that can only remind Americans my age of America's most fulsome public sense of itself in the mid-1950s. "Gosh, dad, I'm really glad you took the time to explain the Feast of the Hungry Ghosts to us in such minutely comprehensive detail." "Look, son, here comes your mother with a nutritious low-cholesterol treat of fat-free lup cheong and skimmed coconut milk " And, in many ways, it really does seem like 1956 in Singapore; the war (or economic struggle, in this case) has apparently been won, an expanded middle class enjoys great prosperity, enormous public works have been successfully undertaken, even more ambitious projects are under way, and a deeply paternalistic government is prepared, at any cost, to hold at bay the triple threat of communism, pornography, and drugs. The only problem being, of course, that it isn't 1956 in the rest of world. Though that, one comes to suspect, is something that Singapore would prefer to view as our problem. (But I begin to wonder, late at night and in the privacy of my hotel room—what might the future prove to be, if this view should turn out to be right?) And, in many ways, it really does seem like 1956 in Singapore. Enormous public works have been successfully undertaken. A deeply paternalistic government is prepared, at any cost, to hold at bay the triple threat of communism, pornography, and drugs. The only problem being, of course, that it isn't 1956. Because Singapore is one happening place, biz-wise. I mean, the future here is so bright … What other country is preparing to clone itself, calving like some high-tech socioeconomic iceberg? Yes, here it is, the first modern city-state to fully take advantage of the concept of franchise operations Mini-Singapores! Many! In the coastal city of Longkou, Shandong province, China (just opposite Korea), Singaporean entrepreneurs are preparing to kick off the first of these, erecting improved port facilities and a power plant, as well as hotels, residential buildings, and, yes, shopping centers. The project, to occupy 1.3 square kilometers, reminds me of "Mr. Lee's Greater Hong Kong" in Neal Stephenson's Snow Crash , a sovereign nation set up like so many fried-noodle franchises along the feeder-routes of edge-city America. But Mr. Lee's Greater Singapore means very serious business, and the Chinese seem uniformly keen to get a franchise in their neighborhood, and pronto. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Ordinarily, confronted with a strange city, I'm inclined to look for the parts that have broken down and fallen apart, revealing the underlying social mechanisms; how the place is really wired beneath the lay of the land as presented by the Chamber of Commerce. This won't do in Singapore, because nothing is falling apart. Everything that's fallen apart has already been replaced with something new. (The word infrastructure takes on a new and claustrophobic resonance here; somehow it's all infrastructure.) Failing to find any wrong side of the tracks, one can usually rely on a study of the nightlife and the mechanisms of commercial sex to provide some entree to the local subconscious. Singapore, as might be expected, proved not at all big on the more intense forms of nightlife. Zouk, arguably the city's hippest dance club (modelled, I was told, after the rave scenes in Ibiza), is a pleasant enough place. It reminded me, on the night I looked in, of a large Barcelona disco, though somehow minus the party. Anyone seeking more raunchy action must cross the Causeway to Johore, where Singaporean businessmen are said to sometimes go to indulge in a little of the down and dirty. (But where else in the world today is the adjoining sleazy bordertown Islamic ?) One reads of clubs there having their licenses pulled for stocking private cubicles with hapless Filipinas, so I assumed that the Islamic Tijuana at the far end of the Causeway was in one of those symbiotic pressure-valve relationships with the island city-state, thereby serving a crucial psychic function that would very likely never be officially admitted. Singapore, meanwhile, has dealt with its own sex industry in two ways: by turning its traditional red-light district into a themed attraction in its own right, and by moving its massage parlors into the Beverly Centers. Bugis Street, once famous for its transvestite prostitutes—the sort of place where one could have imagined meeting Noel Coward, ripped on opium, cocaine, and the local tailoring, just off in his rickshaw for a night of high buggery—had, when it proved difficult to suppress, a subway station dropped on top of it. "Don't worry," the government said, "we'll put it all back, just the way it was, as soon as we have the subway in." Needless to say, the restored Bugis Street has all the sexual potential of "Frontierland," and the transvestites are represented primarily by a number of murals. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The heterosexual hand-job business has been treated rather differently, and one can only assume that it was seen to possess some genuine degree of importance in the national Confucian scheme of things. Most shopping centers currently offer at least one "health center"—establishments one could easily take for slick mini-spas, but which in fact exist exclusively to relieve the paying customer of nagging erections. That one of these might be located between a Reebok outlet and a Rolex dealer continues to strike me as evidence of some deliberate social policy, though I can't quite imagine what it might be. But there is remarkably little, in contemporary Singapore, that is not the result of deliberate and no doubt carefully deliberated social policy. Take dating. Concerned that a series of earlier campaigns to reduce the national birth rate had proven entirely too successful, Singapore has instituted a system of "mandatory mixers." I didn't find this particularly disturbing, under the circumstances, though I disliked the idea that refusal to participate is said to result in a "call" to one's employer. But there did seem to be a certain eugenic angle in effect, as mandatory dating for fast-track yuppies seemed to be handled by one government agency, while another dealt with the less educated. Though perhaps I misunderstood this, as Singaporeans seemed generally quite loathe to discuss these more intimate policies of government with a curious foreign visitor who was more than twice as tall as the average human, and who sweated slowly but continuously, like an aged cheese. Singapore is curiously, indeed gratifyingly devoid of certain aspects of creativity. I say gratifyingly because I soon found myself taking a rather desperate satisfaction in any evidence that such a very tightly-run ship would lack innovative elan. So, while I had to admit that the trains did indeed run on time, I was forced to take on some embarrassingly easy targets. Contemporary municipal sculpture is always fairly easy to make fun of, and this is abundantly true in Singapore. There was a pronounced tendency toward very large objects that resembled the sort of thing Mad magazine once drew to make us giggle at abstract art: ponderous lumps of bronze with equally ponderous holes through them. Though perhaps, like certain other apparently pointless features of the cityscape, these really served some arcane but highly specific geomantic function. Perhaps they were actually conduits for feng shui , and were only superficially intended to resemble Henry Moore as reconfigured by a team of Holiday Inn furniture designers. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But a more telling lack of creativity may have been evident in one of the city's two primal passions: shopping. Allowing for the usual variations in price range, the city's countless malls all sell essentially the same goods, with extraordinarily little attempt to vary their presentation. While this is generally true of malls elsewhere, and in fact is one of the reasons people everywhere flock to malls, a genuinely competitive retail culture will assure that the shopper periodically encounters either something new or something familiar in an unexpected context. Singapore's other primal passion is eating, and it really is fairly difficult to find any food in Singapore about which to complain. About the closest you could come would be the observation that it's all very traditional fare of one kind or another, but that hardly seems fair. If there's one thing you can live without in Singapore, it's a Wolfgang Puck pizza. The food in Singapore, particularly the endless variety of street snacks in the hawker centers, is something to write home about. If you hit the right three stalls in a row, you might decide these places are a wonder of the modern world. And all of it quite safe to eat, thanks to the thorough, not to say nitpickingly Singaporean auspices of the local hygiene inspectors, and who could fault that? (Credit, please, where credit is due.) If there's one thing you can live without in Singapore, it's a Wolfgang Puck pizza. But still. And after all. It's boring here. And somehow it's the same ennui that lies in wait in any theme park, put particularly in those that are somehow in too aggressively spiffy a state of repair. Everything painted so recently that it positively creaks with niceness, and even the odd rare police car sliding past starts to look like something out of a Chuck E. Cheese franchise … And you come to suspect that the reason you see so few actual police is that people here all have, to quote William Burroughs, "the policeman inside." And what will it be like when these folks, as they so manifestly intend to do, bring themselves online as the Intelligent Island, a single giant data- node whose computational architecture is more than a match for their Swiss-watch infrastructure? While there's no doubt that this is the current national project, one can't help but wonder how they plan to handle all that stuff without actually getting any on them? How will a society founded on parental (well, paternal, mainly) guidance cope with the wilds of X- rated cyberspace? Or would they simply find ways not to have to? What if, while information elsewhere might be said to want to be free, the average Singaporean might be said to want, mainly, not to rock the boat? And to do very nicely, thank you, by not doing so? Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Are the faceless functionaries who keep Shonen Knife and Cosmo anti-feminism out of straying local hands going to allow access to the geography-smashing highways and byways of whatever the Internet is becoming? More important, will denial of such access, in the coming century, be considered even a remotely viable possibility by even the dumbest of policemen? Hard to say. And therein, perhaps, lies Singapore's real importance. The overt goal of the national IT2000 initiative is a simple one: to sustain indefinitely, for a population of 2.8 million, annual increases in productivity of three to four percent. IT, of course, is "information technology," and we can all be suitably impressed with Singapore's evident willingness to view such technology with the utmost seriousness. In terms of applied tech, they seem to have an awfully practical handle on what this stuff can do. The National Computer Board has designed an immigration system capable of checking foreign passports in 30 seconds, resident passports in fifteen. Singapore's streets are planted with sensor loops to register real-time traffic; the traffic lights are computer controlled, and the system adjusts itself constantly to optimize the situation, creating "green waves" whenever possible. A different sort of green wave will appear if a building's fire sensor calls for help; emergency vehicles are automatically green-lighted through to the source of the alarm. The physical operation of the city's port, constant and quite unthinkably complex, is managed by another system. A "smart-card" system is planned to manage billings for cars entering the Restricted Zone. (The Restricted Zone is that part of central Singapore which costs you something to enter with a private vehicle. Though I suspect that if, say, Portland were to try this, the signs would announce the "Clean Air Zone," or something similar.) They're good at this stuff. Really good. But now they propose to become something else as well; a coherent city of information, its architecture planned from the ground up. And they expect that whole highways of data will flow into and through their city. Yet they also seem to expect that this won't affect them. And that baffles us, and perhaps it baffles the Singaporeans that it does. Myself, I'm inclined to think that if they prove to be right, what will really be proven will be something very sad; and not about Singapore, but about our species. They will have proven it possible to flourish through the active repression of free expression. They will have proven that information does not necessarily want to be free. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But perhaps I'm overly pessimistic here. I often am; it goes with the territory. (Though what could be more frightening, out here at the deep end of the 20th century, than a genuinely optimistic science fiction writer?) Perhaps Singapore's destiny will be to become nothing more than a smug, neo-Swiss enclave of order and prosperity, amid a sea of unthinkable … weirdness. Dear God. What a fate. Fully enough to send one lunging up from one's armchair in the atrium lounge of the Meridien Singapore, calling for a taxi to the fractal-free corridors of the Airtropolis. But I wasn't finished, quite. There'd be another night to brood about the Dutchman. I haven't told you about the Dutchman yet. It looks like they're going to hang him. A Malayan man was yesterday sentenced to death by the High Court for importing not less than 1 kg of cannabis into Singapore more than two years ago. Mat Repin Mamat, 39, was found guilty of the offense committed at the Woodlands checkpoint on October 9, 1991, after a five-day trial. The hearing had two interpreters. One interpreted English to Malay while the other interpreted Malay to Kelantanese to Mat Repin, who is from Kelantan. The prosecution's case was that when Mat Repin arrived at the checkpoint and was asked whether he had any cigarettes to declare, his reply was no. As he appeared nervous, the senior customs officer decided to check the scooter. Questioned further if he was carrying any "barang" (thing), Mat Repin replied that he had a kilogram of "ganja" (cannabis) under the petrol tank. In his defense, he said that he did not know that the cannabis was hidden there. The Straits Times 4/24/93 The day they sentenced Mat Repin, the Dutchman was also up on trial. Johannes Van Damme, an engineer, had been discovered in custody of a false-bottomed suitcase containing way mucho barang: 4.32 kilograms of heroin, checked through from Bangkok to Athens. The prosecution made its case that Van Damme was a mule; that he'd agreed to transport the suitcase to Athens for a payment of US$20,000. Sniffed out by Changi smackhounds, the suitcase was pulled from the belt, and Van Damme from the transit lounge, where he may well have been watching Beaver's dad explain the Feast of the Hungry Ghosts on a wall-mounted Sony. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The defense told a different story, though it generally made about as much sense as Mat Repin's. Van Damme had gone to Bangkok to buy a wedding ring for his daughter, and had met a Nigerian who'd asked him, please, to take a suitcase through to Athens. "One would conclude," the lawyer for the defense had said, "that either he was a nave person or one who can easily be made use of." Or, hell, both. I took this to be something akin to a plea for mercy. Johannes Van Damme, in the newspaper picture, looks as thick as two bricks. I can't tell you whether he's guilty or not, and I wouldn't want to have to, but I can definitely tell you that I have my doubts about whether Singapore should hang him, by the neck, until dead—even if he actually was involved in a scheme to shift several kilos of heroin from some backroom in Bangkok to the junkies of the Plaka. It hasn't, after all, a whole hell of a lot to do with Singapore. But remember "Zero Tolerance?" These guys have it. And, very next day, they announced Johannes Van Damme's death sentence. He still has at least one line of appeal, and he is still, the paper notes, "the first Caucasian" to find his ass in this particular sling. "My ass," I said to the mirror, "is out of here." Put on a white shirt laundered so perfectly the cuffs could slit your wrists. Brushed my teeth, ran a last-minute check on the luggage, forgot to take the minibar's tinned Australian Singapore Sling home for my wife. Made it to the lobby and checked out in record time. I'd booked a cab for 4 AM, even though that gave me two hours at Changi. The driver was asleep, but he woke up fast, insanely voluble, the only person in Singapore who didn't speak much English. He ran every red light between there and Changi, giggling. “Too early policeman ….” They were there at Changi, though, toting those big-ticket Austrian machine pistols that look like khaki plastic waterguns. And I must've been starting to lose it, because I saw a crumpled piece of paper on the spotless floor and started snapping pictures of it. They really didn't like that. They gave me a stern look when they came over to pick it up and carry it away. So I avoided eye contact, straightened my tie, and assumed the position that would eventually get me on the Cathay Pacific's flight to Hong Kong. In Hong Kong I'd seen huge matte black butterflies flapping around the customs hall, nobody paying them the least attention. I'd caught a glimpse of the Walled City of Kowloon, too. Maybe I could catch another, before the future comes to tear it down. Traditionally the home of pork-butchers, unlicensed denturists, and dealers in heroin, the Walled City still stands at the foot of a runway, awaiting demolition. Some kind of profound embarrassment to modern China, its clearance has long been made a condition of the looming change of hands. Hive of dream. Those mismatched, uncalculated windows. How they seemed to absorb all the frantic activity of Kai Tak airport, sucking in energy like a black hole. I was ready for something like that … I loosened my tie, clearing Singapore airspace. William Gibson's Neuromancer made cyberpunk a household world. His new novel, virtual light, was just published. “Disneyland” is his first major piece of nonfiction. You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer. Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Topics Backchannel WIRED Classic longreads magazine-1.04 China Brandi Collins-Dexter Angela Watercutter Lauren Smiley Andy Greenberg Steven Levy Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Citizen Isn't Here to Be Your Free-Speech Platform | WIRED"

