Datasets:

siavava

/

ai-tech-articles

like 7

"How AI could be used to make life and death decisions | MIT Technology Review"

"https://www.technologyreview.com/2022/10/13/1060945/artificial-intelligence-life-death-decisions-hard-choices"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts The messy morality of letting AI make life-and-death decisions Automation can help us make hard choices, but it can’t do it alone. By Will Douglas Heaven archive page Exit International In a workshop in Rotterdam in the Netherlands, Philip Nitschke—“Dr. Death” or “the Elon Musk of assisted suicide” to some—is overseeing the last few rounds of testing on his new Sarco machine before shipping it to Switzerland, where he says its first user is waiting. This is the third prototype that Nitschke’s nonprofit, Exit International, has 3D-printed and wired up. Number one has been exhibited in Germany and Poland. “Number two was a disaster,” he says. Now he’s ironed out the manufacturing errors and is ready to launch: “This is the one that will be used.” A coffin-size pod with Star Trek stylings, the Sarco is the culmination of Nitschke’s 25-year campaign to “demedicalize death” through technology. Sealed inside the machine, a person who has chosen to die must answer three questions: Who are you? Where are you? And do you know what will happen when you press that button? Here’s what will happen: The Sarco will fill with nitrogen gas. Its occupant will pass out in less than a minute and die by asphyxiation in around five. A recording of that short, final interview will then be handed over to the Swiss authorities. Nitschke has not approached the Swiss government for approval, but Switzerland is one of a handful of countries that have legalized assisted suicide. It is permitted as long as people who wish to die perform the final act themselves. Nitschke wants to make assisted suicide as unassisted as possible, giving people who have chosen to kill themselves autonomy, and thus dignity, in their final moments. “You really don’t need a doctor to die,” he says. Because the Sarco uses nitrogen, a widely available gas, rather than the barbiturates that are typically used in euthanasia clinics, it does not require a physician to administer an injection or sign off on lethal drugs. At least that’s the idea. Nitschke has not yet been able to sidestep the medical establishment fully. Switzerland requires that candidates for euthanasia demonstrate mental capacity, Nitschke says, which is typically assessed by a psychiatrist. “There’s still a belief that if a person is asking to die, they’ve got some sort of undiagnosed mental illness,” he says. “That it’s not rational for a person to seek death.” He believes he has a solution, however. Exit International is working on an algorithm that Nitschke hopes will allow people to perform a kind of psychiatric self-assessment on a computer. In theory, if a person passed this online test, the program would provide a four-digit code to activate the Sarco. “That’s the goal,” says Nitschke. “Having said all that, the project is proving very difficult.” Nitschke’s mission may seem extreme—even outrageous—to some. And his belief in the power of algorithms may prove to be overblown. But he is not the only one looking to involve technology, and AI in particular, in life-or-death decisions. Related Story Yet where Nitschke sees AI as a way to empower individuals to make the ultimate choice by themselves, others wonder if AI can help relieve humans from the burden of such choices. AI is already being used to triage and treat patients across a growing number of health-care fields. As algorithms become an increasingly important part of care, we must ensure that their role is limited to medical decisions, not moral ones. Medical care is a limited resource. Patients must wait for appointments to get tests or treatment. Those in need of organ transplants must wait for suitable hearts or kidneys. Vaccines must be rolled out first to the most vulnerable (in countries that have them). And during the worst of the pandemic, when hospitals faced a shortage of beds and ventilators, doctors had to make snap decisions about who would receive immediate care and who would not—with tragic consequences. The covid crisis brought the need for such choices into harsh focus—and led many to wonder if algorithms could help. Hospitals around the world bought new or co-opted existing AI tools to assist with triage. Some hospitals in the UK that had been exploring the use of AI tools to screen chest x-rays jumped on those tools as a fast, cheap way to identify the most severe covid cases. Suppliers of this tech, such as Qure.ai, based in Mumbai, India, and Lunit, based in Seoul, Korea, took on contracts in Europe, the US, and Africa. Diagnostic Robotics, an Israeli firm that supplies AI-based triage tools to hospitals in Israel, India, and the US, has said it saw a sevenfold jump in demand for its technology in the first year of the pandemic. Business in health-care AI has been booming ever since. This rush to automate raises big questions with no easy answers. What kinds of decision is it appropriate to use an algorithm to make? How should these algorithms be built? And who gets a say in how they work? Rhema Vaithianathan, the director of the Centre for Social Data Analytics and a professor at the Auckland University of Technology in New Zealand, who focuses on tech in health and welfare, thinks it is right that people are asking AI to help make big decisions. “We should be addressing problems that clinicians find really hard,” she says. One of the projects she is working on involves a teen mental-health service, where young people are diagnosed and treated for self-harming behaviors. There is high demand for the clinic, and so it needs to maintain a high turnover, discharging patients as soon as possible so that more can be brought in. Doctors face the difficult choice between keeping existing patients in care and treating new ones. “Clinicians don’t discharge people because they’re super scared of them self-harming,” says Vaithianathan. “That’s their nightmare scenario.” Even when AI seems accurate, scholars and regulators alike call for caution. Vaithianathan and her colleagues have tried to develop a machine-learning model that can predict which patients are most at risk of future self-harming behavior and which are not, using a wide range of data, including health records and demographic information, to give doctors an additional resource in their decision-­making. “I’m always looking for those cases where a clinician is struggling and would appreciate an algorithm,” she says. The project is in its early stages, but so far the researchers have found that there may not be enough data to train a model that can make accurate predictions. They will keep trying. The model does not have to be perfect to help doctors, Vaithianathan says. They are not the only team trying to predict the risk of discharging patients. A review published in 2021 highlighted 43 studies by researchers claiming to use machine-learning models to predict whether patients will be readmitted or die after they leave hospitals in the US. None were accurate enough for clinical use, but the authors look forward to a time when such models “improve quality of care and reduce health-care costs.” And yet even when AI seems accurate, scholars and regulators alike call for caution. For one thing, the data that algorithms follow and the way they follow it are human artifacts, riddled with prejudice. Health data is overpopulated by people who are white and male, for example, which skews its predictive power. And the models offer a veneer of objectivity that can lead people to pass the buck on ethical decisions, trusting the machine rather than questioning its output. This ongoing problem is a theme in David Robinson’s new book, Voices in the Code , about the democratization of AI. Robinson, a visiting scholar at the Social Science Matrix at the University of California, Berkeley, and a member of the faculty of Apple University, tells the story of Belding Scribner. In 1960 Scribner, a nephrologist in Seattle, inserted a short Teflon tube known as a shunt into some of his patients’ arms to prevent their blood from clotting while they underwent dialysis treatment. The innovation allowed people with kidney disease to stay on dialysis indefinitely, transforming kidney failure from a fatal condition into a long-term illness. When word got out, Scribner was inundated with requests for treatment. But he could not take everyone. Whom should he help and whom should he turn away? He soon realized that this wasn’t a medical decision but an ethical one. He set up a committee of laypeople to decide. Of course, their choices weren’t perfect. The prejudices at the time led the committee to favor married men with jobs and families, for example. The way Robinson tells it, the lesson we should take from Scribner’s work is that certain processes—bureaucratic, technical, and algorithmic—can make difficult questions seem neutral and objective. They can obscure the moral aspects of a choice—and the sometimes awful consequences. “Bureaucracy itself can serve as a way of converting hard moral problems into boring technical ones,” Robinson writes. This phenomenon predates computers, he says, “but software-based systems can accelerate and amplify this trend. Quantification can be a moral anesthetic, and computers make that anesthetic easier than ever to administer.” Whatever the process, we need to let that moral anesthetic wear off and examine the painful implications of the decision at hand. For Scribner, that meant asking an open panel of laypeople—instead of a group of ostensibly objective doctors meeting behind closed doors—whom to save. Today, it could mean asking for high-stakes algorithms to be audited. For now, the auditing of algorithms by independent parties is more wish-list item than standard practice. But, again using the example of kidney disease, Robinson shows how it can be done. By the 2000s, an algorithm had been developed in the US to identify recipients for donated kidneys. But some people were unhappy with how the algorithm had been designed. In 2007, Clive Grawe, a kidney transplant candidate from Los Angeles, told a room full of medical experts that their algorithm was biased against older people like him. The algorithm had been designed to allocate kidneys in a way that maximized years of life saved. This favored younger, wealthier, and whiter patients, Grawe and other patients argued. Such bias in algorithms is common. What’s less common is for the designers of those algorithms to agree that there is a problem. After years of consultation with laypeople like Grawe, the designers found a less biased way to maximize the number of years saved—by, among other things, considering overall health in addition to age. One key change was that the majority of donors, who are often people who have died young, would no longer be matched only to recipients in the same age bracket. Some of those kidneys could now go to older people if they were otherwise healthy. As with Scribner’s committee, the algorithm still wouldn’t make decisions that everyone would agree with. But the process by which it was developed is harder to fault. “I didn’t want to sit there and give the injection. If you want it, you press the button.” Nitschke, too, is asking hard questions. A former doctor who burned his medical license after a years-long legal dispute with the Australian Medical Board, Nitschke has the distinction of being the first person to legally administer a voluntary lethal injection to another human. In the nine months between July 1996, when the Northern Territory of Australia brought in a law that legalized euthanasia, and March 1997, when Australia’s federal government overturned it, Nitschke helped four of his patients to kill themselves. The first, a 66-year-old carpenter named Bob Dent, who had suffered from prostate cancer for five years, explained his decision in an open letter: “If I were to keep a pet animal in the same condition I am in, I would be prosecuted.” Nitschke wanted to support his patients’ decisions. Even so, he was uncomfortable with the role they were asking him to play. So he made a machine to take his place. “I didn’t want to sit there and give the injection,” he says. “If you want it, you press the button.” The machine wasn’t much to look at: it was essentially a laptop hooked up to a syringe. But it achieved its purpose. The Sarco is an iteration of that original device, which was later acquired by the Science Museum in London. Nitschke hopes an algorithm that can carry out a psychiatric assessment will be the next step. But there’s a good chance those hopes will be dashed. Creating a program that can assess someone’s mental health is an unsolved problem—and a controversial one. As Nitschke himself notes, doctors do not agree on what it means for a person of sound mind to choose to die. “You can get a dozen different answers from a dozen different psychiatrists,” he says. In other words, there is no common ground on which an algorithm could even be built. But that’s not the takeaway here. Like Scribner, Nitschke is asking what counts as a medical decision, what counts as an ethical one, and who gets to choose. Scribner thought that laypeople—representing society as a whole—should choose who received dialysis, because when patients have more or less equal chances of survival, who lives and who dies is no longer a technical question. As Robinson describes it, society must be responsible for such decisions, although the process can still be encoded in an algorithm if it’s done inclusively and transparently. For Nitschke, assisted suicide is also an ethical decision, one that individuals must make for themselves. The Sarco, and the theoretical algorithm he imagines, would only protect their ability to do so. AI will become increasingly useful, perhaps essential, as populations boom and resources stretch. Yet the real work will be acknowledging the awfulness and arbitrariness of many of the decisions AI will be called on to make. And that’s on us. For Robinson, devising algorithms is a bit like legislation: “In a certain light, the question of how best to make software code that will govern people is just a special case of how best to make laws. People disagree about the merits of different ways of making high-stakes software, just as they disagree about the merits of different ways of making laws.” And it is people—in the broadest sense—who are ultimately responsible for the laws we have. 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 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 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 "