"https://www.wired.com/story/plaintext-citizen-isnt-here-to-be-your-free-speech-platform"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Steven Levy Business Citizen Isn't Here to Be Your Free-Speech Platform As nearby parts of New York City became hot spots for protests, Citizen pinpointed the locations of incidents and emergencies. Photograph: Sergi Reboredo/Universal Images Group/Getty Images Save this story Save Save this story Save Welcome to the summer of 2020, where hot dogs, beach balls, and road trips are joined by protests, oximeters, and arguments about section 230(c). And, every week, your Plaintext newsletter. I have become a Citizen addict. Citizen is an app, currently active in 18 cities, that’s sort of a supercharged police scanner—its home screen is a map of the area around your location that pinpoints disturbances. These include user-contributed videos of fires, police activity, and lately, major protests. Since my New York City neighborhood has become a hot spot for social upheaval in recent weeks, the baseline of nearby incidents and emergencies has dramatically elevated, and the distance to various conflagrations and marches is often reported not in miles but feet. Accompanied by the unrelenting soundtrack of overhead helicopters, my use of Citizen has been both inspiring (the uprising is long overdue!) and alarming (already fragile Covid-affected businesses in my neighborhood have been hit hard by vandalism and looting). Citizen’s founder and CEO is Andrew Frame, a hacker turned entrepreneur who was behind the VoIP app Ooma. “The original foundation for Citizen was really ‘What does the future of public safety look like?’” he tells me, while heading to the airport for his first plane trip since the virus hit. “Step one is opening up the 911 system. So, it's a shared system, and everybody has access to the same information in real time.” Frame says that in recent weeks, hundreds of thousands of new users have flocked to the app. (Though Frame wouldn’t share actual numbers, he didn’t dispute a recent report in Forbes that estimated 600,000 new users, for a total of around 5 million overall.) Once people get that information, he says, it’s up to them to figure out what to do with it—whether to rush out and document an incident, join a protest, or cower in their apartments. (In some cases, he says, people have left their apartments after learning through Citizen that the building was on fire.) “We try to stay as neutral as possible politically—we create the transparency,” he says. But as other platforms have learned, staying neutral is a difficult balance to strike when your decidedly nonneutral users express themselves within the app. Each incident reported on Citizen invites comments, and in our politically fractured environment, these often break out into political discussion. That’s fine, but not when commenters complain about the protests with hate speech and racism, and I’ve been taken aback at some of the intolerance displayed by my supposedly liberal NYC neighbors, including some comments expressing unbridled venom towards people of color. App store reviewers have noted it too—a recent user talked of deleting the app, because “there’s a ton of racist comments.” Frame says that hate speech is definitely against policy, admitting that in the recent surge of new users, the company’s content moderators might have been temporarily overwhelmed. “This is not built as a free-speech platform—there are plenty of platforms where you can go and share your opinions and argue with people.” In contrast to big platforms like Facebook and YouTube, he says, Citizen’s moderators are full-time employees. I suggest hiring more. Citizen has long been discreet about its business plan, though Frame hints that he will soon reveal a clear monetization scheme. He vows that it will not hinge on selling or exploiting the data of his users. As for other future plans, he says that Citizen will broadly interpret its mission of safety through transparency. “Since the mission is safety, it gives us license to do things like Covid and contagious diseases. Anything we can do by using technology to keep our user base safe.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Safe, maybe, but not necessarily reassured, as I can attest, based on my late-night swipes through Citizen. “There’s two things that make people nervous,” says Frame. “Number one, not knowing what's going on. And number two, knowing what's going on.” Citizen would not be possible without the digital-geo revolution, which transformed paper maps into the dynamic tools that power many of our best apps. Sixteen years ago, I wrote about the emergence of digital maps in Newsweek : Just over the azimuth is the holy grail of mapping, where every imaginable form of location-based information is layered onto an aggregate construct that mirrors the whole world. "I call it the Virtual Globe," says Jack Dangermond, founder of Environmental Systems Research Institute (ESRI), a Redlands, Calif., company that pioneered what's known as Geographical Information Systems. "It combines the World Wide Web with geographical information like satellite images, roads, demographic information, sensors … and then you're modeling the planet as a living system" … Think of these supermaps as the equivalent of Web browsers yielding the world's knowledge through the lens of location. They'll spur companies and governments to make better-informed decisions and enrich the experience of just plain people as they take a walk through the city, hook up with their friends and hunt for Chinese food. These will be maps that change the territory. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Michael asks, “Do you think we'll be able to enjoy self-driving cars in our lifetime?” That’s a matter for the actuarial tables, Michael. I assume you are talking about Level 5 autonomy, when cars don’t need us and the steering wheel goes the way of the phone dial. Some of the lower levels, which include a lot of the tasks of driving—steering, braking, navigating, and singing “Bohemian Rhapsody” really loud—are already here, assuming your car has Spotify. Within a few years, most new cars will have options that allow them to do most of that work. But I realized a few years ago, when working on a story on what is now Waymo’s test-driving training, that there are endless scenarios in motoring that AI has difficulty with. It’s kind of a Zeno’s paradox thing—engineers can whittle down those situations, but a percentage still always seems to remain. At some point those will become so rare that we’ll just declare victory and say we’re at Level 5 with an asterisk, and the car you buy will drive off the lot by itself. If you’re alive in 10 or 15 years—certainly 20—you may be one of those buyers who meets the car when it shows up sans driver. So keep washing your hands. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg You can submit questions to [email protected]. Write ASK LEVY in the subject line. For those worried about the apocalypse, at least we had the comfort of knowing that the ancient Mayans were wrong in pinpointing the world’s end to December 21, 2012. Now it turns out that they simply made an error i n calculating the calendar date—it’s this year , folks! So don’t bother with Christmas shopping. Citizen is far from alone in dealing with racist content: Kate Knibbs analyzes HBO’s removal of Gone With The Wind from its new service. Elon Musk completists should not miss this profile of sister Tosca as she innovates in the romance space. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg And don’t forget that the other Musk sibling, Kimbal, would take charge of Tesla and SpaceX if Elon went to Mars. Here’s my report from spending three days in Memphis with him in 2015. While you wait for the Covid vaccine, read about the first-ever inoculation against a disease. Don't miss future subscriber-only editions of this column. Subscribe to WIRED (50% off for Plaintext readers) today. Who discovered the first vaccine ? How to protest safely: What to do and what to avoid As health care moves online, patients are getting left behind Walmart employees are out to show its anti-theft AI doesn't work The confessions of Marcus Hutchins, the hacker who saved the internet 👁 Is the brain a useful model for AI ? Plus: Get the latest AI news 🏃🏽‍♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones Editor at Large X Topics Plaintext protests platforms free speech Reece Rogers Reece Rogers Reece Rogers Will Knight Steven Levy Aarian Marshall Paresh Dave Aarian Marshall Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Mark Zuckerberg Believes Only in Mark Zuckerberg | WIRED"

"https://www.wired.com/story/mark-zuckerberg-believes-only-in-mark-zuckerberg"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Siva Vaidhyanathan Ideas Mark Zuckerberg Believes Only in Mark Zuckerberg Zuckerberg believes in himself so completely, his vision of how the world works so completely, that he is immune to cognitive dissonance. Photograph: Abdulhamid Hosbas/Getty Images Save this story Save Save this story Save What does Mark Zuckerberg believe? What does he really care about? How could a man who marched in a gay pride parade , who advocated for increased immigration to the United States, who hired a high-profile Democrat and feminist as his second-in-command, sit and eat with Donald Trump ? Why, at a moment of global and national crisis, when more than 100,000 Americans have died of a virus that could have been contained by a competent government, a quarter of Americans are in danger of being evicted or thrown into poverty, and thousands of Americans are facing off against violent police forces in the streets of cities and towns of all sizes, does Zuckerberg get on the phone with Trump for a nice chat ? Like other billionaires , Zuckerberg has the money, power, and influence to take a stand against such malfeasance and malevolence. With three global platforms—Facebook, Instagram, and WhatsApp—capable of structuring the cultural and intellectual experience of billions around the world, Zuckerberg chooses to do the opposite. He chooses to bolster Trump and other authoritarians, despite all the harm they do to the world. Zuckerberg knew in 2016 that Trump was a racist. He knew that Trump boasted of sexually assaulting women. Yet Zuckerberg allowed Facebook employees to help Trump use Facebook more effectively , certainly contributing to the electoral college win. How could a person who seems so cosmopolitan let his company effectively support the campaigns of authoritarian nationalists like Narendra Modi in India or Rodrigo Duterte in the Philippines? Why does he let them use his platforms to terrorize critics, journalists, and scholars? Over the past two weeks these questions have taken on a new urgency as Facebook employees have for the first time publicly voiced anger and frustration with Zuckerberg’s decision to protect Trump’s calls for state violence against those who are protesting racist police violence. While Twitter took a modest stand against Trump’s hyperbolic threats, Zuckerberg announced that he sees the posts as different from those that threaten violence because they were about the use of “state force. ” Seriously. In a leaked staff phone call on Tuesday, Zuckerberg defended his decision to angry Facebook staffers. “We basically concluded after the research and after everything I’ve read and all the different folks that I’ve talked to that the reference is clearly to aggressive policing—maybe excessive policing—but it has no history of being read as a dog whistle for vigilante supporters to take justice into their own hands,” Zuckerberg said of Trump’s posts that taunted protesters with, “when the looting starts, the shooting starts.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg And after some civil rights leaders spoke with Zuckerberg on Monday they left “disappointed and stunned,” convinced that Zuckerberg does not—or refuses to—understand basic issues like voter suppression and racism. Now, as the United States faces its greatest threat since the Civil War, Zuckerberg panders to the authoritarian in the White House. You have to ask yourself why. "It's about the money" does not quite track. He would have all that money regardless. Zuckerberg and Facebook are deeply embedded in the global economy and power structure. He does not need Trump. Trump has no direct or immediate power to regulate Facebook or constrict its actions in the short term. Perhaps Zuckerberg is hedging, assuming that Trump and the Republicans will go easier on him if they prevail in November. Zuckerberg already has purchased the support of some powerful Democrats , so he doesn’t have to work so hard to keep them at bay. So what does Zuckerberg really believe? What does he really want for the world? These are questions that for years have been perplexing those of us who write about Facebook. After going through hundreds of speeches, letters, and Facebook posts by Zuckerberg during the research for my latest book , I thought I had him nailed down. I considered Zuckerberg an idealist, someone who naively believed in the positive power of human connectivity, communication, and community. Being largely uneducated and inexperienced, Zuckerberg was untroubled by facts, history, or complexity. Connectivity was just good—always and completely. Never having grown beyond the bubbles of prep school, Harvard, Silicon Valley, and Davos, Zuckerberg had no grasp of the varieties of human cruelty, I thought. Being a straight, white, American man, Zuckerberg was oblivious to the ways in which “community” could oppress as well as comfort. And after years of rich white men throwing money at him and calling him a genius, Zuckerberg, I assumed, was just enthralled by rich white men. Despite, as Steven Levy describes in detail in his essential new book on Facebook , relinquishing much control of day-to-day and commercial operations of Facebook to COO Sheryl Sandberg for much of the past decade, Zuckerberg still embedded his values into the company. He did so imperfectly, though. Despite his claims to support free expression, Facebook has notoriously and enthusiastically executed the censorious wishes of authoritarian governments around the world. So I expected that Zuckerberg was experiencing cognitive dissonance while watching his dear company be exploited to empower genocidal forces in Myanmar , religious terrorists in Sri Lanka , or vaccine deniers around the world. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg I was wrong. I misjudged Zuckerberg. Another thing I learned from Levy’s book is that along with an idealistic and naive account of human communication, Zuckerberg seems to love power more than he loves money or the potential to do good in the world. Having studied just enough Latin in prep school to get him in trouble, Zuckerberg was known to quote Cato, shouting “Carthago delenda est” (Carthage must be destroyed) when referring to Google. Emperor Augustus was a particular inspiration, Levy reports, and Zuckerberg named his child after Augustus, the adopted son of the tyrant Julius Caesar who ruled over the greatest and most peaceful span of the Roman Empire as its first emperor. It was not Zuckerberg suffering from cognitive dissonance. I was. As I watched him cooly face questions from congressional representatives about the Cambridge Analytica debacle , he never seemed thoughtful, just disciplined. That Facebook could serve people well—and it does—and that it could be abused to contribute to massive harm, pain, and death, didn’t seem to generate that one troublesome phenomenon that challenges the thoughtful: Contradiction. Zuckerberg continued and continues to believe in the positive power of Facebook, but that’s because he believes in the raw power of Facebook. “Domination!,” he used to yell at staff meetings, indicating that everything is a game. Games can be won. He must win. If a few million bones get broken along the way, his game plan would still serve the greatest good for the greatest number. He believes in himself so completely, his vision of how the world works so completely, that he is immune to cognitive dissonance. He is immune to new evidence or argument. It turns out megalomaniacs don’t suffer from cognitive dissonance. Zuckerberg continued and continues to believe in the positive power of Facebook, but that’s because he believes in the raw power of Facebook. Considered this way, one might see how Zuckerberg and Trump might get along. Trump, as well, sees life as a series of competitions that he must win, even if that means he has to cheat. Not only must Trump convince himself he won ( even when he loses ), he must convince himself that he dominated his opponent ( even when he failed to ). There are more differences between Trump and Zuckerberg than similarities, of course. Zuckerberg actually wins most of the games he plays. The younger man has legitimate intelligence and prowess, demonstrable success, and earns far more money in one year than Trump has lost in his entire life. Zuckerberg is a dominator and an idealist. He’s an idealist about himself and his vision for how the rest of us must live. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Like the notorious architect Philip Johnson, Mark Zuckerberg is a social engineer. He knows what’s best for us. And he believes that what’s best for Facebook is best for us. In the long run, he believes, Facebook’s domination will redeem him by making our lives better. We just have to surrender and let it all work out. Zuckerberg can entertain local magistrates like Trump because Zuckerberg remains emperor. The only hope we have to depose this emperor is that his troops might rebel and refuse to do his bidding. That might be starting to happen. But it might be far too late. A virtual DJ, a drone, and an all-out Zoom wedding Remote work has its perks, until you want a promotion All the tools and tips you need to make bread at home The confessions of Marcus Hutchins, the hacker who saved the internet On the moon, astronaut pee will be a hot commodity 👁 Is the brain a useful model for AI ? Plus: Get the latest AI news 🏃🏽‍♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones Topics protests Mark Zuckerberg Facebook Meghan O'Gieblyn Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"For Nextdoor, Eliminating Racism Is No Quick Fix | WIRED"

"https://www.wired.com/2017/02/for-nextdoor-eliminating-racism-is-no-quick-fix"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Jessi Hempel Backchannel For Nextdoor, Eliminating Racism Is No Quick Fix Li-Anne Dias Save this story Save Save this story Save Nirav Tolia was sitting down to lunch at a Los Angeles sushi bar when the article dropped. A trim Indian American with a photogenic face and perennially crisp shirts, Tolia, 45, is the cofounder and CEO of the social media site Nextdoor. He’d just finished taping an episode of Dr. Phil—classic Nextdoor press. The segment was about a family whose teenage son was a kleptomaniac. He’d been taking things from the neighbors. At the end of the show, Dr. Phil recommended Nextdoor as a tool that could help the neighbors communicate if, say, a garden hose went missing. These were the kinds of stories Tolia was used to doing: feel-good pieces about the feel-good things that happen on Nextdoor, a site that more than 10 million people use in three quarters of US cities and towns to connect with their neighborhood. A woman has too many tomatoes in her garden, so she’s left them on the porch for people to collect. A man is moving and he has a taupe couch to sell. The parents down the block have a great recommendation for a babysitter. [#image: /photos/5947e0146c638b3847cde2a7]|||||| Jessi Hempel is Backchannel's editorial director. --------- Sign up to get Backchannel's weekly newsletter. But the story that dropped that evening in March 2015, published by Fusion was not Nextdoor’s typical press. It was a feel-bad story. Tolia was dining with his communications director, Kelsey Grady, when her iPhone alerted them to the story’s publication. They read the lengthy feature together. It alleged that white Oakland residents were using the “crime and safety” category of Nextdoor to report suspicious activity about their black neighbors. “Rather than bridging gaps between neighbors, Nextdoor can become a forum for paranoid racialism — the equivalent of the nosy Neighborhood Watch appointee in a gated community,” wrote Pendarvis Harshaw. Caught off guard, Tolia asked his neighborhood operations team, which handles customer service, to review Nextdoor postings. They discovered several dozen messages posted over the course of the previous year that identified suspicious characters only by race. By some measures, it was a tiny issue. The site distributes four million messages daily. But there’s no such thing as a “small” racism problem when the promise of your service is that it allows people to trust their neighbors. “If there’s something that drives communities apart, it just overturns the whole premise,” Tolia tells me. “People will feel like, ‘Oh, [Nextdoor,] that’s that place where people are racist.’” In the last couple years, as the largest social networking sites have come of age, many of them have also become platforms for racial bias. It’s not surprising. Most social web services — like Airbnb or Facebook or Twitter — were launched quickly. Their founding teams—consisting mostly of well-off men (and the occasional woman) from prestigious universities—were not diverse. Those teams hired designers and engineers who looked like them to launch and grow the sites. These companies weren’t thinking about the way bias would influence how people use their services; they were moving fast and breaking things, content to fill in the details later. What’s more, they mostly built advertising businesses that became more successful as people provided them more social data by posting more on the sites. There was little business incentive for them to slow their users down and ask them to think about why and how they were posting—and, in some cases, to post less. "People will feel like, ‘Oh, Nextdoor, that’s that place where people are racist.’” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg In many ways, that approach was successful beyond measure. In less than a decade these services have exploded into the mainstream, replacing brick and mortar stores with more efficient and delightful web versions. It was only after the fact that a major shortcoming began to reveal itself: With many of these services, minorities of all types were targeted or excluded. The problem with technology that allows us to target exactly who we want is that it allows us to target exactly who we want. In other words, the problem with technology is us. For too long, these companies took little or no responsibility, claiming they were just platforms on which behavior — both bad and good — unfolded. Twitter failed to get ahead of its abuse problem. Airbnb has yet to figure out how to stop hosts definitively from refusing African-American guests. Last week, Facebook began to stop some advertisers from keeping certain races from seeing their ads — but outside ads for housing, employment, or credit, that practice is still fair game. This is, point blank, a major failing of the Web 2.0 era. Nevertheless, here we are in 2017, confronted with a host of services that serve some people better than others. These companies are learning the hard way that there is no silver bullet for eliminating racial bias, and no quick web fix for calling out bad behavior. Nextdoor has tried to eliminate racial bias on the site the same way it built its product: through smart product design. It is having some success — Tolia says the site has cut racial profiling in its crime and safety category by 75 percent. But this story is not yet finished. Tolia and his cofounder, early Microsoft veteran Sarah Leary, never intended for Nextdoor to grow into the new neighborhood watch. Both serial entrepreneurs, they’d founded the company in 2010 after a previous startup failed. Facebook had just emerged into the mainstream, acquainting us with the idea of using our real identities to connect to people we knew. They figured Nextdoor could be a next-gen Craigslist, helping us to use those same identities to connect to our neighbors—often people we didn’t really know. The site took off from the start, and has grown into a $1.1 billion company connecting people in 130,000 neighborhoods around the world. More From Home Week Uncategorized Steven Levy Uncategorized Lauren Bohn Uncategorized Kristen French Uncategorized Justin Peters As with many social services, founders launch with the intention of doing one thing, and quickly discover that users want to do something else. From the start, people turned to Nextdoor to discuss crime and safety concerns in the neighborhood, and that part of the site took off. So, by the fall of 2015, roughly one in five Oakland households used Nextdoor, and three Oakland city agencies were using the site to send out public service announcements. About a fifth of the conversations that happened in Oakland’s Nextdoor networks involved crime. To address racial profiling in these conversations, Nextdoor first needed to understand how and where it was happening. So Tolia and Leary assembled a small team of senior people, which included Grady as well as a product manager, a designer, a data scientist, and later an engineer. Its lead was Maryam Mohit, who is director of product at Nextdoor. At 49, with a mop of curly hair and a considered approach to her speech, Mohit was a varsity techie. She’d gotten her start at Amazon, where she was on the team of people who had created the one-click patent. Mohit believed the issue could be addressed through smart product design. Every day, she’d bring home reams of postings. She read them late at night. She sifted through batches of them on Saturday mornings in her bathrobe and slippers, before she heard the patter of her children’s feet in the hallway. “I must’ve read thousands of anonymized posts to see what was actually happening,” she says. “It felt urgent.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg By the late fall of 2015, Nextdoor had landed on its initial three-part fix. First off, it put the entire neighborhood operations team through a diversity training workshop so that its members could better recognize the problem. Second, it updated the company’s community guidelines, and reintroduced them to its users through a blog post. Both moves were well received by people in the Nextdoor community. The third part of their solution flopped. Already, Nextdoor allowed people to flag inappropriate posts. Its members often used the system to flag commercial posts, for example, when they were posted in noncommercial areas of the site. They added a “racial profiling” category, inviting users to report the behavior if they saw it. The problem was that many people didn’t understand what it was, and Nextdoor members began reporting all kinds of unrelated slights as racial profiling. “Somebody reported her neighbor for writing mean things about pit bulls,” Mohit recalls. The team realized it needed to help users understand when to use race when talking about suspicious or criminal activity. And to do that, they needed to define — very specifically — what constituted racial profiling in the first place. “We could not find a definition of racial profiling that everyone agreed on,” says Tolia. “If you go to the NAACP, if you go to the ACLU, if you go to the White House Task Force on Diversity, if you go to the Neighbors for Racial Justice, none of these people agree on what racial profiling is.” Meanwhile, the press attention was escalating. Nextdoor members began reporting actual racial profiling more frequently, especially in several communities in California and Texas. Oakland city officials were concerned the fix wasn’t enough, and they threatened to remove the three Oakland agencies that used it to distribute information. “You rely quite heavily on your relationships with cities. It is a part of your marketing strategy to do this,” said Council Member Desley Brooks, speaking to Nextdoor’s team in front of a public audience at an Oakland city council meeting in early 2016. “If we come off, it is a bold statement that a city is not going to condone racial profiling at all. What is Nextdoor going to do to make sure that if the City of Oakland continues to use this as a tool, all of our residents are protected?” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Nextdoor counted on public agencies to use its platform; it was one of the things Nextdoor members had come to expect from the site. Now it was more than just a moral issue. The health of the business was at stake. In late October, Tolia, Mohit, Grady, and the head of neighborhood operations, Gordon Strause, rode BART across the Bay to the 19th Street stop in downtown Oakland. Nearby, at an airy brick-walled coworking spot called Impact Hub Oakland, they met with five members of the activist group Neighbors for Racial Justice. “We were a bit nervous because we knew they were frustrated,” Grady remembers. Nextdoor had learned about the group through an article in the local alternative weekly, the East Bay Express , and reached out to meet. The activists were wary. They were anxious to share the ideas they’d developed to help Nextdoor improve its product, but they believed Nextdoor was caving to pressure from the press and city officials, rather than authentically trying to tackle the issue. “They were completely placating us,” says Neighbors for Racial Justice leader Shikira Porter. The conversations that happened over the weeks that followed were tough for everyone involved. Some of the activists felt that Nextdoor was paying them lip service. Some Oakland council members were concerned that their agencies should not be distributing public information on a platform that condoned any racial profiling at all. Everyone — even Tolia — agreed that Nextdoor wasn’t moving fast enough. “This is urgent,” Council Member Brooks told the Nextdoor team at one heated January meeting. The Nextdoor group became very familiar with BART. They traveled to Oakland to meet with council members and law enforcement officials. They spoke with representatives of the Oakland chapter of One Hundred Black Men. They began holding regular working groups in which they included these people in the product development process. Of course, this issue was not limited to Oakland, and the team also began seeking information from national organizations. They reached out to experts in all types of institutions that had figured out how to work with people reporting crimes or emergencies. They talked to 911 operators to learn the order in which operators asked questions of people so that they could get information that would be most helpful in emergencies. They spoke to police officers to learn their process for taking reports when they investigated crimes. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg They also studied the work of Jennifer Eberhardt, a Stanford academic who won a MacArthur Genius Award for her research on unconscious racial bias. Eberhardt consults with police departments on bias and racial justice, helping them incorporate her theoretical work into their day-to-day interactions. “The basis of her research is around something she calls decision points,” says Tolia. “If you make people stop and think before they act, they probably won’t do the racist things that they do.” In early 2016, the Nextdoor group set out to add decision points to steps of posting in the site’s crime and safety section. The point was to add friction to the process—to make users stop and think just enough to be purposeful in their actions, without making Nextdoor so laborious to use that it drove them away. This is tricky territory for a social media company. Most of them, including Nextdoor, make their money off the data users input, either by advertising or selling that data to other companies. Therefore, most companies are incentivized to make it ever easier for people to post, and to encourage them to post more. Open Snapchat, for example, and you get a camera, ready to snap and post. Pull up Facebook, and the box at the top of the screen asks, “What’s on your mind?” If a company makes it harder for people to post, they’ll post less, and that will have a negative impact on the bottom line. But there are times when a bit of friction can be useful. Take LinkedIn, which asks people at signup, “Where else did you work?” The company understood, starting from its earliest days, that nudging users to have a more complete profile at the start would make the service more valuable to them over time. Mohit’s team gathered daily in whatever conference room they could find — space was tight — to riff around the whiteboard on ideas for how to take users through a process before they posted. As they worked, they checked in with community groups through in-person working sessions and on Google Hangouts. They developed six different variants. For example, if you show people an interstitial defining racial bias before they post, does it change the way they post? If you force people to describe a person, how many attributes do you need for it to feel like a full and fair description—not one solely based on race? Then they A/B tested the variances for three months, assigning five people to read through thousands of resulting posts. By last August, they’d arrived at a new posting protocol for the crime and safety section. They rolled it out across the site. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Not long ago, Tolia invited me by to show me the result of Nextdoor’s work. It was a busy day, and there was a buzz in the air that felt like the tangible expression of the Silicon Valley term “blitzscale.” Having recently outgrown its offices, Nextdoor has just moved into the building behind Twitter’s headquarters on Market Street. Earlier in the week, it had acquired a United Kingdom competitor, and all employees—including Mohit—had dropped everything to help transition new members to the Nextdoor platform. Tolia slid his laptop around the table and flipped it open to walk me through the new posting process. Today, when you post to the crime and safety section of the site, you must choose whether your post describes a crime, suspicious activity, or the rather ambiguous “other” category. If it’s a crime, you are prompted to describe the incident and to check a box indicating whether you’ve already reported it to the police. If you refer to race in your description of the incident, Nextdoor’s algorithms detect it and prompt you to save this part of the description for the next screen. On the second screen, you’re encouraged to describe vehicles as well as people. “Cars aren’t stereotyped. You’re like, ‘Oh that’s a BMW. That’s a Mercedes,’” says Tolia. If you choose to describe a person, you’re given a series of fields to fill in. If you choose to fill in race, you are required to fill in two of four additional categories — hair, top clothing, bottom clothing, and shoes. If you don’t fill in the requested fields, you can’t post. If, instead of reporting a crime, you are reporting a suspicious activity, you are shown instructions for what constitutes suspicious activity before you are directed through a similar posting process. These extra steps have caused people to post less to this section of the site. Tolia says there are about 25 percent fewer posts. But, he points out, many of those posts shouldn’t have been on the site in the first place. “This is where you make the long-term bet where you have to feel that the content you’re eliminating is not high value,” says Tolia. “The content you’re getting at the end is higher value.” Last fall, the City of Oakland honored Nextdoor for the work that it did to address the racial profiling on the site. Chuck Baker, a board member with the Bay Area chapter of One Hundred Black Men, had participated in Nextdoor’s working groups, and he felt the award was well deserved. “We were pretty happy,” he says. “We were excited they were really talking about this.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Not everyone feels that way. Neighbors for Racial Justice believes that Nextdoor isn’t doing enough. From a technical perspective, they’re right—both Mohit and Tolia tell me this. For one, although a significant number of members use the service on their phones, Nextdoor hasn’t fully rolled out similar measures to prevent people from describing potential miscreants only by race in its iOS and Android apps yet. (The company says it has completed a design.) Also, much of the discussion that occurs in the crime and safety category doesn’t happen in the company’s carefully calibrated posts — it takes place in the comments that respond to those posts. Nextdoor hasn’t yet found a way to monitor those conversation threads for racial profiling. “We need to figure out a way to create friction in those modalities as well,” says Tolia. But even if Nextdoor figures out how to carry out its current plan, activists Shikira Porter and Monica Bien will not be satisfied. They say the fix isn’t good enough, and that people should be required to list five attributes in addition to race instead of just two. And they question Nextdoor’s measure of improvement. “I don’t believe their data,” says Porter. In addition to monitoring her Oakland neighborhood on the site, she keeps in touch with activists around the country doing the same thing. “What I see as a user is that folks are still profiling,” she says. In fact, she has noticed anecdotally that profiling has worsened in the new social climate condoned by the Trump administration. The activists complain that now that Nextdoor has rolled out its initial design fix, it is less responsive to their concerns. “We had a two-hour phone call in October, and we got a response back three weeks ago,” says Porter. I ask them if they believe the world would be better off without Nextdoor altogether. No, they say, not at all—Nextdoor is a valuable resource for all local communities. Porter sighs. She’s said what she’s about to tell me many times. The way our society figures out how to help people who are marginalized, she explains, is by deciding what’s best for them, rather than letting them decide for themselves. She is resigned to the fact that she will say this many more times. She is patient. She is right. Though Nextdoor deserves the credit it has received for tackling bias at the highest level in the company and reducing racial profiling on its site by a considerable amount, it hasn’t eliminated it. And the work left to be done may come at the expense of its business interests. That raises questions every founder in Silicon Valley struggles to answer: What are the moral responsibilities of a small, fast-growing, private, venture-funded startup still eking out a business model? When doing what’s ethical clashes with the business imperatives of a company that has not yet succeeded, is there a middle ground? “The sad reality is that unconscious bias is part of our society,” Mohit said at a heated Oakland City Council meeting last year, during the height of the controversy. “Platforms like Nextdoor sometimes act as a mirror that reflects the thoughts and fears that exist in our neighborhoods today.” To find its way forward, the company has had to face off against one of the biggest challenges facing not only social platforms, but also all of society: how to nudge users to be their better selves. Senior Writer Facebook X Topics Backchannel Apps Startups Social Media Racism Andy Greenberg Angela Watercutter Lauren Smiley Steven Levy Brandi Collins-Dexter Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"These Satellites See Through the Clouds to Track Flooding | WIRED"

"https://www.wired.com/story/these-satellites-see-through-the-clouds-to-track-flooding"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Sarah Scoles Science These Satellites See Through the Clouds to Track Flooding Photograph: REMKO DE WAAL/Getty Images Save this story Save Save this story Save One day Joe Morrison, the vice president of a satellite company, gave members of his team a strange task: Go buy images from another company’s picture-taking spacecraft. He wanted to see how easy it was to exchange money for those orbital goods and services. So the group scampered off and ordered a satellite image of an area in Southeast Asia, to be taken within the next three weeks. They paid around $500. Easy. Three weeks later, though, they’d only gotten radio silence. It turned out that the company had been unable to take a snap, and the broker had canceled their order. It was a high-demand area, of which many people wanted portraits. Plus, it was monsoon season, when clear shots were hard to come by. So instead, the company had tasked their satellite to take the image sometime within the next year. … Thanks? To Morrison, this experience demonstrated much of what’s wrong with the “remote sensing” industry. A picture may be worth a thousand words, but that’s true only if you can get a shot in the first place. Clouds cover, on average, about two thirds of Earth. And at any given time, roughly half of the planet is dark. (This area’s experience is commonly referred to as “night.”) In either of those conditions, traditional satellite imagery is not worth many words at all. And if you want to buy many photos of the same area, tracking how things change, this gets difficult and expensive—unless you’re a defense department or spy agency with deep pockets and front-of-queue influence. That’s why Morrison hopes data from his employer—a company called Umbra, based in Santa Barbara, California—could fulfill what has long been remote sensing’s promise: The ability to monitor Earth, not just take infrequent static photographs of it. Courtesy of Umbra Lab Inc. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Umbra’s satellites don’t take pictures, anyway; they take “synthetic aperture radar” (SAR) data, which functionally means “radar data from space.” It works like this: A satellite shoots microwaves toward the planet, then waits for their echoes to bounce back up. Because the satellite will have orbited to a slightly different spot between the radar’s emissions and returns, it effectively functions as an antenna as big as that distance—a “synthetic aperture.” Objects with different makeups reflect the microwaves differently—a building, for instance, behaves differently than an ocean. And objects at different distances from the satellite take different amounts of time to whip the waves back spaceward. So by using SAR, analysts can get some pretty sharp detail on shape, size, and even composition. Most important, microwaves shoot straight through clouds and don’t know the difference between day and night. SAR satellites, then, can observe Earth in any weather, at any hour. That capability is proving particularly useful to those who want to track events that tend to happen during overcast conditions and under cover of darkness: floods. Flooding has long been the cause of human suffering—it destroys crops, livestock, infrastructure, and human lives. Climate change is increasing flooding risk, since extreme weather events and sea levels are on the rise. According to professional services firm Marsh McLennan, which specializes in risk assessment, since 1980 there have been around 4,600 floods worldwide, which together have cost more than $1 trillion in damages, or around 40 percent of the world’s total natural disaster losses. Severe floods are public health hazards, like 2020’s monsoon flooding in India , which killed 1,922 people—the year’s most fatal natural disaster, unless you count Covid. Worldwide, floods killed more than 6,000 people that year, according to the Global Natural Disaster Assessment Report. Scientists, rescue agencies, governments, and insurance companies would all like to keep track of developing floods and predict the risk to a given area, to direct financial and physical assistance to the right places, to direct people to dry places, and to assess where building, planting, and living don’t make sense. Having reliable real-time data would be helpful, but traditional satellite pictures often fail, because clouds are, obviously, often present over the terrain during a flood. So the images either aren’t possible—or are simply pictures of clouds. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg SAR is the right sort of tool for tracking floods, says Umbra’s chief operating officer, Todd Master, not just because clouds and darkness have no bearing but because you also “get these very distinctive turns between water and not-water” and can calculate how high that water is above the ground compared where it was during the satellite’s previous passes. SAR’s returns can also tell the difference between freshwater, saltwater, and gray water. That’s useful when, say, you need to know whether seawater is intruding inland or whether an oil or sewage leak will be floating downstream. Flooding data represents only a small slice of what Umbra plans to collect. The company, which was founded in 2016, launched its first satellite last summer, another earlier this year, and is preparing to launch two or three more this year. Umbra will task them with collecting intel on how Earth looks today versus tomorrow versus a couple of months from now. In addition to watching floodwaters rise, those shifts can help analysts see things like military equipment being shuffled around, buildings booming up, or glaciers melting. Umbra began collecting on-orbit data in early 2022 and is currently getting it ready for its first customers. Like most remote sensing companies, their client roster is heavy on US government national security and intelligence types but also contains a slice of for-profit companies, scientists, and nonprofits that want to use the information for research, humanitarian, or capitalistic purposes. But what those nerds pull out of the data will be up to them: Umbra isn’t getting into the analytics game. It won’t interpret the echoes for its customers. Instead, the company will just sell its data so that others—experts in their own fields, whether glaciology or spying or flood-mapping—will develop the software to make sense of it. Courtesy of Umbra Lab Inc. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg SAR data has previously also been used to track troop movements , monitor mines , surveil pirates , and inspect dams. But finding water where it shouldn't be is a perfect task for these satellites. Sometimes, telling the difference between land and water from far away—literally just determining whether a spot is flooded—is the hardest part. But water and land scatter microwaves very differently, providing precise maps of where liquid has intruded upon what’s supposed to be solid, even during the most opaque part of the storm. “For flooding, it's so obvious,” says Bessie Schwarz, CEO of a company called Cloud to Street, which tracks floods in (almost) real time and analyzes shifting food risk as rains fall, showing how those environmental conditions will affect population centers, infrastructure, agriculture, and anything for which you can buy insurance. Cloud to Street plans to buy raw data from Umbra satellites, pass it through the company’s automated analysis algorithms, then use it to produce what’s called “actionable intelligence” for its clients. It can locate, map, and count the people, land, crops, and roads that are currently inundated, or provide color-coded risk maps for future floods. SAR helps the company fill in information when optical data isn’t available. Launched in 2016, Cloud to Street started with using data from public and private satellites. Its first radar data came from satellites like the European Space Agency’s Sentinel-1 and the Canadian Space Agency’s RADARSAT, which make data freely available, and have worked with the German public-private partnership TerraSAR-X. But, recently, private companies have come out to play, operating constellations of smaller satellites. “We have been really excited about how many are going up,” says Schwarz. Cloud to Street has dealt with satellite makers like Capella, and is an early-interest group on Umbra’s client list. Schwarz and her cofounder, Beth Tellman, have been working on Cloud to Street for about a decade. They met in 2012, on their first day of graduate school at what’s now called the Yale School of the Environment. Schwarz had been working in policy, focusing on communities vulnerable to climate change, and Tellman had been doing community projects in the wake of natural disasters. They’d both seen, firsthand, what happened when people didn’t have the disaster information they needed. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Hydrology data is lacking in the parts of the world that could use it most. “The information gaps in the developing world are just so huge,” says Schwarz. And efforts to collect that data sometimes don’t work out. “We work in places where maybe they set up a local equipment system, and then all of the equipment got stolen, literally days later, or wiped out during a conflict,” she adds. As the satellite industry, cloud computing, and image-analysis algorithms matured around them, Schwarz and Tellman decided to try to fix that international discrepancy. Satellite data could overcome a lack of ground sensors, and Cloud to Street could get that information to local governments and nonprofits. “We could suddenly put in a flood information system for a country with no equipment basically overnight,” says Schwarz. For example, in 2017, intense floods inundated the town of Impfondo, in the Democratic Republic of the Congo, but its remoteness made sending aid and determining people’s needs difficult. Working with the Congolese government and humanitarian groups, Cloud to Street’s platform has since shortened flood detection times from weeks to days and provided information about where to safely relocate refugees. Initially, Cloud to Street’s customers were governments, their disaster arms, and organizations like the World Bank, helping them figure out who needed to be relocated and where and giving them evidence they could use to lobby for additional relief funds. Today, Cloud to Street also works on more corporate pursuits, helping insurance companies tap out their risk and payout calculations. Either way, says Schwarz, they will need SAR. “It's very clear that radar has really one standout advantage that is hard to overcome, that was always going to be necessary—and that's when it's flooding, it's often cloudy and rainy,” she says. “That's just, very straight up, the huge advantage of it.” Over four weeks, WIRED is publishing a series of stories about the scientific uses of satellites. Read other stories in the series here , here , and here. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Developing algorithms that can parse SAR data, though, is more difficult than whipping up ones that can parse pictures. Partly, that’s an artifact of the limitations of the human brain. Some data-processing algorithm styles are modeled on how our brains analyze visual information. But we don’t perceive anything like SAR data. “It’s harder than dealing with optical data, because we don't see in radar,” says Vijayan Asari, the director of the Vision Lab at the University of Dayton, which has a SAR image analysis arm. “We don't see in microwaves.” (The group, which collaborates with the Air Force Research Lab, among other organizations, is working on using SAR to detect and predict glaciers’ activities—another environmental application for this data. Glaciers are typically on dark, cloudy parts of the planet. In addition to seeing through the gloom, SAR can also penetrate the top of the ice, revealing glaciers’ flow dynamics as they melt and move. As an academic group, the lab will likely need to use data collected by Umbra or a competitor, along with information from public satellites like Sentinel.) Even Umbra’s COO had a hard time grokking SAR at first. “My first exposure to it was with regards to US classified capabilities,” says Master, who was previously a program manager at Darpa, the defense department’s high-risk, maybe-reward research agency. “I think I kind of came into it with an attitude, which is like, ‘SAR is weird, it probably isn’t going to tell you anything.’” After all, as he puts it, “our brain is tuned to our sensors.” (He means eyeballs.) But, he continues, you can think of SAR as being like a “flashlight” that illuminates what your eyeballs can’t make out on their own. SAR also has an advantage over high-definition visual satellites: Radar satellites are cheap and (relatively) easy to make. They don’t require a clean room or giant, precise mirrors. “The issue with optical is that resolution rules the day,” says Master, meaning the sharper an optical image is, the more useful it is. “Resolution is driven by big glass,” he says. “And big glass is expensive.” Umbra’s business model is similarly streamlined: It just sells data to groups like Cloud to Street instead of analyzing it. Morrison thinks it’s better to leave that to the specialists. Take Schwarz, says Morrison. “She wakes up in the morning, and from the moment she's awake to the moment her head hits the pillow she's thinking about flood inundation,” he says. He, meanwhile, rarely dreams of rising waters. (“I've got a satellite to operate,” he says.) But he hopes that once SAR data is readily and relatively cheaply available, more people might wonder about how it might help their own research or business—whether that involves tracking deforestation, carbon credits, wildfires, oil shipments, military movements, leaky pipes, or aging roofs. “There are a million of these little niches,” says Morrison. And some of those niches could keep both lives and livelihoods from going underwater. You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Contributor X Topics satellites maps weather extreme weather climate climate change flood water hurricanes Max G. Levy Matt Simon Max G. Levy Grace Browne Dell Cameron Amit Katwala Dhruv Mehrotra Ramin Skibba Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Satellites Can Spy a Menace in West Africa: Invasive Flowers | WIRED"