"DeepMind is using AI to pinpoint the causes of genetic disease | MIT Technology Review"

"https://www.technologyreview.com/2023/09/19/1079871/deepmind-alphamissense-ai-pinpoint-causes-genetic-disease"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts DeepMind is using AI to pinpoint the causes of genetic disease Fresh from solving the protein structure challenge, Google’s deep-learning outfit is moving on to the human genome. By Antonio Regalado archive page Google DeepMind Google DeepMind says it’s trained an artificial intelligence that can predict which DNA variations in our genomes are likely to cause disease—predictions that could speed diagnosis of rare disorders and possibly yield clues for drug development. DeepMind, founded in London and acquired by Google 10 years ago , is known for artificial-intelligence programs that play video games and have conquered complex board games like Go. It jumped into medicine when it announced that its program AlphaFold was able to accurately predict the shape of proteins , a problem considered a “grand challenge” in biology. Now the company says it has fine-tuned that protein model to predict which misspellings found in human DNA are safe to ignore and which are likely to cause disease. The new software, called AlphaMissense, was described today in a report published by the journal Science. As part of its project, DeepMind says, it is publicly releasing tens of millions of these predictions, but the company isn’t letting others directly download the model because of what it characterizes as potential biosecurity risks should the technique be applied to other species. Although not intended to directly make diagnoses, computer predictions are already used by doctors to help locate the genetic causes of mysterious syndromes. In a blog post, DeepMind said its results are part of an effort to uncover “the root cause of disease” and could lead to “faster diagnosis and developing life-saving treatments.” The three-year project was led by DeepMind engineers Jun Cheng and Žiga Avsec, and the company said it is publicly releasing predictions for 71 million possible variants. Each is what’s known as a missense mutation—a single DNA letter that, if altered, changes the protein a gene makes. “The goal here is, you give me a change to a protein, and instead of predicting the protein shape, I tell you: Is this bad for the human that has it?” says Stephen Hsu, a physicist at Michigan State University who works on genetic problems with AI techniques. “Most of these flips, we just have no idea whether they cause sickness.” Outside experts said DeepMind’s announcement was the latest in a string of flashy demonstrations whose commercial value remains unclear. “DeepMind is being DeepMind,” says Alex Zhavoronkov, founder of Insilico Medicine, an AI company developing drugs. “Amazing on PR and good work on AI.” Zhavoronkov says the real test of modern artificial intelligence is whether it can lead to new cures, something that still hasn’t happened. But some AI-designed drugs are in testing, and efforts to create useful new proteins are a particularly hot sector, investors say. One company, Generate Biomedicines, just raised $273 million to create antibodies, and a team of former Meta engineers started EvolutionaryScale, which thinks AI can come up with “ programmable cells that seek out and destroy cancer ,” according to Forbes. Better models DeepMind’s new effort has less to do with drugs, however, and more to do with how doctors diagnose rare disease, especially in patients with mystery symptoms, like a newborn with a rash that won’t go away, or an adult suddenly feeling weaker. With the rise of gene sequencing, doctors can now decode people’s genomes and then scour the DNA data for possible culprits. Sometimes, the cause is clear, like the mutation that leads to cystic fibrosis. But in about 25% of cases where extensive gene sequencing is done, scientists will find a suspicious DNA change whose effects aren’t fully understood, says Heidi Rehm, director of the clinical laboratory at the Broad Institute, in Cambridge, Massachusetts. Scientists call these mystery mutations “variants of uncertain significance,” and they can appear even in exhaustively studied genes like BRCA1 , a notorious hot spot of inherited cancer risk. “There is not a single gene out there that does not have them,” says Rehm. DeepMind says AlphaMissense can help in the search for answers by using AI to predict which DNA changes are benign and which are “likely pathogenic.” The model joins previously released programs, such as one called PrimateAI , that make similar predictions. “There has been a lot of work in this space already, and overall, the quality of these in silico predictors has gotten much better,” says Rehm. However, Rehm says computer predictions are only “one piece of evidence,” which on their own can’t convince her a DNA change is really making someone sick. Typically, experts don’t declare a mutation pathogenic until they have real-world data from patients, evidence of inheritance patterns in families, and lab tests—information that’s shared through public websites of variants such as ClinVar. “The models are improving, but none are perfect, and they still don’t get you to pathogenic or not,” says Rehm, who says she was “disappointed” that DeepMind seemed to exaggerate the medical certainty of its predictions by describing variants as benign or pathogenic. Fine tuning DeepMind says the new model is based on AlphaFold, the earlier model for predicting protein shapes. Even though AlphaMissense does something very different, says Pushmeet Kohli, a vice president of research at DeepMind, the software is somehow “leveraging the intuitions it gained” about biology from its previous task. Because it was based on AlphaFold, the new model requires relatively less computer time to run—and therefore less energy than if it had been built from scratch. In technical terms, the model is pre-trained, but then adapted to a new task in an additional step called fine-tuning. For this reason, Patrick Malone, a doctor and biologist at KdT Ventures, believes that AlphaMissense is “an example of one of the most important recent methodological developments in AI.” “The concept is that the fine-tuned AI is able to leverage prior learning,” says Malone. “The pre-training framework is especially useful in computational biology, where we are often limited by access to data at sufficient scale.” Biosecurity risks DeepMind says it’s provided free access to all its predictions for human genes, as well as all the details needed to fully replicate the work, including computer code. However, it isn’t releasing the whole model for immediate download and use by others because of what it calls a biosecurity risk if it were applied to analyze the genes of species other than humans. “As part of our commitment to releasing our research breakthroughs safely and responsibly, we will not be sharing model weights, to prevent use in potentially unsafe applications,” the authors wrote in the fine print of their paper. It’s not obvious what those unsafe applications are, or what non-human species the researchers had in mind. DeepMind didn’t spell them out, but risks could include using an AI to design more dangerous bacteria or a bioweapon. However, at least one outside expert we spoke to, who asked for anonymity because Google invests in companies he’s started, characterized the restrictions as a transparent effort to stop others from quickly deploying the model for their own uses. DeepMind denied it was throttling the model for reasons other than safety. The work was assessed both by the Google DeepMind Institute, which studies responsible AI, and by an “outside biosafety expert,” a spokesperson for DeepMind said. The restriction on the model “primarily limits making predictions on non-human protein sequences,” DeepMind said in a statement. “Not releasing weights prevents others from simply downloading the model and using it in non-human species … hence reducing the likelihood of misuse by bad actors.” hide by Antonio Regalado 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 Biotechnology and health Everything you need to know about artificial wombs Artificial wombs are nearing human trials. But the goal is to save the littlest preemies, not replace the uterus. By Cassandra Willyard archive page Some deaf children in China can hear after gene therapy treatment After deafness treatment, Yiyi can hear her mother and dance to the music. But why is it so noisy at night? By Antonio Regalado archive page Zeyi Yang archive page Scientists just drafted an incredibly detailed map of the human brain A massive suite of papers offers a high-res view of the human and non-human primate brain. By Cassandra Willyard archive page How AI can help us understand how cells work—and help cure diseases A virtual cell modeling system, powered by AI, will lead to breakthroughs in our understanding of diseases, argue the cofounders of the Chan Zuckerberg Initiative. By Priscilla Chan archive page Mark Zuckerberg 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 "

"What are quantum-resistant algorithms—and why do we need them? | MIT Technology Review"

"https://www.technologyreview.com/2022/09/14/1059400/explainer-quantum-resistant-algorithms"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts What are quantum-resistant algorithms—and why do we need them? When quantum computers become powerful enough, they could theoretically crack the encryption algorithms that keep us safe. The race is on to find new ones. By Tammy Xu archive page Sven Hoppe/picture-alliance/dpa/AP Images Tech Review Explains: Let our writers untangle the complex, messy world of technology to help you understand what's coming next. You can read more here. Cryptographic algorithms are what keep us safe online, protecting our privacy and securing the transfer of information. But many experts fear that quantum computers could one day break these algorithms, leaving us open to attack from hackers and fraudsters. And those quantum computers may be ready sooner than many people think. That’s why there is serious work underway to design new types of algorithms that are resistant to even the most powerful quantum computer we can imagine. What do these algorithms even do? Cryptographic algorithms turn readable data into a secret, unreadable form so it can be safely shared on the open internet. They are used to secure all types of digital communication, like traffic on websites and the content of emails, and they are necessary for basic privacy, trust, and security on the web. There are several types of standard cryptographic algorithms widely used today, including symmetric-key and public-key algorithms. Related Story A multi-year hacking campaign shows how dangerous old flaws can linger for years. Symmetric-key encryption is what people usually think of as encryption. It allows data and messages to be scrambled using a “key” so they are indecipherable to anyone without the key. It’s commonly used for securing sensitive data stored in databases or hard drives. Even data breaches that compromise databases full of sensitive user information aren’t as bad if the underlying data is encrypted—hackers may get the encrypted data, but there’s still no way to read it. Public-key algorithms are important too. They help get around the fundamental drawback of symmetric-key encryption, which is that you need a secure way to share symmetric keys in the first place. Public-key algorithms use a set of two keys, one that is privately kept by the recipient and one that is made public. Anyone can use the receiver’s public key to scramble data, which only the receiver can unscramble using the private key. This method can be used to transfer symmetric keys and can even be used in reverse for digital signatures—because private keys are unique to the receiver, receivers can use them to validate their identity. Why do these algorithms need to be quantum resistant? Cryptographic algorithms are able to keep data secret because they are mathematically intensive to break. It would take a modern computer trillions of years to break just one set of encryption keys using brute force. But in the 1990s, before quantum computers were ever seriously talked about, mathematician Peter Shor discovered that the way a theoretical quantum computer would work happened to line up particularly well with cracking the kind of math used in public-key encryption. Although no quantum computer existed at the time, other mathematicians were able to confirm that Shor’s Algorithm, as it became known, could theoretically be used by such computers to break public-key encryption. Now it’s widely accepted that once a working quantum computer with enough processing power is built, the algorithms we rely on today for public-key encryption will be easily breakable. The National Institute of Standards and Technology (NIST) predicts that quantum computers that can do this may be ready in just 10 to 20 years. Luckily, symmetric-key encryption methods are not in danger because they work very differently and can be secured by simply increasing the size of the keys they use—that is, unless mathematicians can come up with a way for quantum computers to break those as well. But even increasing the key size can’t protect existing public-key encryption algorithms from quantum computers. New algorithms are needed. What are the repercussions if quantum computers break encryption we currently use? Yeah, it’s bad. If public-key encryption were suddenly broken without a replacement, digital security would be severely compromised. For example, websites use public-key encryption to maintain secure internet connections, so sending sensitive information through websites would no longer be safe. Cryptocurrencies also depend on public-key encryption to secure their underlying blockchain technology, so the data on their ledgers would no longer be trustworthy. There is also concern that hackers and nation-states might be hoarding highly sensitive government or intelligence data —data they can’t currently decipher—in order to decrypt it later once quantum computers become available. How is work on quantum-resistant algorithms progressing? In the US, NIST has been looking for new algorithms that can withstand attacks from quantum computers. The agency started taking public submissions in 2016, and so far these have been narrowed down to four finalists and three backup algorithms. These new algorithms use techniques that can withstand attacks from quantum computers using Shor’s Algorithm. Project lead Dustin Moody says NIST is on schedule to complete standardization of the four finalists in 2024, which involves creating guidelines to ensure that the new algorithms are used correctly and securely. Standardization of the remaining three algorithms is expected in 2028. The work of vetting candidates for the new standard falls mostly to mathematicians and cryptographers from universities and research institutions. They submit proposals for post-quantum cryptographic schemes and look for ways to attack them, sharing their findings by publishing papers and building on each other’s different methods of attack. Related Story Quantum computing startups are all the rage, but it’s unclear if they’ll be able to produce anything of use in the near future. In this way, they slowly weed out candidates that are successfully attacked or shown to have weaknesses in their algorithm. A similar process was used to create the standards we currently use for encryption. However, there are no guarantees that a new type of clever quantum attack, or perhaps even conventional attack, won’t someday be discovered that can break these new algorithms. “It’s impossible to prove that you can’t break it—the nonexistence of a mathematical algorithm is hard to impossible to prove,” says cryptographer Thomas Decru. But “if something stands the test of time in the world of cryptography, the trust grows.” hide by Tammy Xu 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 Computing What’s next for the world’s fastest supercomputers Scientists have begun running experiments on Frontier, the world’s first official exascale machine, while facilities worldwide build other machines to join the ranks. By Sophia Chen archive page AI-powered 6G networks will reshape digital interactions The convergence of AI and communication technologies will create 6G networks that make hyperconnectivity and immersive experiences an everyday reality for consumers. By MIT Technology Review Insights archive page The power of green computing Sustainable computing practices have the power to both infuse operational efficiencies and greatly reduce energy consumption, says Jen Huffstetler, chief product sustainability officer at Intel. By MIT Technology Review Insights archive page How this Turing Award–winning researcher became a legendary academic advisor Theoretical computer scientist Manuel Blum has guided generations of graduate students into fruitful careers in the field. By Sheon Han 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 US is worried that hackers are stealing data today so quantum computers can crack it in a decade | MIT Technology Review"

"https://www.technologyreview.com/2021/11/03/1039171/hackers-quantum-computers-us-homeland-security-cryptography"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts The US is worried that hackers are stealing data today so quantum computers can crack it in a decade The US government is starting a generation-long battle against the threat next-generation computers pose to encryption. By Patrick Howell O'Neill archive page Ms Tech While they wrestle with the immediate danger posed by hackers today, US government officials are preparing for another, longer-term threat: attackers who are collecting sensitive, encrypted data now in the hope that they’ll be able to unlock it at some point in the future. The threat comes from quantum computers, which work very differently from the classical computers we use today. Instead of the traditional bits made of 1 s and 0 s, they use quantum bits that can represent different values at the same time. The complexity of quantum computers could make them much faster at certain tasks, allowing them to solve problems that remain practically impossible for modern machines—including breaking many of the encryption algorithms currently used to protect sensitive data such as personal, trade, and state secrets. While quantum computers are still in their infancy, incredibly expensive and fraught with problems , officials say efforts to protect the country from this long-term danger need to begin right now. Related Story “The threat of a nation-state adversary getting a large quantum computer and being able to access your information is real,” says Dustin Moody, a mathematician at the National Institute of Standards and Technology (NIST). “The threat is that they copy down your encrypted data and hold on to it until they have a quantum computer.” “Adversaries and nation states are likely doing it,” he says. “It’s a very real threat that governments are aware of. They're taking it seriously and they're preparing for it. That's what our project is doing.” Faced with this “harvest now and decrypt later” strategy, officials are trying to develop and deploy new encryption algorithms to protect secrets against an emerging class of powerful machines. That includes the Department of Homeland Security, which says it is leading a long and difficult transition to what is known as post-quantum cryptography. “We don’t want to end up in a situation where we wake up one morning and there’s been a technological breakthrough, and then we have to do the work of three or four years within a few months—with all the additional risks associated with that,” says Tim Maurer, who advises the secretary of homeland security on cybersecurity and emerging technology. DHS recently released a road map for the transition, beginning with a call to catalogue the most sensitive data, both inside the government and in the business world. Maurer says this is a vital first step “to see which sectors are already doing that, and which need assistance or awareness to make sure they take action now.” Preparing in advance Experts say it could still be a decade or more before quantum computers are able to accomplish anything useful, but with money pouring into the field in both China and the US, the race is on to make it happen—and to design better protections against quantum attacks. The US, through NIST, has been holding a contest since 2016 that aims to produce the first quantum-computer-proof algorithms by 2024, according to Moody, who leads NIST’s project on post-quantum cryptography. Transitioning to new cryptography is a notoriously tricky and lengthy task, and one it’s easy to ignore until it’s too late. It can be difficult to get for-profit organizations to spend on an abstract future threat years before that threat becomes reality. “If organizations aren’t thinking about the transition now,” says Maurer, “and then they become overwhelmed by the time the NIST process has been completed and the sense of urgency is there, it increases the risk of accidental incidents … Rushing any such transition is never a good idea.” As more organizations begin to consider the looming threat, a small and energetic industry has sprouted up, with companies already selling products that promise post-quantum cryptography. But DHS officials have explicitly warned against purchasing them, because there is still no consensus about how such systems will need to work. Related Story How it works, why it’s so powerful, and where it’s likely to be most useful first “No,” the department stated unequivocally in a document released last month. “Organizations should wait until strong, standardized commercial solutions are available that implement the upcoming NIST recommendations to ensure interoperability as well as solutions that are strongly vetted and globally acceptable.” But experts are pessimistic about how the transition will go. If it takes a long time for quantum computers to get to the point where they can solve a useful problem, “I think companies will forget the hype and implement the weakest thing that comes out of NIST until they are suddenly reminded of the problem in 30 years,” Vadim Lyubashevsky, a cryptographer at IBM who’s working on post-quantum cryptographic algorithms with NIST, told MIT Technology Review last year. And that is exactly the scenario national security officials want to avoid. Update: One quote from Dustin Moody was added to this story after publication, and the headline was changed to more accurately reflect the content. hide by Patrick Howell O'Neill 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 Computing What’s next for the world’s fastest supercomputers Scientists have begun running experiments on Frontier, the world’s first official exascale machine, while facilities worldwide build other machines to join the ranks. By Sophia Chen archive page AI-powered 6G networks will reshape digital interactions The convergence of AI and communication technologies will create 6G networks that make hyperconnectivity and immersive experiences an everyday reality for consumers. By MIT Technology Review Insights archive page The power of green computing Sustainable computing practices have the power to both infuse operational efficiencies and greatly reduce energy consumption, says Jen Huffstetler, chief product sustainability officer at Intel. By MIT Technology Review Insights archive page How this Turing Award–winning researcher became a legendary academic advisor Theoretical computer scientist Manuel Blum has guided generations of graduate students into fruitful careers in the field. By Sheon Han 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 "

"How a quantum computer could break 2048-bit RSA encryption in 8 hours | MIT Technology Review"