"https://www.wired.com/story/satellites-can-spy-a-menace-in-west-africa-invasive-flowers"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Ramin Skibba Science Satellites Can Spy a Menace in West Africa: Invasive Flowers Aerial image of Ganvie village on Lake Nokoué in Cotonou, Benin. Photograph: Astrid Hsu and Ufuoma Ovienmhada Save this story Save Save this story Save Sometimes flowers can be the villain. Water hyacinths, with their seemingly harmless violet petals and lush green leaves, have invaded tropical parts of West and Central Africa, including Benin. In Lake Nokoué in Cotonou, near the country’s populous central coast, the hyacinths threaten to take over; in the last few decades they’ve spread into dense colonies that block sunlight, crowd out native plants and wildlife, clog the waterways and irrigation canals, and hinder villagers as they try to travel and collect fish. Danielle Wood thought that space technology could be part of the solution. In 2017, soon after moving from a job at NASA to MIT, she attended a conference where she encountered a Beninese entrepreneur who invited her to visit and explore how satellite data could help local groups manage the invasive weeds. Today Wood is the director of the Space Enabled research group at MIT’s Media Lab, and she was part of a team that just published their findings in the journal Frontiers in Climate, showing how Earth observation technologies can map and monitor hard-to-reach areas to inform local decisionmaking—specifically on how Beninese groups are tackling the hyacinth problem with data from satellites, drones, and sensors in the lake. Companies and agencies in North America and Europe frequently have access to such technologies, but that’s not always true in the rest of the world. Wood and her team worked with resources from a program known as SERVIR, led by NASA and USAID, that is playing a role in boosting these capabilities among economically developing countries. “Our goal is to make it an affordable and operationally feasible thing for them to have this ongoing view, with data from space, data from the air, and data from the water,” Wood says of the project in Benin. Ufuoma Ovienmhada, a PhD student in Wood’s group, helped implement the project and worked with Fohla Mouftaou, a Beninese doctor and managing director of the company Green Keeper Africa. Mouftaou doesn’t want to get rid of the water hyacinths, which originate in the Amazon basin in Latin America. But he would rather make better use of them in his community. The flowers can actually be transformed into an organic fiber that’s effective at absorbing oil-based pollutants and can be used to clean up oil spills or surfaces contaminated with oil, acids, and paints. Green Keeper Africa contracts hundreds of people in the area, including women who live near the lake, to gather the hyacinths and make them into the fiber. First, however, they need to know where to focus their harvesting efforts. Ovienmhada had flown a drone quadcopter over and around the lake to collect high-resolution photos of where and how fast the hyacinths are growing, but she was limited by where she could pilot it and how long the batteries lasted. Satellite data was more comprehensive. The team collected images of the whole region in visible and near-infrared wavelengths, as well as radar data with radio and microwaves. Then she compared it to NASA orbital images going back to 1980. “The really cool thing about satellite data, compared to other methods, is that satellite data is large-scale and has a long historical archive of imagery. We were able to analyze trends in water hyacinth growth,” Ovienmhada says. Researcher Ufuoma Ovienmhada operating a drone in Cotonou, Benin. Photograph: David Lagomasino Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg While the satellite images give a regional perspective, Ovienmhada’s drone photos provided detailed views of targeted areas. She also took a boat into the lake, stopping here and there to take water quality measurements with sensors. Using all this data, Ovienmhada was able to show that, despite some annual variation, the water hyacinth problem was indeed worsening, on average covering more and more of the lake each year. The project also produced an online tool that helps GKA plan where they’ll harvest, estimate how many people and how much storage space they need, and assess how well they’re preventing the plant from spreading excessively. SERVIR, which launched in 2004, is making such projects possible. The program (Spanish for “to serve”) helps local governments and communities to make use of satellite data to address environmental threats and respond to natural disasters. “Countries all over the world could use the data. NASA had the data and the know-how. How do you bring those two together?” asks Daniel Irwin, SERVIR global program manager and research scientist at NASA Marshall Space Flight Center in Alabama. Irwin emphasizes that local experts, not embedded NASA officials, design these projects. SERVIR currently has five regional hubs, one of which is in West Africa. The others are in Eastern and Southern Africa, the Amazon, the Hindu Kush, and the Mekong, and they may add more, such as in Central America. The program doesn’t have its own spacecraft, but it uses data collected by a variety of NASA satellites, as well as some from the European and Japanese space agencies and, recently, commercial ones, such as from San Francisco–based Planet Labs. “We’re power users of Landsat,” Irwin says, referring to a series of satellites developed by NASA and the US Geological Survey that have been orbiting the globe since 1972. (Ovienmhada and Wood’s work benefited from those older Landsat images.) The newest spacecraft in that family, Landsat 9, just launched last month. Like its predecessor, which is still in orbit, it provides images that each represent an area that’s about 180 kilometers on a side, with each pixel covering an area 30 meters per side. “We get really great-quality data every eight days. That’s going to be a boon, especially for water quality applications,” says Jeffrey Masek, the Landsat 9 project scientist at NASA Goddard Space Flight Center in Maryland. The scope and resolution of the images have proved useful not just for Ovienmhada’s analysis, but also for other projects mapping algae blooms , or tracking and forecasting droughts and floods. Other SERVIR projects have used Landsat data to map and track deforestation, loss of rangelands, crop yields, and wildfires. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg A water hyacinth infestation on Lake Nokoué in Cotonou, Benin. Photograph: Danielle Wood and Ufuoma Ovienmhada While one need not be a data scientist or computer programmer to make use of SERVIR images, it does take some training—available at the project’s hubs—in scripting languages like Python to find and manage the best data set for a project. It also helps to have online, cloud-based tools available, like Google Earth Engine, which Ovienmhada used to import data, maps, and tables. The SERVIR program has been increasingly active in Africa and other regions partly because, through training and collaboration, NASA and USAID have been able to make their tools and data more useful to people on the ground, says Niall Hanan, an ecologist at New Mexico State University in Las Cruces. Hanan wrote a paper last year reviewing the many ways Earth observation data can be deployed for decisionmaking in economically developing countries. “They’re trying to tailor their products for managers down to the level of individual farmers and communities, so more on the application side and less on the research side,” he says. “They put a lot of effort into building relationships with various stakeholders, whether that’s government ministries, regional managers, NGOs, landowners, and land users.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Indeed, some projects are led by people in the region of study. Edward Ouko, ecosystem and modeling lead at the Regional Centre for Mapping of Resources for Development in Nairobi, wanted to map invasive plants in Kenyan rangelands to aid farmers as they take their cattle and goats for grazing. These plants are unpalatable and unhealthy for the livestock, making the animals undernourished and threatening the farmers’ livelihoods. “The northern frontier of Kenya was highly invaded by invasive species: acacia and prickly pear. We cannot eradicate them, but the best we can do now is monitor them and mitigate their effects,” says Ouko, who led the project for SERVIR’s East African hub. Last year, he published a study in the journal Frontiers in Environmental Science mapping where the invasive plants are and projecting how they’ll spread under different climate scenarios. Wood recently completed another project involving Landsat data; she and colleagues in Ghana mapped more than a decade of deforestation there. In August, they published their findings, which included showing that as much land was being lost to small-scale mining as to expanding urban areas, degrading and destroying forest ecosystems. For Ovienmhada and Wood, their water hyacinth project isn’t just about the results. It’s also about developing practical advice for how to respectfully collaborate, collect data, and present findings when scientists and local experts work together. They hope their work inspires others. “The methodology gives special attention to inclusivity, historical power imbalances, and different ways of generating knowledge,” Ovienmhada says. Updated 11/18/2021 6:00 PM ET: This story has been updated to clarify that the hyacinth invasion is occurring in both West and Central Africa, and that Green Keeper Africa contracts (rather than hires, as previously stated) workers to gather hyacinths. 📩 The latest on tech, science, and more: Get our newsletters ! The mission to rewrite Nazi history on Wikipedia Actions you can take to tackle climate change Denis Villeneuve on Dune : “I was really a maniac” Amazon's Astro is a robot without a cause The effort to have drones replant forests 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 🎧 Things not sounding right? Check out our favorite wireless headphones , soundbars , and Bluetooth speakers Staff Writer X Topics environment satellites Earth Science NASA pollution nature Africa farming Ramin Skibba Matt Simon Matt Simon Amit Katwala Grace Browne Ramin Skibba Jim Robbins Matt Simon Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"The Dark Asteroid Ryugu Finally Comes Into the Light | WIRED"

"https://www.wired.com/story/the-dark-asteroid-ryugu-finally-comes-into-the-light"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Ramin Skibba Science The Dark Asteroid Ryugu Finally Comes Into the Light Photograph: JAXA Save this story Save Save this story Save In 2018, the Japanese space agency’s Hayabusa2 probe visited the near-Earth asteroid Ryugu, which occasionally traverses our world’s orbit (but has yet to come dangerously close). It extracted a tiny fragment of that hurtling space rock and in December became the first spacecraft to deliver a piece of an asteroid to Earth , ahead of a NASA mission that will return a sample from a different asteroid in 2023. While the initial analysis from that precious sample likely won’t be available until early next year, scientists are now releasing findings from Hayabusa2’s onboard cameras and instruments. This new research, led by Deborah Domingue at the Planetary Science Institute in Tucson, Arizona, and Yasuhiro Yokota at the Japan Aerospace Exploration Agency, sheds light on Ryugu’s complex structure, revealing it to be a dark, weathered pile of rubble tumbling in space, different from anything seen on the surface of the Earth. “I’m very hopeful our results will be helpful for the sample team,” Yokota says. Ryugu’s known as a C-type, or carbonaceous, asteroid, meaning its rocks and pebbles are packed with carbon molecules, contributing to its sooty coloration. It’s only a kilometer in size, less than half the width of Manhattan, and it travels in a nearly circular orbit around the sun, closer to Earth than either the asteroid belt or Mars. Scientists want to study it because its composition might tell us compelling things about the building blocks that formed the rocky inner planets in the early days of the solar system. When Hayabusa2 first arrived at the asteroid, scientists wanted to use its tools and mini rovers to collect samples, but they were surprised to see that one couldn’t simply scoop up some sand or dust, like you would on a beach. (Or on the moon or Mars. ) Despite expectations based on telescope observations from afar and from a bread-loaf-sized rover called Mascot, it looked like Ryugu was somehow made of rocks of various sizes mashed together—but no dust. That made some scientists wonder if Ryugu simply didn’t have any. Since Ryugu is so small, its gravitational pull is far less than that of the moon. On the moon, jumping astronauts don’t launch themselves into space, but on Ryugu, “if you even took a step, you’d fly off the surface,” says Erica Jawin, a planetary geologist at the Smithsonian National Museum of Natural History in Washington, DC. “The asteroid has a micro-gravity on the surface which might not be large enough to hold fine-grain material.” In findings that will be published in the October issue of Planetary Science Journal , Domingue and Yokota showed that the dust isn’t missing, but it is elusive, coating surfaces instead of turning up in piles. They took images with Hayabusa2’s Optical Navigation Camera (ONC) and used its near-infrared spectrometer (NIRS3) to measure spectra, maps of light at a range of wavelengths. Their spectral analysis, tuned toward picking up the presence of tiny things, showed that at least some dust is indeed present. “Where did the dust go? Our study shows that it’s there. It’s ubiquitous,” says Domingue. But instead of being in a soft, sandy pile, that dust could be mixed in with coarser-grained sand or coating the bigger rocks and in their nooks and crannies. The rocks and boulders of Ryugu aren’t solid and hefty like those of Earth, says Michele Bannister, a planetary astronomer at University of Canterbury in New Zealand. They’re so rough, porous, and lightly held together that they could easily break up, producing the kinds of sand and dust Domingue and Yokota see. Tiny meteorites and cosmic radiation pockmarking the surface could also help to erode the rocks into smaller bits. But the mystery probably won’t be solved until researchers finish studying the contents of the sample capsule. After they retrieved it from the South Australian outback last December, scientists did see some dark grains inside the container. They hope Hayabusa2 successfully collected at least 0.1 gram of material from Ryugu, and perhaps much more, in that treasure box from space. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Hayabusa2 also provided the researchers with unique opportunities to observe the asteroid at multiple angles, including hard-to-get images taken at “opposition.” This involved maneuvering the fridge-sized spacecraft to catch snapshots while the asteroid and sun were on opposite sides of it, an alignment that provides views of the asteroid with the sun’s rays reflected directly back toward the camera, without producing any shadows. Thanks to the physics of optics, anything with a rough surface that reflects light will seem slightly brighter when it’s in opposition. This means that small, faint, and distant asteroids can really only be seen at opposition. In fact, they’re so dark that from Earth we can’t see a “crescent phase,” like the moon has. Domingue and Yokota find that Ryugu is one of the darkest objects ever seen: Reflecting only about 3.5 percent of sunlight, it’s darker than other kinds of asteroids and darker even than a lump of coal. But taking photos up close and at opposition allowed the researchers to get a detailed image of the asteroid’s surface; it enhanced the way the asteroid’s dust interacts with light, making it clearer that it is in fact there. Bannister says opposition images are like looking at a grassy lawn when the sun is directly behind you, allowing you to see individual blades, as opposed to when sunlight falls obliquely on the lawn, which produces lots of shadows. Comparing opposition images to those taken at near-opposition “tells you how bristly your lawn is, but from a distance, it can all appear completely smooth,” she says. The mostly shadow-free photos also enabled the researchers to map Ryugu’s surface structure, at least on one side. This exploration of Ryugu is part of a broader effort to investigate many types of asteroids to learn more about their shapes, contents, and origins. Ryugu is similar to another near-Earth asteroid, called Bennu, that was recently visited by NASA’s OSIRIS-REx spacecraft. They’re both C-type asteroids that are shaped like tops, though with differently accentuated central ridges. The first Hayabusa mission rendezvoused with a more stony, S-type asteroid. NASA’s planned Psyche mission will next year voyage toward an M-type asteroid full of iron and other metals, and the agency’s Lucy craft , which launches this October, will head towards the D-type Trojan asteroids to study the building blocks that formed the Jovian worlds. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The residents of the main asteroid belt, a scattered conglomeration of space rocks Jupiter never allowed to become a planet, have had stable orbits over billions of years, says Andy Rivkin, a planetary astronomer at Johns Hopkins University in Baltimore. In contrast, near-Earth asteroids have wonkier orbits. “Something like Bennu and Ryugu eventually hits a planet or the sun over millions of years, so they can’t have been there very long,” he says. Ryugu likely formed when something collided with a much larger asteroid, breaking off a bunch of rocky debris that later glommed together and headed on a different trajectory. Meteorites, or chunks of asteroids and comets that hit the Earth, can have similar origins, though C-type meteorites aren’t common, Rivkin says. Upon comparing Ryugu’s structure, terrain, and composition to a variety of other, larger asteroids, Yokota believes that it probably originated from a “parent body” called Eulalia, which is similarly dark and rich in carbon, though other asteroids haven’t been ruled out as its parents. Research on near-Earth asteroids has implications for scientists’ understanding of bodies that might one day collide with the Earth. “We know of no asteroids that are going to hit the Earth,” Rivkin is quick to point out, but scientists at NASA and elsewhere try to monitor every trackable asteroid, just in case one turns out to be heading in our direction with an arrival time within a couple decades. Occasionally their trajectories can subtly shift, potentially pointing them in a more hazardous direction (from Earthlings’ perspective). This could happen thanks to impacts by smaller objects or to something known as the Yarkovsky effect, which is when sunlight hits an asteroid and gets reradiated as heat, giving it a tiny thrust. NASA and the European Space Agency are currently studying how to deflect an asteroid on a collision course. In November, NASA will launch the Double Asteroid Redirection Test (or DART), a mission Rivkin’s involved in that will try bumping an asteroid onto a new path by slamming a small probe into it. DART’s target asteroid is a bit different from the rubble pile that is Ryugu, but the same physics should apply to any asteroid: “We expect to kick off some debris, but the momentum will still get transferred,” Rivkin says. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Would-be asteroid miners are surely paying attention, too. Deep-space missions might one day depend on astronauts extracting water for consumption or fuel from them. Domingue and her colleagues used data from Hayabusa2’s onboard spectrometer to find evidence of water molecules on Ryugu, within its dust grains, pebbles, and rocks. “If they are mining for water, there is some present, but there are probably some objects that would have more than Ryugu would,” Domingue says. (Psyche’s destination asteroid lacks water, though it does have iron, nickel, and possibly more lucrative metals like platinum.) While Yokota and Domingue aren’t directly involved in the study of the little piece of Ryugu, which has already begun, they’re looking forward to what their colleagues learn from it. “I suspect that the sample will have many surprises for us. It’s just exciting!” Domingue says. 📩 The latest on tech, science, and more: Get our newsletters ! Can robots evolve into machines of loving grace? 3D printing helps ultracold quantum experiments go small How community pharmacies stepped up during Covid The Artful Escape is psychedelic perfection How to send messages that automatically disappear 👁️ Explore AI like never before with our new database 🎮 WIRED Games: Get the latest tips, reviews, and more 📱 Torn between the latest phones? Never fear—check out our iPhone buying guide and favorite Android phones Staff Writer X Topics Asteroids Astronomy space planetary science Earth Science NASA Ramin Skibba Ramin Skibba Ramin Skibba Matt Simon Matt Simon Rhett Allain Emily Mullin Rhett Allain Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Inside the Cleanroom Where NASA’s New Mars Lander Waits to Launch | WIRED"