"https://www.technologyreview.com/2019/05/30/65724/how-a-quantum-computer-could-break-2048-bit-rsa-encryption-in-8-hours"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts How a quantum computer could break 2048-bit RSA encryption in 8 hours By Emerging Technology from the arXiv archive page A close-up of the D-Wave Vesuvius chip Steve Jurvetson | Flickr Many people worry that quantum computers will be able to crack certain codes used to send secure messages. The codes in question encrypt data using “trapdoor” mathematical functions that work easily in one direction but not in the other. That makes encrypting data easy but decoding it hugely difficult without the help of a special key. These encryption systems have never been unbreakable. Instead, their security is based on the huge amount of time it would take for a classical computer to do the job. Modern encryption methods are specifically designed so that decoding them would take so long they are practically unbreakable. But quantum computers change this thinking. These machines are far more powerful than classical computers and should be able to break these codes with ease. That raises an important question—when will quantum computers be powerful enough to do this? After that date, any information protected by this form of encryption becomes insecure. So computer scientists have attempted to calculate the resources such a quantum computer might need and then work out how long it will be until such a machine can be built. And the answer has always been decades. Today, that thinking needs to be revised thanks to the work of Craig Gidney at Google in Santa Barbara and Martin Ekerå at the KTH Royal Institute of Technology in Stockholm, Sweden. These guys have found a more efficient way for quantum computers to perform the code-breaking calculations, reducing the resources they require by orders of magnitude. Consequently, these machines are significantly closer to reality than anyone suspected. The result will make uncomfortable reading for governments, military and security organizations, banks, and anyone else who needs to secure data for 25 years or longer. First some background. Back in 1994, the American mathematician Peter Shor discovered a quantum algorithm that outperformed its classical equivalent. Shor’s algorithm factors large numbers and is the crucial element in the process for cracking trapdoor-based codes. Trapdoor functions are based on the process of multiplication, which is easy to perform in one direction but much harder to do in reverse. For example, it is trivial to multiply two numbers together: 593 times 829 is 491,597. But it is hard to start with the number 491,597 and work out which two prime numbers must be multiplied to produce it. And it becomes increasingly difficult as the numbers get larger. Indeed, computer scientists consider it practically impossible for a classical computer to factor numbers that are longer than 2048 bits, which is the basis of the most commonly used form of RSA encryption. Shor showed that a sufficiently powerful quantum computer could do this with ease, a result that sent shock waves through the security industry. And since then, quantum computers have been increasing in power. In 2012, physicists used a four-qubit quantum computer to factor 143. Then in 2014 they used a similar device to factor 56,153. It’s easy to imagine that at this rate of progress, quantum computers should soon be able to outperform the best classical ones. Not so. It turns out that quantum factoring is much harder in practice than might otherwise be expected. The reason is that noise becomes a significant problem for large quantum computers. And the best way currently to tackle noise is to use error-correcting codes that require significant extra qubits themselves. Taking this into account dramatically increases the resources required to factor 2048-bit numbers. In 2015, researchers estimated that a quantum computer would need a billion qubits to do the job reliably. That’s significantly more than the 70 qubits in today’s state-of-the-art quantum computers. On that basis, security experts might well have been able to justify the idea that it would be decades before messages with 2048-bit RSA encryption could be broken by a quantum computer. Now Gidney and Ekerå have shown how a quantum computer could do the calculation with just 20 million qubits. Indeed, they show that such a device would take just eight hours to complete the calculation. “[As a result], the worst case estimate of how many qubits will be needed to factor 2048 bit RSA integers has dropped nearly two orders of magnitude,” they say. Their method focuses on a more efficient way to perform a mathematical process called modular exponentiation. This is the process of finding the remainder when a number is raised to a certain power and then divided by another number. This process is the most computationally expensive operation in Shor’s algorithm. But Gidney and Ekerå have found various ways to optimize it, significantly reducing the resources needed to run the algorithm. That’s interesting work that should have important implications for anyone storing information for the future. A 20-million-qubit quantum computer certainly seems a distant dream today. But the question these experts should be asking themselves is whether such a device could be possible within the 25 years they want to secure the information. If they think it is, then they need a new form of encryption. Indeed, security experts have developed post-quantum codes that even a quantum computer will not be able to crack. So it is already possible to safeguard data today against future attack by quantum computers. But these codes are not yet used as standard. For ordinary people, there is little risk. Most people use 2048-bit encryption, or something similar, for tasks like sending credit card details over the internet. If these transactions are recorded today and broken in 25 years, little will be lost. But for governments, there is more at stake. The messages they send today—between embassies or the military, for example—may well be significant in 20 years and so worth keeping secret. If such messages are still being sent via 2048-bit RSA encryption, or something similar, then these organizations should start worrying—quickly. Ref: arxiv.org/abs/1905.09749 : How To Factor 2048 Bit RSA Integers In 8 Hours Using 20 Million Noisy Qubits hide by Emerging Technology from the arXiv 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 Computing What’s next for the world’s fastest supercomputers Scientists have begun running experiments on Frontier, the world’s first official exascale machine, while facilities worldwide build other machines to join the ranks. By Sophia Chen archive page AI-powered 6G networks will reshape digital interactions The convergence of AI and communication technologies will create 6G networks that make hyperconnectivity and immersive experiences an everyday reality for consumers. By MIT Technology Review Insights archive page The power of green computing Sustainable computing practices have the power to both infuse operational efficiencies and greatly reduce energy consumption, says Jen Huffstetler, chief product sustainability officer at Intel. By MIT Technology Review Insights archive page How this Turing Award–winning researcher became a legendary academic advisor Theoretical computer scientist Manuel Blum has guided generations of graduate students into fruitful careers in the field. By Sheon Han 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 "

"What's next for quantum computing | MIT Technology Review"

"https://www.technologyreview.com/2023/01/06/1066317/whats-next-for-quantum-computing"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts What’s next for quantum computing Companies are moving away from setting qubit records in favor of practical hardware and long-term goals. By Michael Brooks archive page Stephanie Arnett/MITTR; Getty This story is a part of MIT Technology Review’s What’s Next series , where we look across industries, trends, and technologies to give you a first look at the future In 2023, progress in quantum computing will be defined less by big hardware announcements than by researchers consolidating years of hard work, getting chips to talk to one another, and shifting away from trying to make do with noise as the field gets ever more international in scope. For years, quantum computing’s news cycle was dominated by headlines about record-setting systems. Researchers at Google and IBM have had spats over who achieved what—and whether it was worth the effort. But the time for arguing over who’s got the biggest processor seems to have passed: firms are heads-down and preparing for life in the real world. Suddenly, everyone is behaving like grown-ups. As if to emphasize how much researchers want to get off the hype train, IBM is expected to announce a processor in 2023 that bucks the trend of putting ever more quantum bits, or “qubits,” into play. Qubits, the processing units of quantum computers, can be built from a variety of technologies, including superconducting circuitry, trapped ions, and photons, the quantum particles of light. IBM has long pursued superconducting qubits, and over the years the company has been making steady progress in increasing the number it can pack on a chip. In 2021, for example, IBM unveiled one with a record-breaking 127 of them. In November, it debuted its 433-qubit Osprey processor , and the company aims to release a 1,121-qubit processor called Condor in 2023. But this year IBM is also expected to debut its Heron processor, which will have just 133 qubits. It might look like a backwards step, but as the company is keen to point out, Heron’s qubits will be of the highest quality. And, crucially, each chip will be able to connect directly to other Heron processors, heralding a shift from single quantum computing chips toward “modular” quantum computers built from multiple processors connected together—a move that is expected to help quantum computers scale up significantly. Heron is a signal of larger shifts in the quantum computing industry. Thanks to some recent breakthroughs, aggressive roadmapping, and high levels of funding, we may see general-purpose quantum computers earlier than many would have anticipated just a few years ago, some experts suggest. “Overall, things are certainly progressing at a rapid pace,” says Michele Mosca, deputy director of the Institute for Quantum Computing at the University of Waterloo. Here are a few areas where experts expect to see progress. Stringing quantum computers together IBM’s Heron project is just a first step into the world of modular quantum computing. The chips will be connected with conventional electronics, so they will not be able to maintain the “quantumness” of information as it moves from processor to processor. But the hope is that such chips, ultimately linked together with quantum-friendly fiber-optic or microwave connections, will open the path toward distributed, large-scale quantum computers with as many as a million connected qubits. That may be how many are needed to run useful, error-corrected quantum algorithms. “We need technologies that scale both in size and in cost, so modularity is key,” says Jerry Chow, director at IBM Quantum Hardware System Development. Related Story Other companies are beginning similar experiments. “Connecting stuff together is suddenly a big theme,” says Peter Shadbolt, chief scientific officer of PsiQuantum , which uses photons as its qubits. PsiQuantum is putting the finishing touches on a silicon-based modular chip. Shadbolt says the last piece it requires—an extremely fast, low-loss optical switch—will be fully demonstrated by the end of 2023. “That gives us a feature-complete chip,” he says. Then warehouse-scale construction can begin: “We’ll take all of the silicon chips that we’re making and assemble them together in what is going to be a building-scale, high-performance computer-like system.” The desire to shuttle qubits among processors means that a somewhat neglected quantum technology will come to the fore now, according to Jack Hidary , CEO of SandboxAQ, a quantum technology company that was spun out of Alphabet last year. Quantum communications, where coherent qubits are transferred over distances as large as hundreds of kilometers, will be an essential part of the quantum computing story in 2023, he says. “The only pathway to scale quantum computing is to create modules of a few thousand qubits and start linking them to get coherent linkage,” Hidary told MIT Technology Review. “That could be in the same room, but it could also be across campus, or across cities. We know the power of distributed computing from the classical world, but for quantum, we have to have coherent links: either a fiber-optic network with quantum repeaters, or some fiber that goes to a ground station and a satellite network.” Many of these communication components have been demonstrated in recent years. In 2017, for example, China’s Micius satellite showed that coherent quantum communications could be accomplished between nodes separated by 1,200 kilometers. And in March 2022, an international group of academic and industrial researchers demonstrated a quantum repeater that effectively relayed quantum information over 600 kilometers of fiber optics. Taking on the noise At the same time that the industry is linking up qubits, it is also moving away from an idea that came into vogue in the last five years—that chips with just a few hundred qubits might be able to do useful computing, even though noise easily disrupts their operations. This notion, called “noisy intermediate-scale quantum” (NISQ), would have been a way to see some short-term benefits from quantum computing, potentially years before reaching the ideal of large-scale quantum computers with many hundreds of thousands of qubits devoted to correcting errors. But optimism about NISQ seems to be fading. “The hope was that these computers could be used well before you did any error correction, but the emphasis is shifting away from that,” says Joe Fitzsimons, CEO of Singapore-based Horizon Quantum Computing. Related Story Quantum computing startups are all the rage, but it’s unclear if they’ll be able to produce anything of use in the near future. Some companies are taking aim at the classic form of error correction, using some qubits to correct errors in others. Last year, both Google Quantum AI and Quantinuum , a new company formed by Honeywell and Cambridge Quantum Computing, issued papers demonstrating that qubits can be assembled into error-correcting ensembles that outperform the underlying physical qubits. Other teams are trying to see if they can find a way to make quantum computers “fault tolerant” without as much overhead. IBM, for example, has been exploring characterizing the error-inducing noise in its machines and then programming in a way to subtract it (similar to what noise-canceling headphones do). It’s far from a perfect system—the algorithm works from a prediction of the noise that is likely to occur, not what actually shows up. But it does a decent job, Chow says: “We can build an error-correcting code, with a much lower resource cost, that makes error correction approachable in the near term.” Maryland-based IonQ , which is building trapped-ion quantum computers, is doing something similar. “The majority of our errors are imposed by us as we poke at the ions and run programs,” says Chris Monroe, chief scientist at IonQ. “That noise is knowable, and different types of mitigation have allowed us to really push our numbers." Getting serious about software For all the hardware progress, many researchers feel that more attention needs to be given to programming. “Our toolbox is definitely limited, compared to what we need to have 10 years down the road,” says Michal Stechly of Zapata Computing , a quantum software company based in Boston. Related Story The way code runs on a cloud-accessible quantum computer is generally “circuit-based,” which means the data is put through a specific, predefined series of quantum operations before a final quantum measurement is made, giving the output. That’s problematic for algorithm designers, Fitzsimons says. Conventional programming routines tend to involve looping some steps until a desired output is reached, and then moving into another subroutine. In circuit-based quantum computing, getting an output generally ends the computation: there is no option for going round again. Horizon Quantum Computing is one of the companies that have been building programming tools to allow these flexible computation routines. “That gets you to a different regime in terms of the kinds of things you’re able to run, and we’ll start rolling out early access in the coming year,” Fitzsimons says. Helsinki-based Algorithmiq is also innovating in the programming space. “We need nonstandard frameworks to program current quantum devices,” says CEO Sabrina Maniscalco. Algorithmiq’s newly launched drug discovery platform, Aurora, combines the results of a quantum computation with classical algorithms. Such “hybrid” quantum computing is a growing area, and it’s widely acknowledged as the way the field is likely to function in the long term. The company says it expects to achieve a useful quantum advantage—a demonstration that a quantum system can outperform a classical computer on real-world, relevant calculations—in 2023. Competition around the world Change is likely coming on the policy front as well. Government representatives including Alan Estevez, US undersecretary of commerce for industry and security, have hinted that trade restrictions surrounding quantum technologies are coming. Tony Uttley, COO of Quantinuum, says that he is in active dialogue with the US government about making sure this doesn’t adversely affect what is still a young industry. “About 80% of our system is components or subsystems that we buy from outside the US,” he says. “Putting a control on them doesn’t help, and we don’t want to put ourselves at a disadvantage when competing with other companies in other countries around the world.” And there are plenty of competitors. Last year, the Chinese search company Baidu opened access to a 10-superconducting-qubit processor that it hopes will help researchers make forays into applying quantum computing to fields such as materials design and pharmaceutical development. The company says it has recently completed the design of a 36-qubit superconducting quantum chip. “Baidu will continue to make breakthroughs in integrating quantum software and hardware and facilitate the industrialization of quantum computing,” a spokesman for the company told MIT Technology Review. The tech giant Alibaba also has researchers working on quantum computing with superconducting qubits. Related Story The US government is starting a generation-long battle against the threat next-generation computers pose to encryption. In Japan, Fujitsu is working with the Riken research institute to offer companies access to the country’s first home-grown quantum computer in the fiscal year starting April 2023. It will have 64 superconducting qubits. “The initial focus will be on applications for materials development, drug discovery, and finance,” says Shintaro Sato, head of the quantum laboratory at Fujitsu Research. Not everyone is following the well-trodden superconducting path, however. In 2020, the Indian government pledged to spend 80 billion rupees ($1.12 billion when the announcement was made) on quantum technologies. A good chunk will go to photonics technologies—for satellite-based quantum communications, and for innovative “qudit” photonics computing. Qudits expand the data encoding scope of qubits—they offer three, four, or more dimensions, as opposed to just the traditional binary 0 and 1, without necessarily increasing the scope for errors to arise. “This is the kind of work that will allow us to create a niche, rather than competing with what has already been going on for several decades elsewhere,” says Urbasi Sinha, who heads the quantum information and computing laboratory at the Raman Research Institute in Bangalore, India. Though things are getting serious and internationally competitive, quantum technology remains largely collaborative—for now. “The nice thing about this field is that competition is fierce, but we all recognize that it’s necessary,” Monroe says. “We don’t have a zero-sum-game mentality: there are different technologies out there, at different levels of maturity, and we all play together right now. At some point there’s going to be some kind of consolidation, but not yet.” Michael Brooks is a freelance science journalist based in the UK. hide by Michael Brooks 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 Computing What’s next for the world’s fastest supercomputers Scientists have begun running experiments on Frontier, the world’s first official exascale machine, while facilities worldwide build other machines to join the ranks. By Sophia Chen archive page AI-powered 6G networks will reshape digital interactions The convergence of AI and communication technologies will create 6G networks that make hyperconnectivity and immersive experiences an everyday reality for consumers. By MIT Technology Review Insights archive page The power of green computing Sustainable computing practices have the power to both infuse operational efficiencies and greatly reduce energy consumption, says Jen Huffstetler, chief product sustainability officer at Intel. By MIT Technology Review Insights archive page How this Turing Award–winning researcher became a legendary academic advisor Theoretical computer scientist Manuel Blum has guided generations of graduate students into fruitful careers in the field. By Sheon Han 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 "

"Facing tomorrow’s quantum hackers today | MIT Technology Review"

"https://www.technologyreview.com/2022/03/28/1048325/facing-tomorrows-quantum-hackers-today"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Sponsored Facing tomorrow’s quantum hackers today Organizations need to strengthen their cybersecurity now before quantum computing becomes powerful enough to break today’s encryptions. By MIT Technology Review Insights In collaboration with Abu Dhabi’s Technology Innovation Institute When it comes to computing ability, the general rule of thumb is more is better. Quantum computers promise to feed this hunger. Their immense processing power comes from their ability to store and handle significantly larger volumes of data than classical bit-driven computers. The result—a future quantum computer could, in theory, take minutes to solve problems that take classical computers tens of thousands of years. Facing tomorrow’s quantum hackers today Download the full report The possibilities of such computing power are enormous. Sifting through libraries of molecular combinations to accelerate drug discoveries, tightening logistics planning, boosting computational chemistry, fine-tuning weather forecasting accuracy, and strengthening financial modeling are a few of the applications waiting in the wings. Quantum computing could create a “value of $450 billion to $850 billion in the next 15 to 30 years,” according to estimates from a 2021 report from Boston Consulting Group. Governments and private companies around the world recognize this potential and are working to develop their own quantum strategies and research initiatives. Bracing for the power of quantum However, as quantum technology continues to advance, one dark cloud lurks on the horizon. Hackers could one day use this processing power to break public-key cryptography systems, which form the basis for today’s secure interactions over the Internet, as well as other systems such as public-key infrastructure, code-signing systems, secure email, and key-management systems. Experts warn this is a major threat to modern digital security that needs to be tackled now. “It will completely break these crypto systems,” says Dustin Moody, a mathematician at US-based National Institute of Standards and Technology (NIST). Although a full-scale quantum computer has yet to become reality, the danger is imminent. Duncan Jones, head of cybersecurity at a Cambridge- and Colorado-based quantum computing company, Quantinuum, says he’s concerned about a particular problem. “If I send you some encrypted data today and somebody records that, they can break into that later on,” says Duncan. “They don't need a quantum computer today to break into it. They can just patiently sit on that data and they can then decrypt in the future.” Post-quantum cryptography is emerging as an efficient and effective solution to defend against such quantum attacks. This solution is a set of new cryptographic algorithms, in particular public-key algorithms, that can be implemented using today’s classical computers. There is growing urgency for enterprises of all sizes and across all industries, as well as public institutions and other organizations, to make their systems crypto-agile and adopt such quantum-resistant algorithms in their security frameworks. Companies and organizations cannot afford to wait and see how the quantum-computing landscape evolves. “The cost will blow up if it is adopted after quantum computers are established,” says Jung Hee Cheon, professor of mathematics at Seoul National University in South Korea. Given the high stakes, a proactive, rather than reactive, stance toward such threats is crucial. Download the full report. This content was produced by Insights, the custom content arm of MIT Technology Review. It was not written by MIT Technology Review’s editorial staff. by MIT Technology Review Insights 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 Computing What’s next for the world’s fastest supercomputers Scientists have begun running experiments on Frontier, the world’s first official exascale machine, while facilities worldwide build other machines to join the ranks. By Sophia Chen archive page AI-powered 6G networks will reshape digital interactions The convergence of AI and communication technologies will create 6G networks that make hyperconnectivity and immersive experiences an everyday reality for consumers. By MIT Technology Review Insights archive page The power of green computing Sustainable computing practices have the power to both infuse operational efficiencies and greatly reduce energy consumption, says Jen Huffstetler, chief product sustainability officer at Intel. By MIT Technology Review Insights archive page How this Turing Award–winning researcher became a legendary academic advisor Theoretical computer scientist Manuel Blum has guided generations of graduate students into fruitful careers in the field. By Sheon Han 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 "