"https://www.wired.com/story/inside-the-cleanroom-where-nasas-new-mars-lander-waits-to-launch"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Matt Simon Science Inside the Cleanroom Where NASA’s New Mars Lander Waits to Launch The InSight lander has solar panels that will power the spacecraft as it does science and communicates with Earth. NASA/JPL-CALTECH/LOCKHEED MARTIN Save this story Save Save this story Save A few rules for the cleanroom where NASA ’s new InSight Mars lander waits for launch. One, if you must sneeze, sneeze away from the spacecraft. Two, if you drop anything, let one of NASA’s escorts pick it up for you. Three, do not under any circumstances cross the black-and-yellow-striped tape and touch the spacecraft. Oh also—an engineer tells a dozen media in a conference room at Vandenberg Air Force Base—do not lick the spacecraft. There’s always that one rebel, I suppose. The InSight lander at rest in a cleanroom. NASA The reasons to behave ourselves are many, and they are serious. For one, InSight costs nearly a billion dollars , and although it’s engineered to survive the punishing journey to Mars , it’s not engineered to be licked. And two, this conference room is loaded with planetary protection specialists, whose oh-no-big-deal job is to make sure Earthling microbes don’t end up colonizing Mars. And not just for the solar system’s sake—NASA is obligated by international treaty to keep other planets clean. In just a month, it'll fire InSight to the Red Planet, where the lander will drill to unravel the geological mysteries of our solar system's rocky bodies. On Friday NASA shuffled us media into a pair of rooms designed to keep bugs the hell away from InSight. In the first, we step all over a sticky white rectangle, a kind of fly paper for particulates. Then we don those blue fabric booties you’d find in a hospital. In the next room over, on goes the face mask, and over that a hood. A friendly yet stern specialist demonstrates how to step into coveralls without making any of the material touch the ground, or falling over and having to start all over again. Then I sit on a bench, feet on one side of a line of tape, and slide on shoes with high socks that cinch tight over my calfs. Only now can I swing my feet over to the other side of the tape—the clean zone. The specialist ushers me through a glass door into a tiny closet dotted with vents, which blast my body as I spin 360 degrees with arms up. After a few seconds, I push through another door and into the planetary science version of heaven. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg It’s shiny, almost entirely white, and cavernous. There sits InSight in two pieces—the spacecraft itself and the heat shield that’ll protect it from the 2,800-degree-Fahrenheit temperatures as it descends through the red planet’s atmosphere. Around it stand engineers in all white (media get conspicuous dark blue), hands clasped in front of them. I can see nothing but their eyes, but they’re friendly eyes. Eyes that say, What would you like to talk about at a safe distance from the spacecraft? Two of those eyes belong to Ryan Hendrickson, a planetary protection engineer at NASA’s Jet Propulsion Laboratory. Hendrickson’s greatest foe: bacterial spores. “They're usually the ones that are resistant to UV radiation or they're resistant to certain cleaning products,” he mumbles through his face mask. “So when we build a spacecraft in a cleanroom, we're kind of artificially selecting for those bacteria to hang around. That's why we specifically target those organisms to measure.” If they’re hard to find on InSight, chances are other less-hardy microorganisms like fungi haven’t been able to take hold either. Fun fact: When a waiter scrubs your table with circular swirls of a wet cloth, they’re really just spreading bacteria around. With InSight, NASA instead periodically tests for bacteria and gives the thing good linear wipes up and down, physically removing spores from the surface. And they’re damn good at it. This particular mission is Category IVa. “So it's limited to 300,000 spores on the entire spacecraft,” says Hendrickson. “If you piled those all into one place, they would probably fit on a hangnail.” For some perspective, just one square inch of your hand is home to around 10,000 bacteria. With its extended solar panels—which will power the spacecraft as it does science and communicates with Earth—InSight is 20 feet long. A rendering showing the lander’s domed seismometer and its drill, which will probe down 16 feet to take the planet’s temperature. NASA/JPL-CALTECH Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg When InSight settles on the Martian surface, it’ll deploy two primary instruments. The first is a seismometer wrapped in a dome that insulates and protects from the planet's dust storms. This will measure marsquakes —don’t you dare call them earthquakes. Like scientists can do here on Earth, with InSight planetary geologists will be able to infer the composition of Mars’ innards from these vibrations. The second instrument is the fanciest thermometer you ever did see, which will drill down 16 feet, deeper than any other Mars craft has probed. It will trail a cable embedded with thermal sensors every foot and a half. “We can actually figure out what the increase in temperature is as you go down this hole,” says Bruce Banerdt, principal investigator of the mission. “That thermal gradient is what is pushing the heat out of the planet. So even over that short interval, we can extrapolate that and get the temperature deep into the planet.” The bad news about Mars is that scientists don’t really know how much heat is left over from the formation of the planet. But the good news is that Mars is nowhere near as geologically active as Earth, with its plate tectonics and volcanism and many earthquakes. So how does a rocky planet end up like Earth, or how does it end up relatively calm like Mars? “On Earth, we can't really study that very well because the crust has been recycled by plate tectonics, the mantle has been churned up by vigorous convection,” says Banerdt. That’s erased a lot of the evidence for the early processes in the formation of a planet, yet Mars may have retained a lot of those fingerprints. So InSight will be measuring things like the thickness of the planet's crust and the size of its core. "We can use that to understand those processes that happen early on in the history of Mars and then extrapolate that to all the other rocky planets," says Banerdt. First, though, NASA has to erase InSight’s biological history, (potential) licks and all. -Drill-happy landers are pivotal to understanding the geology of Mars. But that doesn't mean orbiters can't also sniff out things like fresh water on the Red Planet. -Sit back and take in a stunning stitched-together video of Mars. -Meanwhile, don't forget the Curiosity rover. It's still hard at work autonomously finding rocks to blast with a laser. Staff Writer X Topics NASA Mars space Ramin Skibba Swapna Krishna Ramin Skibba Ramin Skibba Ramin Skibba Rebecca Boyle Ramin Skibba Ramin Skibba Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"How NASA Scrambled to Save OSIRIS-REx From Leaky Disaster | WIRED"

"https://www.wired.com/story/how-nasa-scrambled-to-save-osiris-rex-from-leaky-disaster"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Chris Wright Science How NASA Scrambled to Save OSIRIS-REx From Leaky Disaster Photograph: Symeon Platts/University of Arizona Save this story Save Save this story Save On October 20, an uncrewed spacecraft roughly the size of a Sprinter van and traveling at the glacial pace of 10 centimeters per second collided with an asteroid 200 million miles from Earth. The OSIRIS-REx craft’s proboscis-like “Touch-and-Go Sample Acquisition Mechanism” (Tagsam), an 11-foot-long shock absorber tipped by a round vacuum head and a collection canister, touched down atop a boulder on the asteroid Bennu’s surface—and appeared to smash right through it. Several seconds after impact, the arm had punched more than a foot and a half into the asteroid. It would have kept going too, but for the programmed sequence that burst the arm’s nitrogen gas canister, tripped its vacuum suction, and milliseconds later fired the spacecraft’s reverse thrusters to initiate a hyperbolic escape trajectory. After 17 years and $800 million in funding, the crux of OSIRIS-REx’s smash-and-grab mission was over in 15 seconds. At the Lockheed Martin mission support area in Colorado, the masked OSIRIS-REx team celebrated with air hugs and elbow bumps. A clear landing spot, flush contact, and deep penetration into Bennu looked good to ops. The Tagsam should have collected more than its target mass of 60 grams (about 2 ounces, or one large egg’s worth) of fragments, dust, and rocks (“regolith,” in asteroid-speak) from the surface, perhaps much more. All that remained was to perform a sample mass measurement maneuver to estimate the collection’s actual mass , stow the collector head away in a sample return capsule, and navigate it back to Earth by the year 2023. Then, scientists could begin to study the space dust to learn more about the beginnings of the universe, whether asteroids might have brought water or even life to Earth, and how to react if Bennu turns out to be on course to hit Earth between the years 2175 and 2195, as it seems it might be. In the middle of a global pandemic , the touch-and-go felt like a triumph. But several team members had nagging concerns. “There was almost no resistance at the surface,” says Mike Moreau, OSIRIS-REx’s deputy project manager. “When the gas bottles fired, it looked like it blew all the surface material away like it was packing peanuts.” Two days later, the team repositioned the Tagsam arm in front of a ship-mounted camera for visual inspection. The head appeared to be packed full of material—but it also appeared to be leaking. A series of three still images projected in sequence onto a large screen at Lockheed MSA showed a cloud of rocky material escaping into space. The room began to buzz with nervous discussion. The next photos, long-exposure images, appeared to show the precious asteroid debris leaving the Tagsam head’s one-way Mylar flap like water streaming from a showerhead. Dante Lauretta, the mission’s principal investigator, shouted over the chatter: “We have to do something about this!” Video: NASA/Goddard/University of Arizona But the delay in sending and receiving images from 200 million miles away meant the leak had actually happened 30 to 40 minutes before. The team huddled in groups and began to ask questions about just what the hell had happened. How long had the arm been leaking? How much material had escaped, and why? How could they stop it? The leak’s source was easy to spot. Rock-sized pieces of regolith were bulging the head’s Mylar flap ring partially open in several places. The flap was meant to allow material in—but not out. Nothing like this had happened during testing, which had included simulations of near-zero-G conditions using regolith-like materials, says Beau Bierhaus, Lockheed Martin’s Tagsam lead scientist. The particles appearing to hold the flap open were the right size and shape for collection. “I can’t think of anything that would have prevented the particles from being collected [inside the Tagsam head], other than there was no more room left at the inn,” Bierhaus says. “Because there was no more room inside, it got stuck.” How might the Tagsam head have become so full? Because Bennu’s surface was a mystery to scientists before OSIRIS-REx arrived to scope it up close, Bierhaus and other Lockheed engineers had to design their collector head to bounce off and suction up a range of surface types, from ones similar to a hard-packed gravel driveway to ones softer than a fine, sandy beach. Before the team saw Bennu up close, they modeled its surface based on the 25103 Itokawa asteroid, sampled in 2005 by the first Japanese Hayabusa mission. “We were hoping to, in essence, scoop up a big bucket of soft sand,” says Ed Beshore, the former deputy principal investigator of the mission, now retired from the University of Arizona. Instead, pictures of Bennu’s surface taken by OSIRIS-REx’s cameras before the touch-and-go appeared to show a minefield of sharp boulders and rocks. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg But Bennu had more surprises in store. In fact, based on the Tagsam’s deep bounce, it seems the surface material was not hard. In the asteroid’s microgravity environment, it instead behaved like a viscous fluid—thousands of marbles bouncing and scattering in low gravity. “If you push into it, it displaces and moves in ways we could not have anticipated,” Bierhaus says. The head penetrated the first few centimeters of surface without much resistance. This, Moreau says, “preloaded the center of the Tagsam head with material, and then when the gas blew, all that stuff went into the head immediately.” As the arm continued downward another half meter through the yielding surface, more regolith might have been jammed in. “By the time we backed away, the head would’ve been packed full,” he continues. Another possibility, given the surprisingly viscous surface material, is that the regolith’s soft, malleable rocks wedged into the Mylar flap opening and weren’t able to make it all the way into the head, Moreau says. Still, at HQ, there was some good news. Twenty to 30 minutes after the spacecraft stopped moving its Tagsam arm, the leak of material appeared to have died down. “Every time we moved the arm, we were shaking stuff loose,” Moreau says. Now the team ordered the ship to quiet itself, point toward Earth for easy communication, and “park” its arm in place. The team also canceled the upcoming sample mass measurement maneuver, which required extending the Tagsam arm and spinning the spacecraft—an action that was likely to spray debris out of the head in 360 degrees. Confident the Tagsam had gagged up only a portion of its enormous bite, the team moved on to the next question: Assuming the head had been crammed full of material when it bounced off Bennu, and that the leakage had been caused largely by movement of the arm, how much of the sample had been lost? Were there at least 60 grams left to stow away? To answer those questions without the measurement maneuver, five teams set about making estimates using alternate techniques. One group analyzed high-resolution imagery of the landing zone, down to the individual rocks, to model how many grams should have been collected; they estimated it was likely hundreds. Another group pored over photos of the Tagsam after the touch and go, peering into its visible area (about 40 percent of the container) to estimate the volume of the debris inside. The obstruction of light seen in a screen ringing the outside of the container offered another clue that the capsule might be close to full. One team estimated that the rocky material jammed in the Mylar flap was in the tens of grams—not enough to make up the necessary sample on its own, but a sizable prize. Another team used new 3D imaging techniques to estimate the size and mass of hundreds of particles shown escaping during the 10-minute imaging session just after the movement of the Tagsam arm, and found loss in the tens of grams—a “decent amount,” says Coralie Adam, the mission’s lead optical navigation engineer, but “we probably lost the smallest material that could escape through those gaps.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Another factor added uncertainty to these five alternative estimates: density. Until they get their hands on a sample, the team can only estimate a range of densities for Bennu’s regolith. The mass of the regolith they captured equals its volume times its density; less density, less mass, no matter the volume of the sample. A bag full of pumice is a lot lighter than the same bag full of marble. “It’s one of the areas where we could be surprised,” Moreau says, “and we could end up with a less massive sample if the density is much less than we assumed.” In a meeting with NASA’s administrators, Moreau and his team used their five estimates to propose that the ship had collected several hundred grams of Bennu's regolith, and perhaps much more. The team made the case that, despite the leakage, the Tagsam head still held well in excess of the minimum 60 grams, and they recommended stowing the sample immediately. The administrators approved, so the team sprinted to secure the head in its sample return capsule a week ahead of schedule. Unlike the touch-and-go maneuver, which was entirely automated, the stowing process involved manual visual checks and adjustments at every step of moving the arm into its secure position within the capsule. “It was a lot of work,” says Sierra Gonzales, a mission operations systems engineer who led the stow effort. In practice maneuvers on the ground before the mission, the team had struggled to maneuver the arm into its secure lashings. Banging the capsule’s edge now, they worried, might spill regolith everywhere. But this time, the team aced the process at record speed—36 hours rather than four days. Moving the arm meant losing more asteroid dust, though. Imaging analysis showed that they again lost hundreds of particles, or tens of grams, during the maneuver. On October 27, a week after the Tagsam maneuver, the team did a pull test to verify that the head was locked into position, then fired pyro bolts to separate it from the arm and closed the sample return capsule. The remaining regolith was now locked in and ready to ship to Earth. Video: NASA/Goddard/University of Arizona So how much space dust is now inside the return capsule? The team can’t offer a specific estimate, but one can imagine a few different scenarios, based on predictions about what might have happened during the Tagsam maneuver and the movements of the arm afterward. If the head came away from Bennu crammed full of material—say, a hulking 500 grams, which the team believes is within the realm of possibility—and leakage afterward during arm movements was in the low tens of grams, say 50 grams total, that would leave 450 grams of material in the capsule, more than seven times the mission’s required amount. The head could also have collected more like 200 grams of material, the low end of the team’s estimates, perhaps thanks to the surprising behavior of the asteroid’s viscous surface. Leakage in the tens of grams—again, let’s say 50 grams—would ensure a relatively good haul of 150 grams. But what if the ship lost more material than expected when the arm was moved? Doubling the leakage estimate to 100 grams of loss would cut the remaining amount of captured regolith in half. That’s still well within the mission’s parameters for success, but with a tighter margin for error if, say, the regolith’s density is surprisingly low. Overall, Moreau says, it would take a significant disaster to end up with fewer than 60 grams stowed in the head: Some major leakage the team didn’t spot, a significant miscalculation about the amount of regolith they initially captured, an entirely missed dynamic or factor. “All our analysis says with more than 99 percent probability that we have at least 60 grams, and probably more than that,” Moreau says. Every team member WIRED spoke to sounded equally confident that their craft had stowed more—and maybe much more—than its 60-gram target. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg If all goes well, in 2021, OSIRIS-REx will depart the vicinity of Bennu for Earth. In September 2023, the OSIRIS-REx will separate from the return capsule and steer itself to a lonely sleep somewhere in space. The capsule will fall through Earth’s atmosphere at 27,700 miles per hour, protected by a thick heat shield, and parachute to a landing zone at the Utah Test and Training Range. A retrieval team will track its location via optical techniques and radar. In the lab, researchers will finally be able to precisely measure the mass inside. Only then will the team know for sure how much space dust they’ve captured. 📩 Want the latest on tech, science, and more? Sign up for our newsletters ! One man’s search for the DNA data that could save his life The race to crack battery recycling— before it’s too late AI can run your work meetings now Spoil your cat over the holidays with our favorite gear Hacker Lexicon: What is the Signal encryption protocol ? 🎮 WIRED Games: Get the latest tips, reviews, and more 🏃🏽‍♀️ Want the best tools to get healthy? Check out our Gear team’s picks for the best fitness trackers , running gear (including shoes and socks ), and best headphones Topics space NASA Asteroids Spacecraft planetary science Ramin Skibba Ramin Skibba Swapna Krishna Ramin Skibba Ramin Skibba Ramin Skibba Charlie Wood Matt Simon Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"For the Second Time Ever, an Asteroid Sample Returns to Earth | WIRED"