"DeepMind’s AI predicts almost exactly when and where it’s going to rain | MIT Technology Review"

"https://www.technologyreview.com/2021/09/29/1036331/deepminds-ai-predicts-almost-exactly-when-and-where-its-going-to-rain"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts DeepMind’s AI predicts almost exactly when and where it’s going to rain The firm worked with UK weather forecasters to create a model that was better at making short term predictions than existing systems. By Will Douglas Heaven archive page Getty First protein folding , now weather forecasting: London-based AI firm DeepMind is continuing its run applying deep learning to hard science problems. Working with the Met Office, the UK’s national weather service, DeepMind has developed a deep-learning tool called DGMR that can accurately predict the likelihood of rain in the next 90 minutes—one of weather forecasting’s toughest challenges. In a blind comparison with existing tools, several dozen experts judged DGMR’s forecasts to be the best across a range of factors—including its predictions of the location, extent, movement, and intensity of the rain—89% of the time. The results were published in a Nature paper today. DeepMind’s new tool is no AlphaFold, which cracked open a key problem in biology that scientists had been struggling with for decades. Yet even a small improvement in forecasting matters. Forecasting rain, especially heavy rain, is crucial for a lot of industries, from outdoor events to aviation to emergency services. But doing it well is hard. Figuring out how much water is in the sky, and when and where it’s going to fall, depends on a number of weather processes, such as changes in temperature, cloud formation, and wind. All these factors are complex enough by themselves, but they’re even more complex when taken together. The best existing forecasting techniques use massive computer simulations of atmospheric physics. These work well for longer-term forecasting but are less good at predicting what’s going to happen in the next hour or so, known as nowcasting. Previous deep-learning techniques have been developed, but these typically do well at one thing, such as predicting location, at the expense of something else, such as predicting intensity. “The nowcasting of precipitation remains a substantial challenge for meteorologists,” says Greg Carbin, chief of forecast operations at the NOAA Weather Prediction Center in the US, who was not involved in the work. The DeepMind team trained their AI on radar data. Many countries release frequent snapshots throughout the day of radar measurements that track the formation and movement of clouds. In the UK, for example, a new reading is released every five minutes. Putting these snapshots together provides an up-to-date stop-motion video that shows how rain patterns are moving across a country, similar to the forecast visuals you see on TV. The researchers fed this data to a deep generative network, similar to a GAN—a kind of AI that is trained to generate new samples of data that are very similar to the real data it was trained on. GANs have been used to generate fake faces , even fake Rembrandts. In this case, DGMR (which stands for “deep generative model of rainfall”) learned to generate fake radar snapshots that continued the sequence of actual measurements. It’s the same idea as seeing a few frames of a movie and guessing what’s going to come next, says Shakir Mohamed, who led the research at DeepMind. To test the approach, the team asked 56 weather forecasters at the Met Office (who were not otherwise involved in the work) to rate DGMR in a blind comparison with forecasts made by a state-of-the-art physics simulation and a rival deep-learning tool; 89% said that they preferred the results given by DGMR. “Machine-learning algorithms generally try and optimize for one simple measure of how good its prediction is,” says Niall Robinson, head of partnerships and product innovation at the Met Office, who coauthored the study. “However, weather forecasts can be good or bad in lots of different ways. Perhaps one forecast gets precipitation in the right location but at the wrong intensity, or another gets the right mix of intensities but in the wrong places, and so on. We went to a lot of effort in this research to assess our algorithm against a wide suite of metrics.” Related Story The company has already used its protein-folding AI, AlphaFold, to generate structures for the human proteome, as well as yeast, fruit flies, mice, and more. DeepMind’s collaboration with the Met Office is a good example of AI development done in collaboration with the end user, something that seems like an obviously good idea but often does not happen. The team worked on the project for several years, and input from the Met Office’s experts shaped the project. “It pushed our model development in a different way than we would have gone down on our own,” says Suman Ravuri, a research scientist at DeepMind. “Otherwise we might have made a model that was ultimately not particularly useful.” DeepMind is also eager to demonstrate that its AI has practical applications.. For Shakir, DGMR is part of the same story as AlphaFold: the company is cashing in on its years of solving hard problems in games. Perhaps the biggest takeaway here is that DeepMind is finally starting to tick off a bucket list of real-world science problems. 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 "

"2022’s seismic shift in US tech policy will change how we innovate | MIT Technology Review"

"https://www.technologyreview.com/2023/01/09/1064735/us-tech-policy-changing-innovation"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts 2022’s seismic shift in US tech policy will change how we innovate Three bills investing hundreds of billions into technological development could change the way we think about government’s role in growing prosperity. By David Rotman archive page AP Photo/Manuel Balce Ceneta This essay is part of MIT Technology Review's 10 Breakthrough Technologies 2023. Explore the full list here. It was the perfect political photo op. The occasion was the September groundbreaking for Intel’s massive $20 billion chip manufacturing complex in the suburbs of Columbus, Ohio. Backhoes dotted a construction site that stretched across hundreds of flat, empty acres. At a simple podium with the presidential seal, Joe Biden talked about putting an end to the term “Rust Belt,” a name popularized in the 1980s in reference to the Midwest’s rapidly declining manufacturing sector. It was a presidential victory lap after the passage of some landmark US legislation, beginning with the infrastructure bill in late 2021. Together, three major bills promise hundreds of billions in federal investments to transform the nation’s technology landscape. While ending the Rust Belt might be typical political hyperbole, you get the point: the spending spree is meant to revive the country’s economy by rebuilding its industrial base. The dollar amounts are jaw-dropping. The bills include $550 billion in new spending over the next five years in the Infrastructure Investment and Jobs Act, $280 billion in the CHIPS and Science Act (which prompted Intel to go ahead on the Ohio construction), and another roughly $390 billion for clean energy in the Inflation Reduction Act. Among the investments is the most aggressive federal funding for science and technology in decades. But the greatest long-term impact of the legislative flurry could come from its bold embrace of something that has long been a political third rail in the US: industrial policy. That means deliberate government interventions, including financial incentives and investments, favoring growth in particular industries or technologies—say, for national security reasons or to address problems such as climate change. Think of US support for semiconductor manufacturing in the 1980s or the creation during the Cold War of the Defense Advanced Research Projects Agency (DARPA), which led to the internet and GPS. But for decades now, free-market advocates have disparaged industrial policy as a foolhardy attempt to pick economic winners. Since the early 1980s and the era of Ronald Reagan, US politicians and many mainstream economists have disdained it. In reality, it never completely went away. President Obama toyed with elements of it in trying to revive manufacturing in the US after the 2008 recession; President Trump turned to it in his Operation Warp Speed to mobilize industry around covid vaccine development. But for the most part, it has seemed foreign to US political thinking: it was something China does, something Japan, South Korea, and France used to do (remember the Concorde?). The US has effective and productive free markets. And, of course, we have Silicon Valley, our own engine of economic growth, propelling the economy forward. All we need to do is unleash that engine by loosening regulations and cutting taxes. Or so the dominant narrative went. That narrative began crumbling long before the covid-19 pandemic made clear the need for the government to help bolster critical industrial sectors and supply chains. An unblinking faith in free markets has led to globalization, helping to gut many of the country’s industries, particularly in manufacturing. For a while, the economic argument was that it didn’t matter where you made stuff; cheap commodities were good for living standards, and the country should focus on high-tech growth. The problem is that high-tech growth has been limited, anemic, and unevenly distributed. Income inequality has climbed to high levels. The Rust Belt and other sections of the middle of the country keep getting rustier. Despite impressive advances in artificial intelligence and other areas of high tech, the nation’s prosperity has largely benefited people in only a few regions; notably, experts have begun identifying a handful of superstar cities, including San Francisco, Seattle, and Boston, that are booming while the rest of the country suffers. Perhaps most telling, growth of productivity—particularly the kind related to innovation, called total factor productivity—has been sluggish for several decades now in the US and many other rich countries. I wrote about the failure of technologies such as social media and artificial intelligence to boost productivity growth in the mid-2010s, in an essay titled “ Tech slowdown threatens the American Dream. ” Since then, the situation hasn’t gotten any better, roiling US politics and fueling a mood of economic malaise. What’s changed now is that the new legislation, which passed with some degree of bipartisan support in Congress, signals a strong appetite across the political spectrum for the US government to reengage with the country’s industrial base. After decades of declining federal investment in R&D , which dropped from 1.2% of GDP in the late 1970s to below 0.8% in recent years, the CHIPS and Science Act alone authorizes some $174 billion for research at places like the National Science Foundation. Related Story In 2001, we picked our first annual set of 10 breakthrough technologies. Here’s what their fates tell us about progress over the last two decades. Part of the reason the legislation received such broad support is that the funding provisions are a bit of Rorschach test. Some see measures to defend critical national technology businesses like chip production against the threat from China, and to make sure we don’t lose the global race in areas such as AI and quantum computing. Others see green jobs and efforts to address climate change, and a return to the post–World War II recognition that investing in science and research is critical to economic well-being. Still, despite the differences in motivation, the federal government’s willingness to embrace hawkish industrial policy is at least providing a chance to rethink the role the state plays in innovation. “It’s not just an opportunity—it’s a necessity,” says Dan Breznitz, the Peter J. Munk professor of Innovation Studies at the University of Toronto and co-director of its Innovation Policy Lab. After decades, he says, it’s time the US government got back in the game of “understanding the importance of merging innovation strategy with industrial policy.” Likewise, the European Union, South Korea and Japan, countries in the Middle East, and various other members of the Organization for Economic Cooperation and Development are all “back on the industrial-policy bandwagon,” says Dani Rodrik, an economist at Harvard. “It’s not like industrial policy ever went away,” says Rodrik, “but now it’s at the center of the conversation.” Instead of being embarrassed by the topic, he says, politicians are now touting it as a strategy. For economists like Diane Coyle, an expert on productivity and the emerging digital economy, the need for industrial policy to promote targeted growth is obvious at a time when productivity is stagnant, climate change is reaching a crisis point, and the rapid digitalization of the economy is worsening inequality. “We absolutely do need industrial policy in the kind of economy we have now,” says Coyle, the co-director of the Bennett Institute for Public Policy at the University of Cambridge. “But the catch, of course, is it’s difficult to do, and governments often don’t do it well.” What about Solyndra? The well-worn critique that industrial policy asks governments to pick winners, something they aren’t particularly good at, doesn’t really hold up to scrutiny. For every Solyndra (a solar company that received a half-billion-dollar federal loan guarantee before flaming out, and the favorite example of a disastrous losing pick), there is a Tesla—funded around the same time by a federal loan. But the criticism does have some truth to it; industrial policy requires, well, policies. It requires choices. The US legislation passed over the last year is really a series of different industrial and innovation strategies. There’s a classic industrial policy that singles out support to the chip industry; a green industrial policy in the Inflation Reduction Act (which is often called the climate bill) that broadly favors specific types of companies such as EV manufacturers; and other spending choices and policies scattered throughout the bills that aim to create new jobs. Arguably the most important provisions, at least according to some economists, are those designed to boost federal support for R&D. There is no obvious, coherent vision tying it all together. For now, says David Victor, a professor of innovation and public policy at the University of California, San Diego, that’s fine. “It’s more like industrial policy à la carte,” he says. It’s based on what is politically possible, appeasing different interests, from labor to industry to climate activists. Now, says Victor, “we need to turn it into as effective industrial policy as possible.” One challenge will be dealing with potentially conflicting priorities. For example, the climate bill’s generous tax incentives for electric vehicles come with a few stipulations. The EVs must be assembled in North America. What’s more, the battery components must be made or assembled in North America and the critical metals going into the batteries must be mined in the US or by its free-trade partners. That might boost long-term domestic manufacturing, creating jobs and building more reliable supply chains, but it also could create a bottleneck in EV production. If that happens, it could slow down efforts to reduce carbon emissions. Various other trade-offs and choices loom as the country ramps up its technology investments. To help make better choices, Erica Fuchs, a professor of engineering and public policy at Carnegie Mellon, and her collaborators have started a pilot project, funded by the NSF, that will use advanced data analysis and cross-disciplinary expertise from a team of university researchers to better inform policy makers on technology decisions. Called the National Network for Critical Technology Assessment, it’s meant to provide useful information on different options to meet various geopolitical and economic objectives. For example, given US dependency on China for lithium and the Democratic Republic of the Congo for cobalt, and given the risks of those supply chains, what is the potential value of innovations in battery recycling, alternative battery chemistries (such as ones that don’t use cobalt), and alternative extraction technologies? Likewise, there are questions around what parts of domestic battery manufacturing are most important for creating US jobs. While much analysis has already gone into writing the legislation, says Fuchs, many more questions will come up as the government attempts to spend the allocated funds to best realize legislative goals. She hopes the project will eventually lead to a larger network of experts from academia, industry, and government that provide the tools to clarify and quantify opportunities emerging from US innovation policies. A new story Any new narrative that the government can promote innovation and use it to foster economic prosperity is still very much a work in progress. It’s not yet clear how the various provisions in the different pieces of legislation will play out. Perhaps most worrisome, the large jumps in funding for R&D in the CHIPS and Science Act are simply authorizations—recommendations that Congress will need to work into the budget anew every year. A switch in political mood could quickly kill the funding. But perhaps the greatest unknown is how the federal funding will affect local economies and the welfare of millions of Americans who have suffered decades of lost manufacturing and declining job opportunities. Economists have long argued that technological advances are what drive economic growth. But over the last few decades, the prosperity resulting from such advances has been largely restricted to a few high-tech industries and has mostly benefited a relatively small elite. Can the public once again be convinced that innovation can lead to widespread prosperity? One worry is that while the recent legislation strongly supports semiconductor manufacturing and assorted clean technologies, the bills do little to create good jobs where they are most needed, says Harvard’s Rodrik. “In terms of bang for the buck,” he says, investing in advanced manufacturing and semiconductors “is one of the least effective ways of creating good jobs.” There is, he says, a “kind of manufacturing nostalgia” and a belief that rebuilding this sector will bring the middle class back. But that’s illusory, he says, since today’s advanced manufacturing is highly automated, and facilities tend to employ relatively few workers. Rodrik proposes what he calls an industrial policy for good jobs that would move beyond manufacturing and target the service sector, where by far the most jobs are in the US. His plan calls for investing in new technologies and companies that would improve productivity in jobs long thought of as low-skilled. For example, he points to opportunities to increase the capabilities of people working in long-term care, an area that is exploding as the population ages, by giving them digital tools. We also need to drop the pretensions around Silicon Valley’s role in creating widespread prosperity. A little more than six years ago, I wrote an essay titled “ Dear Silicon Valley: Forget flying cars, give us economic growth. ” Even with the advent of AI and driverless cars, economists were fretting over slow productivity growth. The inability of those in Silicon Valley to develop and commercialize the types of technologies and innovations that produce growth across a broad swath of the economy was clear. The tech industry gave us Zoom to survive the pandemic, and Amazon went on a hiring spree, but none of this led to a widespread economic expansion. We’re still waiting for the long-anticipated economy-­wide productivity boom from AI. These days, I would tweak the message: Forget about Silicon Valley and look elsewhere for economic transformation. Related Story If not Silicon Valley and other centers of innovation, where will that transformation come from? Though federal legislation has kick-started the discussion about industrial policy and innovation strategies, any real change will have to happen through efforts by cities and states. Each city, says Breznitz of the University of Toronto, will need to figure things out for itself, creating innovation strategies that work for its people on the basis of its industrial base, educational resources, and type of workforce. And, he admonishes, cities need to stop pinning their hopes on an elusive high-tech strategy modeled on Silicon Valley. “Two hundred cities in the US are all trying to look like Silicon Valley,” Breznitz says, adding, “I don’t know why. Maybe they’ve never been to Silicon Valley?” A key, he says, is recognizing that inventions are just one stage of innovation. Local governments need to support what he calls continuous innovation by helping local companies and industries offer improved and cheaper products and services. It might not be as glamorous as coming up with a novel idea for a radical new business, but it’s how most companies and regions become more productive and localities prosper. Creating a convincing narrative that large parts of the country buy into will take time. But that, says UCSD’s Victor, is precisely the point of industrial policy: “You begin to change the facts on the ground. You create new industries and jobs. And then the politics shift.” Before that happens, of course, lots can go wrong. Successful industrial policy depends on consistent and disciplined choices by politicians. You can decide for yourself whether you think they will manage that. But one reason for renewed optimism is that today’s technologies, especially artificial intelligence, robotics, genomic medicine, and advanced computation, provide vast opportunities to improve our lives, especially in areas like education, health care, and other services. If the government, at the national and local level, can find ways to help turn that innovation into prosperity across the economy, then we will truly have begun to rewrite the prevailing political narrative. hide by David Rotman 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 January/February 2023 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 "

"China Report: What’s up with all of Biden’s executive orders on China? | MIT Technology Review"