"https://www.wired.com/story/for-the-second-time-ever-an-asteroid-sample-returns-to-earth"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Daniel Oberhaus Science For the Second Time Ever, an Asteroid Sample Returns to Earth Photograph: Tsuyoshi Matsumoto/AP Save this story Save Save this story Save Early on Sunday morning, the skies above a secluded military complex in central Australia will be brightened by a fireball plummeting to Earth. It will be a flamboyant homecoming for the sample return capsule from Hayabusa2, a Japanese spacecraft launched almost exactly six years ago on a mission to shoot an ancient asteroid and steal some of its dirt. If the capsule survives its fiery descent, its payload of pristine space rock will help scientists understand the earliest days of our solar system, shed light on the mysterious origins of meteorites , and may even provide clues about the emergence of life on Earth. By the time it lands under parachute in the Australian outback, the sample will have traveled more than 180 million miles from Ryugu, a diamond-shaped asteroid orbiting the sun between Earth and Mars. Scientists believe that Ryugu broke off from a larger parent body only a few million years ago, but the rocks that compose it are closer to 4 billion years old. Hayabusa2 camped out around Ryugu for more than a year and a half, studying the asteroid from a distance and sending robotic scouts to its surface to prepare for a sample collection. Its main mission was to collect just a few grams of dust and pebbles from this cosmic time capsule that has been preserved for eons in the frigid vacuum of space. “We're hoping to learn a lot about how a giant cloud of gas and dust turned into planets 4.5 billion years ago in our solar system,” says Larry Nittler, a cosmochemist at the Carnegie Institution for Science and one of nine American scientists selected by NASA to participate in the Japanese mission. “Ryugu and other asteroids like it are basically the leftover building blocks that didn't grow into planets and have been floating around ever since.” Ryugu looks like a piece of charcoal the size of several city blocks, and it spins like a top once every eight hours. It is one of the darkest asteroids ever discovered, its inky complexion a result of all the carbon trapped in organic compounds smeared across its surface. Some of these prebiotic compounds, such as amino acids, are the building blocks of life, and it may very well have been asteroids like Ryugu that seeded Earth with the molecular grist that kicked evolution into gear. Carbonaceous asteroids like Ryugu are abundant in our solar system, but they mostly hang out around the outer planets. Every now and then, they bump into each other, break apart, and the pieces are sent on a trajectory toward the sun’s inner sanctum. If those pieces happen to collide with Earth, we call them meteorites. Almost everything we know about them is from the bits and pieces that make it to the surface. But by the time these stones have crash-landed on Earth, they have been cooked to a crisp and have been corrupted by terrestrial chemistry. Sending a probe to a still-orbiting asteroid is the best way to collect a clean sample. As the first spacecraft to visit a carbonaceous asteroid, Hayabusa2 can help determine the provenance of meteorites discovered on Earth and shed some light on the processes that formed the organic compounds in the early solar system. “Are there samples of the organics that we don’t have in our collection because they didn’t survive going through the atmosphere? We don’t know,” says Harold Connolly, a geologist at Rowan University and a member of the sample analysis team for Hayabusa2 and NASA’s own asteroid sample return mission, OSIRIS-REx. But he hopes Hayabusa2 can help solve the mystery. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg There is also a pragmatic reason to visit Ryugu. NASA researchers have identified it as a potentially hazardous asteroid , which means its orbit comes close enough to Earth to create a non-negligible chance of collision. While the risk is small, the complex forces acting on asteroids as they loop around the sun make it difficult to accurately predict their trajectory more than a few decades into the future. For example, when it’s exposed to the sun, an asteroid can release volatile compounds like water, and this outgassing can produce thrust that subtly changes its orbit. “We don't fully understand how asteroids move in detail, because we don’t fully know their composition,” says Connolly. “This will help us better predict hazardous asteroids and when they might hit Earth.” Hayabusa2 is a follow up to Hayabusa, a Japanese mission launched in 2003. It was the world’s first asteroid sample return mission, but a failure with the collection mechanism meant that only a few micrograms of dust made it back to Earth. Like its predecessor, Hayabusa2 was designed to collect samples and deploy small robots on the asteroid’s surface. Hayabusa2 arrived at Ryugu in late 2018 after cruising through the solar system for three years, and a few months later the spacecraft deployed a lander called Mascot and the first of two small Minerva-II rovers. The cylindrical rover spent five weeks hopping around the surface collecting data and sent incredible pictures back to Earth. The shoebox-sized lander lasted just 17 hours before its battery died. During its brief life, Mascot used a suite of instruments to analyze the composition and structure of the asteroid’s regolith. By the end of 2018, the rover and lander had completed their missions and set the stage for Hayabusa2’s descent to the surface. Scooping up some asteroid dirt is harder than it sounds, because Ryugu isn’t solid. Like most asteroids, it’s more like a rubble pile, a loose collection of dust and rocks held together by their own gravity. This makes it tricky to get down to the surface to collect a sample without stirring up a lot of rocks that could damage the spacecraft. Ryugu also turned out to be composed of more large boulders—some up to 10 stories high—than the mission’s scientists expected. “Safe landing locations were limited by the high abundance of rocks,” says Tomokatsu Morota, a planetary scientist at the University of Tokyo and one of the researchers who worked on Hayabusa2’s navigation camera. He says the team had to manually count more than 10,000 rocks and remotely measure more than 100 to narrow down suitable landing sites on the asteroid’s rough surface. “It was very hard work,” Morota says. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg By early 2019 the team had a landing site picked out, and Hayabusa2 made its first descent. The spacecraft’s sample collection horn tapped the surface for only about a second before returning to orbit the asteroid. During that brief encounter, Hayabusa2 fired a small bullet into the asteroid to kick up some dust and trapped it in a collection chamber. A few months later, Hayabusa2 prepared for another collection run by dropping a small plastic explosive from its orbit to create an artificial crater more than 30 feet across , exposing the older rock beneath Ryugu’s surface. Once the debris around the asteroid had settled, the spacecraft made its second brief descent to take a sample from inside the crater. Just a few weeks before Hayabusa2 departed Ryugu, its second Minerva-II rover failed before deployment. But rather than let the rover go to waste, mission controllers released it and conducted a few gravitational measurements before it hit the asteroid. Hayabusa2 will jettison its sample container when it’s about 100,000 miles away from Earth, roughly half the distance between our planet and the moon. Once the capsule has touched down, it will be recovered by a team of Japanese researchers stationed in the scorching Australian desert. It will immediately be brought to a temporary clean room built on site so it can be analyzed for any volatile compounds like water that may have been contained in the sample. Within hours of recovering the capsule, the researchers will puncture its hull and bottle any gases that may have been released by the sample and save them for analysis. After that, the sample will be returned to Japan where researchers at the Japan Aerospace Exploration Agency will distribute small portions to research teams around the world for further study. “Exploring samples with laboratory instruments can tell us their composition, how much heating they have experienced, shock events, water flow events, and so on. You can get an entire history lesson from just a tiny sample,” says Bill Bottke, a planetary scientist at the Southwest Research Institute who was not involved with the Hayabusa2 mission. “Only a portion of this information can be determined by orbiting spacecraft. It is like the difference between seeing a mountain from a distance and studying one of its rocks in the lab.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The Hayabusa2 team won’t know how much asteroid dirt the spacecraft collected until they pry the capsule open, but they’re optimistic that it will be around 10 grams. A significant portion of the sample will be given to NASA researchers, who collaborated closely with Japan on Hayabusa2 as well as OSIRIS-REx. In fact, NASA and the Japanese space agency each tapped a few of their own researchers to help the other agency. Connolly, who was one of the researchers working on both missions, is optimistic that the research done on the Hayabusa2 sample will improve the research done on the much larger OSIRIS-REx sample when it returns to Earth in 2023. “We can apply the lessons learned in the analytical process and the actual information that we manage to tease out of these whispering rocks so that we can prepare better as a community for the analysis of OSIRIS-REx samples,” says Connolly. “My expectation is that they’re going to be complementary and will give us a better picture of the constraints on the earliest solar system processes.” The Hayabusa2 capsule’s return to Earth marks a major milestone for the mission, but it’s not the end of the spacecraft’s journey. After it jettisons its sample this weekend, it will continue on a bonus mission to another asteroid that could last as long as 10 years. This time, it won’t collect any samples, but it will gather valuable data while it orbits the asteroid. You can catch a livestream of the fiery finale of Hayabusa2’s main mission on Japan Aerospace Exploration Agency’s YouTube channel. The capsule is scheduled to begin its atmospheric entry at around 12:30 pm ET on Saturday (or 2:30 am on Sunday in Japan) and will land about 15 minutes later. 📩 Want the latest on tech, science, and more? Sign up for our newsletters ! The strange and twisted tale of hydroxychloroquine I bricked my computer with a BIOS update. But there's hope ! How to escape a sinking ship (like, say, the Titanic ) The future of McDonald's is in the drive-thru lane The few, the tired, the open source coders 🎮 WIRED Games: Get the latest tips, reviews, and more 💻 Upgrade your work game with our Gear team’s favorite laptops , keyboards , typing alternatives , and noise-canceling headphones Staff Writer X Topics Asteroids Japan space exploration Spacecraft space Geology Ramin Skibba Ramin Skibba Swapna Krishna Ramin Skibba Ramin Skibba Ramin Skibba Rebecca Boyle Charlie Wood Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"Why NASA Wants to Go Back to the Moon | WIRED"

"https://www.wired.com/story/why-nasa-wants-to-go-back-to-the-moon"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Ramin Skibba Science Why NASA Wants to Go Back to the Moon Photograph: Joel Kowsky/NASA Save this story Save Save this story Save With the Artemis 1 mission scheduled to blast off in a few weeks, NASA is poised to return to the moon for the first time in half a century. It’s a major step in a formidable plan to launch new spacecraft, assemble a lunar space station, and bring humans back to the moon for the first time since the end of the Apollo program, when astronauts Gene Cernan and Harrison Schmitt were the last people to set foot on the dusty regolith. Artemis 1 will mark the inaugural launch of a 32-story rocket called the Space Launch System , topped by the Orion space capsule. The capsule will fly within 62 miles of the lunar surface, while deploying small spacecraft for research on—and beyond—the moon. Although this first flight will be uncrewed, others with astronauts will follow in the coming years, and Orion is capable of carrying humans farther than any spacecraft has ever flown before. While the momentous Artemis 1 mission includes some research objectives, it serves as a technology demonstration and a symbol. “To all of us who gazed up at the moon, dreaming of the day humankind returns to the lunar surface, we are going back. That journey, our journey, begins with Artemis 1,” said NASA chief Bill Nelson at a virtual press conference in early August. The Artemis 1 launch period begins in late August, with NASA planning for the morning of August 29, and backup dates on September 2 and 5. If the liftoff from NASA’s Kennedy Space Center in Florida, the moon flyby, and Orion’s reentry and splashdown off the coast of San Diego in October go as planned, Artemis 2 will go ahead. On that first crewed mission in 2024, four astronauts will do a moon flyby. Then comes Artemis 3 in 2025 or 2026, the first lunar landing since 1972, which will include the first woman to walk on the moon. Astronauts aboard Artemis 4 in 2027 will deliver the I-HAB module, which will become crews’ main living quarters aboard the Lunar Gateway station in its orbit around the moon. The Artemis program has been in the works since 2017, and so far, it has cost about $40 billion. Its primary goal will be establishing a sustained presence on the moon in the form of a space station and a lunar base camp or colony, as part of NASA’s broader push to prioritize human space travel. “We are beginning a long-term journey of science and exploration,” said Bhavya Lal, an associate NASA administrator, at last week’s press conference. “We have done our early reconnaissance with both robots and humans, and now we are learning what we need to know to be able to spend more time on the moon, and then to prepare for going to Mars and beyond.” Indeed, Artemis fits into NASA’s long-term “Moon to Mars” program, as the space agency envisions sending astronauts to the Red Planet within 20 years. “Everything that we’re doing on the lunar surface, we’re doing to explore for science, and we’re going not just for ‘flags and footprints,’ as some people refer to [Apollo], but also to test out all of the systems that we’ll eventually need to bring down risks for a human mission to Mars,” says Cathy Koerner, a deputy associate administrator at NASA, based at Johnson Space Center in Houston. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg These include the development of the Gateway robotics and habitat modules for crews, as well as a lunar rover, all of which could be precursors for future technologies on Mars. Next-generation spacesuits, to be developed by Axiom Space and Collins Aerospace, will include improved life support and communication systems and would allow for extra mobility. Assuming the early Artemis missions are successful, on subsequent voyages more components will be dispatched to the moon station, and astronauts will be deployed for extended jaunts on the lunar soil, possibly for weeks at a time. “As we’re doing these missions, they’re getting more and more complex. And so the infrastructure to support them gets more and more complex,” Koerner says. Although no passengers will travel on Artemis 1, the capsule will carry along three mannequins. The male one, dubbed Commander Moonikin Campos thanks to a public naming contest, has been used for Orion vibration tests. He will fly alongside two female mannequin torsos, made from materials that mimic the bones, soft tissues, and organs of an adult woman. All of them will be equipped with sensors for detecting space radiation , because prolonged exposure can harm astronauts’ health. (The European Space Agency, which is collaborating with NASA on the flight, is sending along a Shaun the Sheep doll.) The mission will also deploy 10 shoebox-sized spacecraft called CubeSats, some of which will map the moon’s surface and study its pockets of ice, while others will test a space radiation shield or proceed to more distant spots, like a near-Earth asteroid. The Artemis project will also serve as a test bed for technologies developed through public-private partnerships. NASA has already worked with Terran Orbital and Rocket Lab to launch a small spacecraft known as Capstone , which is currently scouting the future orbit of the Lunar Gateway. Maxar Technologies of Westminster, Colorado, will provide Gateway’s power and propulsion, while Northrop Grumman ​​of Dulles, Virginia, is working on the HALO module, a small area where the first Gateway astronauts will live and conduct research. SpaceX will launch both of those on a Falcon Heavy rocket in late 2024. Grand programs also create opportunities for global diplomacy and relationships among space agencies. NASA is working with many international partners on Artemis, with the European Space Agency providing Orion’s service module on Artemis 1 and collaborating on Gateway’s I-HAB. Japan’s space agency is developing a cargo supply spacecraft for Gateway and is looking into the concept of a pressurized moon rover, inside which astronauts would be able to take off their bulky spacesuits. Canada’s space agency is designing a robotic arm for the station. A total of 21 countries have also signed on to the Artemis Accords, the US government’s attempt to establish best practices for future international exploration of the moon. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Yet a project as ambitious as returning to the moon is not always a political winner. It’s expensive, for one thing. Some critics, like former NASA deputy administrator Lori Garver , have called out the ballooning cost of the agency’s building its own Space Launch System—at a time when SpaceX is developing the less expensive Super Heavy rocket, along with the reusable Starship spacecraft. And programs that extend through many presidential administrations with different space priorities can be vulnerable to shifting political winds. Sometimes a program won’t survive a transition in power at the White House. Former US presidents George W. Bush and Donald Trump—who initiated the Artemis program—favored lunar missions, while former president Barack Obama focused on launching humans to Mars. “Artemis has spanned multiple presidential administrations, so that bodes well. But there are still a lot of unknowns, and it’s a large investment,” says Teasel Muir-Harmony, a space historian and curator at the Smithsonian National Air and Space Museum in Washington, DC. Public opinion can shift, as well, Muir-Harmony points out. Many Americans initially opposed the former Kennedy and Johnson administrations’ gigantic investment in the Apollo program—which dwarfs funding for Artemis today, as a fraction of the nation's gross domestic product. But all that changed after the historic moon landing in 1969. The space race with the former Soviet Union also spurred the Apollo program, but today potential competition with China, Russia , or even private space companies doesn’t drive investments in moon exploration the same way. Recent surveys show more public support for NASA’s climate research and efforts to monitor asteroids that could be on a collision course with Earth. (One of the goals of the Artemis program will be sharing off-planet images with the public, meant to inspire new generations, as the iconic Earthrise photo taken by astronaut Bill Anders on Apollo 8 did back in 1968.) While much has changed since the 1960s and ’70s, Muir-Harmony says, the legacy of the Apollo program still looms large. It starts with the name itself: In Greek mythology, Artemis is the twin sister of Apollo. And NASA officials, she says, have made a case that Artemis should go beyond “flags and footprints”—in other words, that it must build on the achievements of Apollo. “Its presence is felt today. When you look at the rationale behind Artemis, when we talk about Artemis, it’s an essential part of that conversation,” she says. “I think it helps to build excitement. There’s a renewing of that sense of purpose. There’s some nostalgia for that, some recognition that Apollo brought a lot of people together and focused them on a really challenging goal, and in doing so it tested the best of our abilities.” You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Staff Writer X Topics NASA moon Artemis astronauts Spacecraft space exploration European Space Agency Ramin Skibba Ramin Skibba Ramin Skibba Ramin Skibba Ramin Skibba Charlie Wood Swapna Krishna Garrett M. Graff Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"The Capstone Launch Will Kick Off NASA’s Artemis Moon Program | WIRED"

"https://www.wired.com/story/the-capstone-launch-will-kick-off-nasas-artemis-moon-program"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Ramin Skibba Science The Capstone Launch Will Kick Off NASA’s Artemis Moon Program Photograph: Dominic Hart/NASA Save this story Save Save this story Save A toaster-sized probe will soon scope out a special orbit around the moon, the path planned for NASA’s Lunar Gateway space station. The Gateway, to be rolled out later this decade, will be a staging point for the astronauts and gear that will be traveling as part of NASA’s Artemis lunar program. The launch of this small yet powerful pathfinding probe will inaugurate the Artemis mission, finally setting the space agency’s ambitious moon projects in motion. The plucky little spacecraft is called Capstone, or, more officially, the Cislunar Autonomous Positioning System Technology Operations and Navigation Experiment. It will be perched atop a Rocket Lab Electron rocket scheduled to blast off on June 27 from the Mahia Peninsula of New Zealand at 9:50 pm local time (5:50 am EDT). If it can't launch that day, it’ll have other opportunities between then and July 27. Launch operators had planned the liftoff for earlier this month but decided to postpone it while updating the flight software. “We’re really excited. It’ll basically be the first CubeSat launched and deployed to the moon,” says Elwood Agasid, the Capstone program manager and deputy program manager for NASA’s Small Satellite Technology Program at Ames Research Center. “Capstone will serve as a pathfinder to better understand the particular orbit Gateway will fly in and what the fuel and control requirements for maintaining orbit around the moon are.” CubeSats pack a lot into tiny spaces, typically at a lower cost than larger satellites. The “cube” refers to a single standard unit, which is about 4 inches on a side. Many CubeSats have a 3U format, with a trio joined to form a configuration about the size of a loaf of bread. Capstone is a 12U spacecraft, or four of those combined. Everything’s designed to fit in that compact box, including a lithium-ion battery and the avionics systems, with the electronics and microcontrollers in charge of propulsion, navigation, and data-handling. Horizontal solar panels extend from both sides of the box, like wings. While plenty of spacecraft have orbited the moon, Capstone’s technology demonstrations will make it unique. In particular, it includes a positioning system that makes it possible for NASA and its commercial partners to determine the precise location of the spacecraft while it’s in lunar orbit. “On Earth, people take for granted that GPS provides that information,” said Bradley Cheetham, CEO of Advanced Space in Westminster, Colorado, and principal investigator of Capstone, at a virtual press conference in May. But GPS doesn’t extend to upper Earth orbits, let alone the moon. Beyond Earth orbit, researchers still rely on ground-based systems to track spacecraft through the Deep Space Network , an international system of giant antennas managed by NASA’s Jet Propulsion Laboratory. Instead, Capstone will provide a spacecraft-to-spacecraft navigation system, taking advantage of the Lunar Reconnaissance Orbiter that’s already there. The pair will communicate with each other and measure the distance between them and each of their positions, independent of ground systems, Cheetham said. Capstone will cruise to the moon on a roundabout route called a ballistic lunar transfer, which expends little energy but takes three months for the trip. (Astronauts will travel on a more direct trajectory over just a few days.) Then Capstone will soar into an oval-shaped near-rectilinear halo orbit, or NRHO, which goes around the moon over the course of a week, separated from it by 43,500 miles at its furthest point. This path has the advantage of balancing the gravitational pull of the Earth, moon, and sun, thereby limiting fuel usage, which will be important for the Gateway station. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The NRHO is also always in view of the Earth, never behind the moon, so that Gateway will be able to stay in constant communication with other lunar spacecraft and with mission control on Earth, says Marc Bell, CEO of Terran Orbital, which designed and built the spacecraft: “We’re building a comms network for the moon. How much cooler does it get?” Once Capstone arrives in lunar orbit, its navigation system will be tested, while engineers on Earth monitor its fuel consumption and make sure that it maintains its unique orbit. That will help them gauge how much energy the future Gateway station will likely need. “It’s kind of rare in our field of spacecraft trajectory design to actually get to send a physical experiment up into space before we do the real thing,” says Diane Davis, the mission design lead for NASA’s Gateway program. “I’m super excited to see how it performs out there.” Once Gateway is built, it will be centered around two crew cabins, which will be connected to a science and cargo module, a service module, an airlock, and other elements. It will be a distant outpost, smaller than the International Space Station , and it will host a handful of astronauts at a time, including those coming from Earth and those using it as a base camp for treks down to the moon. The Capstone mission involves a collaboration between NASA and industry, and it benefits from the agency’s Small Business Innovation Research program, Agasid says. In addition to Advanced Space, which owns and operates the spacecraft, they partnered with Tyvak Nano-Satellite Systems of Irvine, California, a Terran Orbital company, for the CubeSat platform and with Stellar Exploration of San Luis Obispo, California, for the propulsion system. Rocket Lab provided the Electron launch vehicle and upper stage called Lunar Photon. (A small spacecraft doesn’t need to fly on a huge rocket; the diminutive Electron is only about one-fourth as tall as a SpaceX Falcon 9 , and NASA’s Space Launch System towers above that.) All that adds up to just under $10 million in launch costs and slightly less than $20 million in mission costs—an affordable sum for a trip to the moon. NASA is working with other commercial partners for the Gateway space station, including Northrop Grumman and Maxar for the first crew cabin and the solar electric propulsion system, and with the European and Japanese space agencies. Those first components are scheduled to launch in 2024 on a SpaceX Falcon Heavy, and crew will visit and aid the assembly after that. “Once it’s fully constructed, crew will use it for science and as a staging location for lunar surface missions,” Davis says. “One of the goals is to show these deep-space technologies in action in our nearish neighborhood before we use those to get us out to Mars.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg This summer, NASA will take several other big steps on its journey back to the moon and potential future missions to Mars. First, the agency must decide whether to conduct further tests on the Space Launch System , the massive rocket that will be used for the Artemis 1 launch. The rocket was recently rolled out to the launch pad at Cape Canaveral, and NASA’s SLS team nearly completed a practice countdown test on Monday. If NASA chooses to move ahead with it, the Artemis 1 flight could launch as soon as August. The SLS and an uncrewed Orion spacecraft will orbit the moon and deploy 10 CubeSats for a variety of secondary missions. Artemis 2, the first crewed mission, will make a lunar flyby in 2024. And then Artemis 3, planned for 2025, will send some astronauts to Gateway while the others will make NASA’s first moon landing since the Apollo program a half-century ago. The crew will also be sporting new space suits for exploring the moon’s terrain. But first, Capstone has to scout ahead of them and check how well its new navigation technologies work. “We’re excited to demonstrate some of these capabilities and use them for the next mission,” Agasid says. “We’re all impatient, as usual.” Courtesy of Rocket Lab 📩 The latest on tech, science, and more: Get our newsletters ! The takedown of the web’s biggest child abuse site Get ready for a decade of uranus jokes How to use BeReal , the “unfiltered” social media app Should all video games be replayable? The fake agents case baffling US intelligence experts 👁️ Explore AI like never before with our new database 📱 Torn between the latest phones? Never fear—check out our iPhone buying guide and favorite Android phones You Might Also Like … 📩 Get the long view on tech with Steven Levy's Plaintext newsletter Watch this guy work, and you’ll finally understand the TikTok era How Telegram became a terrifying weapon in the Israel-Hamas War Inside Elon Musk’s first election crisis —a day after he “freed” the bird The ultra-efficient farm of the future is in the sky The best pickleball paddles for beginners and pros 🌲 Our Gear team has branched out with a new guide to the best sleeping pads and fresh picks for the best coolers and binoculars Staff Writer X Topics Spacecraft rockets moon Artemis NASA space satellites Ramin Skibba Ramin Skibba Ramin Skibba Ramin Skibba Ramin Skibba Rhett Allain Ramin Skibba Swapna Krishna Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"NASA’s Huge SLS Rocket Finally Launches the Artemis 1 Moon Mission | WIRED"

"https://www.wired.com/story/artemis-1-nasa-moon-mission-launch-sls-rocket-orion"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons Ramin Skibba Science NASA’s Huge SLS Rocket Finally Launches the Artemis 1 Moon Mission Photograph: Bill Ingalls/NASA Save this story Save Save this story Save After years of delays and several false starts, the wait is finally over: NASA’s massive Space Launch System rocket and the Orion capsule lifted off at 1:48 am Eastern time, heading for a historic lunar flyby. Crowds of onlookers watched at the Kennedy Space Center in Florida, where the thunder of a NASA rocket could once again be heard at the launchpad where shuttles and the Apollo missions began their journeys into space. The 212-foot rocket, including an orange core stage and two white solid rocket boosters, had rested upon a ground structure called the mobile launcher, as it had during earlier tests. As the boosters ignited, the rocket lifted above an explosion of flames, and then it quickly cleared the launch tower and began its ascent through the atmosphere, an ombre orange streak blazing behind it. “Liftoff for Artemis 1,” proclaimed Derrol Nail, NASA’s livestream commentator. “We rise together, back to the moon and beyond.” After the two-minute mark, the SLS boosters finished burning through their propellant and fell away. About eight minutes after launch, the core stage rocket used up its fuel and separated too. That left the uncrewed Orion capsule still attached to the upper-stage rocket and the service module, provided by the European Space Agency, which supplies the spacecraft’s main propulsion and power. Orion continued on at over 16,000 miles per hour, and a few minutes later it deployed its solar arrays. If the mission goes according to plan, after about two hours, the capsule will separate from the SLS upper stage. As it drifts away, the upper stage will then disperse—in batches—10 small spacecraft known as CubeSats, sending them out to conduct mini missions around the moon, Mars, and a near-Earth asteroid. Meanwhile Orion will fly on, taking about 10 days to reach the moon, where it will spend a couple of weeks in what’s called a “distant retrograde orbit,” which balances the gravitational pull of the Earth and moon and doesn’t take much fuel to maintain. While circling the moon, it will take images of the Earth and its satellite—including one like the iconic “Earthrise” photo taken on the Apollo 8 mission—and collect space radiation data so that scientists can learn more about potential health risks for astronauts on extended trips beyond the Earth’s protective atmosphere. At the end of November, Orion will leave that orbit and cruise 40,000 miles beyond the moon—the farthest a spacecraft capable of carrying humans has ever traveled—before slingshotting back past it en route to Earth in early December. Its 26-day trip will end when it splashes down under parachutes into Pacific Ocean waters about 50 miles off the coast of San Diego, probably on December 11. Members of the Artemis mission team are ecstatic that this moment has arrived—and also anxious about the first major moonshot since the Apollo era. “I'm excited to kick off this Artemis mission series to go back to the moon and basically start a new era that will represent deeper space exploration, and on to Mars one day. I’m most excited to watch that rocket turn night into day tonight when it takes off. It’s going to be spectacular,” said NASA astronaut Christina Koch, speaking earlier Tuesday before the launch. There will be many scientific, economic, and other benefits to the Artemis program , she says, thanks to NASA’s international and commercial partnerships, and it will help inspire the next generation of space explorers. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The mission is intended to be the first of many, all part of NASA’s ambitious back-to-the-moon program. In mid-2024, Artemis 2 will carry four astronauts aboard Orion—Koch is a potential candidate—as it performs a similar maneuver around the moon. Then in 2025 or 2026, Artemis 3 will bring astronauts back to the lunar surface, including the first woman to land on the moon. In 2027, Artemis 4 will deliver the living quarters module for the Lunar Gateway, a new space station to be assembled in orbit around the moon. ( NASA’s small Capstone spacecraft , which is on a pathfinder mission, arrived in Gateway’s future orbit on Sunday.) On future crewed Artemis missions, astronauts will add modules and equipment to Gateway. Today’s much-awaited launch was not the space agency’s first try. An attempt on August 29 was scrubbed when a liquid hydrogen leak was discovered with the third RS-25 engine. A second shot on September 3 was also called off due to a hydrogen leak—this time, it was larger. While NASA has plenty of experience with liquid hydrogen leaks during space shuttle launch attempts, the SLS is a new rocket, and it poses new challenges. The team next tried a “kinder, gentler loading approach” to tanking, using less pressure to push the propellant through the lines to the core-stage rocket, said Brad McCain, vice president of Jacobs Space Operations Group, the prime contractor for NASA’s Exploration Ground Systems, at a press conference in September. That worked during a tanking test on September 21. Still, the Artemis team’s would-be third launch attempt on September 27 was canceled when Hurricane Ian came rumbling in , forcing the team to roll back the rocket to the Vehicle Assembly Building for protection. Earlier this month, they trundled the rocket back to the pad in anticipation of a November 14 launch, just as Tropical Storm Nicole—soon to elevate to hurricane strength—grew on the horizon. NASA considered moving the rocket into shelter again, but that would have entailed some risks. Standing on the launchpad, parts of the rocket can tolerate sustained winds of up to 74 knots. But it’s more vulnerable if it’s on the crawler, the slow-moving machine that would be used to bring it indoors. In the end, there wasn’t enough time to deliver it to shelter. The team made the call to leave the rocket on the pad and push the launch date to November 16. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg Hurricane Nicole brought strong winds, including some around the 74-knot level. But NASA personnel assessed that storm damage to the SLS rocket and Orion capsule was minor. A very thin strip of caulk or insulation at the base of Orion’s protective nose cone had come loose, and they detected an electrical connection issue with a cable involved in the liquid hydrogen fueling of the rocket. While there’s a chance more of that caulk-like material could be stripped off during launch, the Artemis team deemed this a minimal risk, said Mike Sarafin, the Artemis mission manager, at a press conference on Monday. They decided to press ahead. “I’m extremely proud of the resilience of this team. It was a bit of a letdown when we had to roll back for Hurricane Ian, but then by the next day, everyone was super focused on what work we needed to do. It was a similar story for Hurricane Nicole,” said Jeremy Parsons, deputy manager of NASA’s Exploration Ground Systems at Kennedy Space Center, at that press briefing. Countdown procedures started up again at 1:24 am Eastern time Monday morning. The launch team and US Space Force meteorologists confirmed that the weather was 80 percent favorable, with no more hurricanes on the way. The team began gradually going through their checklist of 489 launch criteria. On Tuesday afternoon, they began filling the big orange fuel tank with more than 700,000 gallons of liquid hydrogen and liquid oxygen, supercooled to a frigid -423 and -297 degrees Fahrenheit. Finally, with 10 minutes left, launch director Charlie Blackwell-Thompson and the team made the call that they were “go” for launch. Speaking just a few minutes later, she told the team: “You have earned your place in history. You are part of a first. That doesn’t come along very often—once in a career, maybe. We are all part of something incredibly special: the first launch of Artemis. The first step in returning our country to the moon and on to Mars. What you have done today will inspire generations to come. So thank you for your resilience. The harder the climb, the better the view. We showed the Space Coast tonight what a beautiful view it is.” Artemis 1 should be considered a “test flight,” Parson says. That means even if some conditions aren’t ideal, they’re not likely to abort the mission mid-flight. At a NASA press conference in August, Sarafin underscored this point. “This is the first flight of a new rocket and new spacecraft, and it does carry inherent risk,” he said. “We have a ‘lean forward’ strategy to get our high-priority objective, which is to demonstrate the heat shield at reentry conditions [from the moon]. We would be ‘go’ on this flight for conditions that we’d normally be ‘no go’ on a crewed flight, in the interest of crew safety.” Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The Artemis team will be watching to see how Orion’s heat shield handles the scorching 5,000 degrees Fahrenheit during reentry through the atmosphere at about 25,000 miles per hour (or Mach 32, if you’re counting). The heat shield involves a special material called Avcoat, which is built into connected blocks at the bottom of Orion. As it heats up, parts of it slough off. Such heat shields have never been tested at the speeds a spacecraft returning from the moon will experience. The team will also be checking to see that the communication and navigation systems work well, supplemented by NASA’s Near Space Network of ground stations in Chile and South Africa. They’ll collect radiation data from sensors worn by the three mannequins riding onboard—including one dubbed “Commander Moonikin Campos”—plus data about the spacecraft’s trajectory and the temperature of the crew module. And they will be making sure that the three parachutes deploy properly, slowing the spacecraft to about 20 miles per hour. As Orion splashes down, NASA officials will work with a Navy recovery ship, including divers and team members on inflatable boats, so that they can safely and quickly retrieve the spacecraft, since there will be astronauts aboard next time. Orion’s return will set the stage for Artemis 2—and for even more far-flung trips to Mars. But it all depends on a first mission that demonstrates humankind is ready to take its next giant leap. You Might Also Like … 📨 Make the most of chatbots with our AI Unlocked newsletter Taylor Swift, Star Wars, Stranger Things , and Deadpool have one man in common Generative AI is playing a surprising role in Israel-Hamas disinformation The new era of social media looks as bad for privacy as the last one Johnny Cash’s Taylor Swift cover predicts the boring future of AI music Your internet browser does not belong to you 🔌 Charge right into summer with the best travel adapters , power banks , and USB hubs Staff Writer X Topics NASA moon Artemis rockets space apollo Ramin Skibba Ramin Skibba Ramin Skibba Ramin Skibba Ramin Skibba Swapna Krishna Rebecca Boyle Garrett M. Graff Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "

"We’re All Living Under Gravity’s Rainbow | WIRED"

"https://www.wired.com/story/living-under-gravitys-rainbow-thomas-pynchon"

"Open Navigation Menu To revist this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revist this article, visit My Profile, then View saved stories. Close Alert Search Backchannel Business Culture Gear Ideas Science Security Merch Podcasts Video Artificial Intelligence Climate Games Newsletters Magazine Events Wired Insider Jobs Coupons By John Semley Backchannel We’re All Living Under Gravity’s Rainbow ILLUSTRATION: TEO GEORGIEV Save this story Save Save this story Save Black curtains hang in the windows of a dinky suburban LA apartment, two blocks from the Pacific, blotting out the light. Inside, Thomas Pynchon—early thirties, awkward, with a Zappa ’stache—scribbles on reams of graph paper. The scene is spartan: a cot, some books, a messy pile of correspondence, a collection of chintzy piggy banks. On his desk sits an ad hoc model rocket, jerry-rigged together from a paper clip and an old pencil eraser. A friend of Pynchon's described the vibe in a gentlemen’s magazine as “a monk’s cell decorated by the Salvation Army.” Outside, the world rages on. The Watts riots. LSD. The Space Race. Watergate. The Bomb. Society is seized by one roiling convulsion after the next. Fantasies of post-WWII prosperity curdle into generational revolt, paranoia, and duck-and-cover drills. At his desk, Pynchon is processing it all, absorbing it—like Emerson’s transparent eyeball, but hyper-dilated and a bit bleary from too much Panama Red. What sent the world reeling? To get to the bottom of such a Big Question, Pynchon must have read widely: about synthetic chemistry and Calvinist prophecy and Kabbalah and Turkic alphabet reform. But most of all, it seems, he read about rockets. There is a point in a rocket’s parabola called Brennschluss (“burnout,” in German). It marks the moment at which the missile exhausts its fuel and continues its trajectory aided only by momentum and the force of gravity. As he frames it in his seminal novel Gravity’s Rainbow , World War II—with its missiles and death camps and atomic bombs that sealed humanity’s suicidal covenant with technology—was civilization’s Brennschluss, and we have been in free fall ever since. February 2023 marks the 50th anniversary of Gravity’s Rainbow. A controversial literary sensation when it was published—it was infamously snubbed by Pulitzer higher-ups, despite unanimous recommendation from the fiction jury—the novel has since gathered a daunting reputation. Like Ulysses , The Recognitions , and Infinite Jest , Gravity’s Rainbow is the kind of book people pretend to read to appear smart while riding the bus. A New York magazine critic once dubbed it “perhaps the least-read must-read in American history.” This reputation does an obvious disservice to the book itself, and to a potential audience of curious readers. The time to pick up Gravity’s Rainbow is now. It is at once a busy almanac of its era and a sort of field guide for our own. It echoes eerily in the new-ish millennium. In a way, our own age’s greasy stew of absurdity and apocalypticism, creeping death tinged with clown-shoe idiocy, suggests a world that has finally, fatefully, caught up with Pynchon. We are still living under Gravity’s Rainbow. If anyone knows anything about the author, it’s that nobody knows a whole lot about him. Arguably the most committed living mystery in American letters, Pynchon practically makes Cormac McCarthy look like some literary gadfly. After graduating from Cornell in 1959, Pynchon moved to Seattle, where he wrote technical literature and internal newsletters for Boeing. It was there that he became intimately familiar with the science, logistics, and jargon of heavy weapons manufacturing and the emerging aerospace industry. It was also where he began honing his own literary style—in one article, he compares the relationship between the US Air Force and private aerospace contractors to a happy marriage, copping an ironic tone that would later define his fiction. Pynchon was, for a brief period, essentially a functionary (albeit a cheeky, sarcastic functionary) within America’s expanding military-industrial complex. This means he knew about ballistics. And rockets. And what these weapons were capable of doing, not only to their intended targets but to the souls of those who wrought them. Anti-war, anti-capitalist, and prolifically vulgar, Gravity’s Rainbow is a novel of ideas, big and small. Across 700-plus pages, Pynchon teases out a hefty head trip of plots and subplots, introduces hundreds of characters, and riffs on rocket science, cinema, Germanic runology, Pavlovian behaviorism, probability theory, witchcraft, futurism, zoot-suit couture, psychedelic chemistry, and the annihilation of the dodo. But there is, amid the novel’s encyclopedic remit, something like a story. The V-2 rocket violated basic conceptions of cause and effect. Gravity’s Rainbow unfolds within this discombobulation. It’s the tale of Tyrone Slothrop, a Harvard-educated, Massachusetts blue blood. Because the waypoints of his sexual encounters seem to match perfectly with the Nazis’ V-2 rocket strikes in London, a small cadre of Allied intelligence operatives believe he possesses a strange magnetism, or magic. Various factions push Slothrop around like a pawn, wielding him in service of their schemes, as he winds through the Zone (the moniker given to postwar Germany) on a woozy, picaresque adventure. He rescues a damsel from an enormous octopus. Dressed in a stolen cape and mangled Wagnerian opera helmet, he recasts himself as the superhero Rocketman and recovers a brick of hash hidden at Potsdam. He meets Mickey Rooney, fornicates prolifically, gets in a high-altitude cream-pie fight, and narrowly avoids castration. Along the way, he scrambles for information about a mysterious rocket known only as the 00000 and tries to parse his own motivations from those imposed on him. Which moves are Slothrop making freely? And which are being guided by some ominous, invisible hand? It’s one lackey’s quest to unshackle himself from stoogedom. Slothrop’s weird odyssey, and the novel’s seeming chaos, are ordered by one thing: the rocket. A V-2 rocket is the first thing the reader encounters in the novel’s opening lines: “A screaming comes across the sky. It has happened before, but there is nothing to compare it to now.” The Nazi weapon broke the sound barrier: It exploded before anyone heard it coming. No warning. The V-2 violated basic conceptions of cause and effect. Gravity’s Rainbow unfolds within this discombobulation. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg In this world, the rocket means different things to different people. For the Nazi mystic Captain Blicero (father of the 00000), the rocket will catalyze humanity’s ascension to a higher realm of being. For the African revolutionary Enzian, the rocket is a weapon of global genocide that will force the colonial project to its logical conclusion. For Slothrop, the rocket is the key to his own history and deep family ties to vast conspiracies that date at least as far back as the Puritan migration to New England. (Slothrop is, like Pynchon, a descendant of the first wave of colonists who settled the Massachusetts Bay.) The rocket hangs over the action of the novel, drawing together scores of characters and plots, giving contour both to the narrative and to Pynchon’s own clear-eyed vision of the future. Pynchon’s rocket mania may seem, like so many elements of Rainbow ’s post-hippie milieu, squarely a product of its time. At the novel’s publication, America’s dreams of conquering the heavens were abating. The Apollo 11 moon landing effectively ended the US-Soviet Space Race. By 1971, an Apollo astronaut was shagging golf balls on the lunar surface, definitive proof (if we needed it) that the starry-eyed conquest of space would be bound not by technology but by the perimeter of the American imagination. Wild-eyed rocket mysticism was replaced by projections of all-American middle-class idleness. But for Pynchon, the rocket was more than a voguish, phallic expression of ideological dominance. It encapsulated the whole century. It was the pinnacle of science, human ingenuity, and the dream life of a whole species who fantasized about trekking through the stars, wrapped up in a weapon of death. Not only did the rocket breach Earth’s atmosphere and mark humanity’s first foray into outer space, it also transcended the piddly matters of ideology around which the 20th century ostensibly revolved. Indeed, even NASA’s giant leaps were as much German triumphs as American ones. America’s rocketry know-how was essentially purchased wholesale. The US military eagerly recruited Nazi scientists. True believers like Walter Dornberger, Wernher von Braun, and dozens of others were secreted away to develop missile and rocket technology for NASA, Bell, and Boeing. Some have speculated that Gravity’s Rainbow is itself a kind of long-form mea culpa, in which Pynchon reckons with his own stint of active complicity within a system optimized for the delivery of death. To go a step further, one may even consider that Pynchon’s desire to drop out of public life is in some sense a response to this: a way of deliberately extricating himself, Slothrop-style, from societal systems, in his case of literary celebrity. Why bother with an absurdist novel that’s now only as absurd as reality itself? Throughout the book, matters of politics or patriotism are steamrolled by corporations, which (like the rocket) transcend nations and their trifling differences. “The true war,” as one character observes, “is a celebration of markets.” Pynchon name-checks Shell Oil, I.G. Farben, and other concerns whose business interests cut across battle lines. A chemical pitchman named Wimpe proudly proclaims that his “little chemical cartel is the model for the very structure of nations.” Another character, Clayton Chiclitz, is a toy manufacturer who recruits war orphans to scrounge for black market bric-a-brac. By the time of Pynchon’s The Crying of Lot 49 (set some 20 years after the events of Rainbow ), Chiclitz has moved from peddling children’s playthings to heavy weaponry, heading up a mega-corp called Yoyodyne. This idea of the corporation supplanting the nation-state—what critic Edward Mendelson termed “Pynchon’s new internationalism”—proved the author’s most prescient forecast. In 1973, in the throes of the Cold War , the notion that nations and ideologies would be incidental might have seemed like the stuff of pulpy sci-fi. Before Don DeLillo and George Romero showed supermarkets and shopping malls as temples of spiritual longing, decades before Fukuyama proclaimed “the end of history,” Pynchon saw that the new world order was incorporation: a technological arrangement of global capital that would defy nationality and morality. Fifty years later, that consolidation of power seems total. Individual empires rival many countries’ GDPs. Private industrialists have effectively realized the fantasy of Pynchon’s deranged Captain Blicero, who calls his rocket launchpad/sex dungeon his “Little State.” And the real men who order all this capital (some of the wealthiest in the world) have now, like their predecessors in the dying empires of old, become obsessed with that most Pynchonian totem of megalomaniacal techno-vanity: the rocket. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg The hifalutin fantasies of space conquest and rocket mysticism have been taken up by multibillionaires like Jeff Bezos , Richard Branson , and Elon Musk. They have minted their own rocket cartels and framed their own schemes of earthbound exploitation around delusional dreams of conquering the stars. Keep the yokels gazing skyward, preoccupied with what Walter Dornberger, the head of the Nazi’s V-2 program, called the “ancient dream” of space travel , or with the sci-fi fantasy of bustling Martian colonies , and maybe they won’t notice what you’re up to here on boring ol’ Planet Earth. It is Pynchonian history, come to life. That the world has, rather despairingly, finally caught up with Gravity’s Rainbow poses another impediment to actually reading the book. Why bother with an absurdist novel that’s now only as absurd as reality itself? The nondespairing answer, for me, is always Pynchon’s imagination. It’s like his brain has an antenna tuned to a weird frequency that vibes outside the conceptual spectrum of most people. And for all of Rainbow ’s dismal prognostications about our corporatized, death-obsessed future (er … present), for all its chronicling of the foreclosure of the frontier of human possibility, Pynchon serves up countless images and ideas that baffle and inspire: a village ruled by a roving pack of dogs, a sentient light bulb on a revolutionary crusade against the Man, a mind-boggling sequence in which the novel’s characters appear to bust through the fourth wall and invade the real world of the reader. He is always thinking outside of a world that feels increasingly boxed-in. And while lively and entertaining in their own right, his po-mo flights of writerly fancy are grounded in a deeply serious intellectual program. Some Marxist thinkers maintain that everything in history happens (at least) twice: first as tragedy, then as farce. Put another way: “It has happened before, but there is nothing to compare it to now.” But Pynchon’s theory of history offers its own immanent critique. It is attentive to how systems of technology, power, and information shape the world. It is the anti-Great Man theory of history, sympathetic to the stooges, geeks, schemers, and naive dreamers who strive, however vainly, to resist or—like Slothrop—elude them. History is grotesque and caricatured to begin with, and it only repeats itself in increasingly stupefying forms, like a string of Hollywood remakes diluting the spirit of the original. Business What Sam Altman’s Firing Means for the Future of OpenAI Steven Levy Business Sam Altman’s Sudden Exit Sends Shockwaves Through OpenAI and Beyond Will Knight Gear Humanity’s Most Obnoxious Vehicle Gets an Electric (and Nearly Silent) Makeover Boone Ashworth Security The Startup That Transformed the Hack-for-Hire Industry Andy Greenberg How can anyone look at Elon Musk desperately currying the favor of a tweeter called “Catturd” or Donald Trump hawking digital trading cards that depict him as a spaceman, or a packet of supposedly feminist M&Ms, or watch the “Q Shaman” playact an insurrection, or track conversations about the merits of computer-generated “synthetic art,” or read in the news that we’re all accidentally consuming a credit card’s worth of plastic a week (why is “a credit card” the metric?!), and not feel like they’re living in Pynchonland? Even the Atomic Age threat of global apocalypse is back, thanks to escalating nuclear tensions and impending environmental collapse. The figure of the rocket dangles precariously overhead, just as it does in the closing pages of Gravity’s Rainbow , as the Doomsday Clock ticks closer to midnight. By the time we hear the boom, it will be too late. Correction, February 24, 2023: This article was updated to more accurately describe the rocketry concept of Brennschluss. If you buy something using links in our stories, we may earn a commission. This helps support our journalism. Learn more. Let us know what you think about this article. Submit a letter to the editor at [email protected]. You Might Also Like … 📧 Find the best bargains on quality gear with our Deals newsletter “ Someone is using photos of me to talk to men” First-gen social media users have nowhere to go The truth behind the biggest (and dumbest) battery myths We asked a Savile Row tailor to test all the “best” T-shirts you see in social media ads My kid wants to be an influencer. Is that bad? 🌞 See if you take a shine to our picks for the best sunglasses and sun protection Contributor X Topics longreads Books military tech conspiracy theories rockets Brendan I. Koerner Brandi Collins-Dexter Andy Greenberg Steven Levy Lauren Smiley Angela Watercutter Facebook X Pinterest YouTube Instagram Tiktok More From WIRED Subscribe Newsletters Mattresses Reviews FAQ Wired Staff Coupons Black Friday Editorial Standards Archive Contact Advertise Contact Us Customer Care Jobs Press Center RSS Accessibility Help Condé Nast Store Do Not Sell My Personal Info © 2023 Condé Nast. All rights reserved. Use of this site constitutes acceptance of our User Agreement and Privacy Policy and Cookie Statement and Your California Privacy Rights. WIRED may earn a portion of sales from products that are purchased through our site as part of our Affiliate Partnerships with retailers. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. Ad Choices Select international site United States LargeChevron UK Italia Japón Czech Republic & Slovakia "