"https://www.technologyreview.com/2022/09/20/1059782/china-report-bidens-executive-orders"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts China Report: What’s up with all of Biden’s executive orders on China? Plus the rush to secure an HPV shot in China. By Zeyi Yang archive page Alex Wong / Getty Images Welcome to the very first China Report newsletter! I’m Zeyi Yang, and every Tuesday I’ll bring you news about China’s technology industry. This week, let’s unpack recent actions on China from the Biden administration. Lately, President Biden has been getting busy with executive orders that are, without naming China, very related to China. In the past three weeks, there have been at least three orders, but you’re not alone if you’ve found them hard to follow. On August 25, he signed EO 14080 to boost the domestic semiconductor industry; last Monday, he signed EO 14081 to build a strong domestic biotechnology industry and reduce reliance on foreign countries; then there’s EO 14083, which was officially published in full today. This last one clarifies the scope of the work of the Committee on Foreign Investments in the United States (CFIUS), a body that has existed for over four decades. There are also reports about more orders on the way. While none of these orders are explicitly about China, they are about countering foreign regimes that are both technological competitors and national security threats to the US. There aren’t many that fit the bill. The most interesting one: The CFIUS order is probably the hardest to understand if you haven’t been following this space closely. To catch you up, CFIUS is an interagency committee spanning 16 federal departments, including Treasury and Defense—and it’s one of the major weapons the federal government has long wielded to stop Chinese companies from acquiring US companies and technologies. If you want to know more, here’s a short explainer on CFIUS. Its stated goal has been to protect national security interests from all sources of foreign investment. It has stopped Chinese buyers from acquiring (or forced Chinese owners to sell) Grindr, MoneyGram, hard drive maker Western Digital, and several semiconductor companies. Under the Trump administration, it famously almost forced ByteDance to sell off TikTok in 2019. The new EO, though, doesn’t really change any of that. Honestly, it’s unclear if it will significantly change how CFIUS works. Instead, it will clarify a mission that has long been frustratingly vague. Related Story Previously, CFIUS cast a long and undefined shadow on any business acquisition activities between the US and China. No one knew for sure what sectors CFIUS was most interested in screening; the deals it has blocked have been all over the place. (My favorite odd example is from 2018, when the committee asked HNA , the Chinese conglomerate behind an aviation group of the same name, to sell a building in Manhattan. Why? CFIUS didn’t clarify, but the building is a) located blocks away from Trump Tower and b) home to a police precinct in charge of the security work for Trump Tower. I’ll let you draw your own conclusions.) The new order, though, gets specific. It lists a few industries that CFIUS should prioritize—microelectronics, artificial intelligence, biotechnology and biomanufacturing, quantum computing, advanced clean energy, and climate adaptation technologies —and also singles out threats to personal data protection, provisions the committee could use to justify blocking deals in consumer tech that aren’t traditionally seen as a national security risk. To be fair, the new “focused scope” of CFIUS still reads as incredibly broad and can likely be used however the federal government wants. But, speaking as a journalist, isn’t more transparency better? It will arguably help the agency use its resources more efficiently and effectively, and also help stakeholders know what to expect. The others: Okay, they may seem a little boring now that we’ve heard so much about supply chain problems over the past few years. But at their heart, the other two orders—which are about the semiconductor supply chain and the biotech supply chain—focus on making sure technological advancement and economic activities happen on US soil. The TL;DR here: The US and China used to trust each other in industrial cooperation and trade, despite ideological differences. But now, I think both sides will agree, that kind of trust doesn’t seem realistic anymore. These orders aim to move industries that emigrated from the US back stateside. (You can read more here about how the pandemic highlighted this issue.) Despite that growing distrust, these new policies follow the same playbook that China has used for decades: generous industry subsidies, government funding for academic institutions, and entry barriers for foreign competitors to protect domestic companies. And it just might work! After all, it’s precisely the success of the Chinese government at growing key technology sectors in short periods of time that pushed the US to act in the first place. Whether the administration admits it or not, I think these moves to build up domestic industries are a form of protectionism. It reminds me of the term “economic nationalism,” which the New Yorker writer E. Tammy Kim used to describe how both parties’ candidates in Ohio’s Senate race have promised to bring back manufacturing jobs from China. I don’t think the government stepping in to help a domestic industry is itself bad. But economic nationalism comes with problems, too: unfair competition, corruption, xenophobia, turning away trade allies, etc. Biden will surely be challenged from both sides on these issues. I find it ironic that after years of criticizing the Chinese approach of developing domestic tech industries, the US—under both Trump and Biden—is also learning from China. But to be fair, the best way to produce tech advancement is likely halfway between overreaching government interventions and an unregulated free market. It will be interesting to see how the US handles that balance as compared with its rival. Do you have a different thought on the Biden admin’s executive orders on China? I’d love to hear from you at [email protected]. Catch up with China 1. A car crash in Guizhou killed 27 people being transported to a covid quarantine facility. It sparked widespread outrage online about China’s ongoing zero-covid policy. ( CNN ) 2. Even though individual Chinese users have been blocked from Twitter, local governments are paying for tourism ads there—and they have become a fast-growing source of revenue for the platform. ( Reuters $) 3. Brick-and-mortar store owners in Mexico are reselling the Shein clothes they bought online and making a fortune. ( Rest of World ) 4. 3,470 Chinese chip companies shut down in 2021, more than in any other year. ( South China Morning Post $) Callback to my story from August: The era of unlimited semiconductor subsidies, which gave rise to corruption and unprofitable businesses, could soon end in China. ( MIT Technology Review ) 5. There’s an incredibly detailed, eye-popping story about a Chinese spy who tried to steal trade secrets from GE. The details come partly from the spy’s own diary that he backed up in iCloud. 🤦‍♂️ ( Bloomberg $) 6. China is revising its 2017 cybersecurity law; changes include a tenfold increase to some financial penalties for service providers that fail to take adequate security measures. ( Reuters $) 7. Chinese police in the Tibet Autonomous Region have collected millions of DNA samples over the past six years. ( Citizen Lab ) The police department bought DNA sequencer equipment from the Massachusetts-based company Thermo Fisher. ( The Intercept ) Lost in Translation There are great works of journalism in Chinese-language media that often don’t reach readers outside China. Each week, I’ll bring you one such story. Recently 八点健闻, a Chinese-language health news publication , reported on the crunch in getting a 9-valent HPV vaccine in China. The only such vaccine currently in use around the world is Gardasil 9, which was approved in 2014 in the US but not until 2018 in China. There’s been a supply bottleneck since. In order to secure a Gardasil 9 shot, patients have been traveling to Hong Kong, where it’s more accessible, or looking for alternative options like local-government-run vaccine lotteries or expensive private health services. Still, there’s a widespread feeling of anxiety about getting the most powerful HPV vaccine before it’s too late. The rush was exacerbated last month, when Gardasil 9 expanded its eligibility age range in China from 16–26 to 9–45. One More Thing Have you ever wanted a party game that tests your knowledge of Chinese politics and the ruling party? Just me? Well, there’s now a board game for that. You win by earning scores—“幸福指数/Happiness points”—by paying the in-game currency “正能量/positive energy” and answering trivia questions about China’s party and state history. There goes my Friday night. Happy birthday to me 🥳 Husband and I first became interested in the current trend for PRC environmental NGOs to use board games to advocate. Who knew, the Party's getting in on the action. This 强国梦 文创桌游 is a board game to test your Party knowledge. pic.twitter.com/LRPDm9IIo6 hide by Zeyi Yang 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 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 "

"China has never had a real chip industry. Making AI chips could change that. | MIT Technology Review"

"https://www.technologyreview.com/2018/12/14/138260/china-has-never-had-a-real-chip-industry-making-ai-chips-could-change-that"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts China has never had a real chip industry. Making AI chips could change that. By Will Knight archive page courtesy of bitmain Donald Trump is speaking Mandarin. This is happening in the city of Tianjin, about an hour’s drive south of Beijing, within a gleaming office building that belongs to iFlytek, one of China’s rapidly rising artificial-intelligence companies. Beyond guarded gates, inside a glitzy showroom, the US president is on a large TV screen heaping praise on the Chinese company. It’s Trump’s voice and face, but the recording is, of course, fake—a cheeky demonstration of the cutting-edge AI technology iFlytek is developing. Jiang Tao chuckles and leads the way to some other examples of iFlytek’s technology. Throughout the tour, Jiang, one of the company’s cofounders, uses another remarkable innovation: a hand-held device that converts his words from Mandarin into English almost instantly. At one point he speaks into the machine, and then grins as it translates: “I find that my device solves the communication problem.” iFlytek’s translator shows off AI capabilities that rival those found anywhere in the world. But it also highlights a big hole in China’s plan, unveiled in 2017, to be the world leader in AI by 2030. The algorithms inside were developed by iFlytek, but the hardware—the microchips that bring those algorithms to life—was designed and made elsewhere. While China manufactures most of the world’s electronic gadgets, it has failed, time and again, to master the production of these tiny, impossibly intricate silicon structures. Its dependence on foreign integrated circuits could potentially cripple its AI ambitions. However, AI itself could change all that. New types of chips are being invented to fully exploit advances in AI, by training and running deep neural networks for tasks such as voice recognition and image processing. These chips handle data in a fundamentally different way from the silicon logic circuits that have defined the cutting edge of hardware for decades. It means reinventing microchips for the first time in ages. A more advanced chip industry will help China realize its dream of becoming a true technology superpower. China won’t be playing catch-up with these new chips, as it has done with more conventional chips for decades. Instead, its existing strength in AI and its unparalleled access to the quantities of data required to train AI algorithms could give it an edge in designing chips optimized to run them. China’s chip ambitions have geopolitical implications, too. Advanced chips are key to new weapons systems, better cryptography, and more powerful supercomputers. They are also central to the increasing trade tensions between the US and China. A successful chip industry would make China more economically competitive and independent. To many, in both Washington and Beijing, national strength and security are at stake. Silicon visions On the outskirts of Wuhan, a sprawling city a few days’ cruise up the Yangtze from Shanghai, stands a factory that would span several football fields. It belongs to Tsinghua Unigroup, a state-backed microchip manufacturer. By the end of 2019, the factory will be producing silicon wafers that will then be cut into advanced memory chips. Tsinghua Unigroup aims to expand the Wuhan facility to three times its current size, at a total cost of $24 billion. It’s developing two similar sites, one along the Yangtze in Nanjing and another further west in Chengdu, at similar cost. They will be the largest and most sophisticated chip factories ever built by a Chinese company. It’s all part of an effort by China to drag its chipmaking industry forward. In 2014, the government established the National Integrated Circuits Industry Investment Fund, a subsidy program that plans to raise $180 billion from local-government-backed funds and state-owned enterprises. A year later, it released Made in China 2025, a sweeping blueprint for upgrading China’s entire manufacturing industry. This set the hugely ambitious goal of producing $305 billion worth of chips per year and meeting 80% of domestic demand for chips by 2030, up from $65 billion and 33%, respectively, in 2016. Today global production stands at $412 billion. There is still a long way to go. China is the world’s largest and fastest-growing market for semiconductors, but no Chinese chipmaker has broken into the top 15 globally in terms of sales. Advanced chips are primarily made by companies from the US, Taiwan, Japan, South Korea, and Western Europe. China’s big economic rival, the US, accounts for about half of global sales and half of China’s chip imports. Beijing has been trying to build a powerful microchip industry for a long time. Researchers developed China’s first transistor not long after the device was invented in the US at the end of the 1950s. But the country fell behind as its universities and businesses went through the turmoil of the Cultural Revolution. In the 1960s, as the semiconductor industry began ramping up in Silicon Valley and Moore’s Law was articulated, China’s fledgling chip industry lay in ruins. By the time the Chinese economy opened up in the 1980s, it was too late. Chipmakers partnered with foreign firms, but the manufacturing equipment they imported became outdated quickly, and they failed to produce even basic chips reliably or in sufficient volume. And even as China’s electronics manufacturing took off in the 1990s, bureaucratic missteps and the ready availability of high-quality imported chips stymied further government pushes. No Chinese company could match the decades of expertise at foreign firms like Intel, Samsung, and Taiwan Semiconductor. Mark Li, an analyst at Bernstein who tracks the chip industry in Asia, estimates that China’s most advanced chipmakers are still at least five years behind. Since Moore’s Law describes a doubling of chip performance every two years or so, that’s a sizable gap. China does have numerous low-end fabs making the relatively simple chips used in smart cards, SIM cards, and even basic phones, but not the kinds of factories needed to produce advanced processors. Why does China still struggle to make advanced chips when it has become so good at so much else? Basically, because it’s incredibly hard. The latest chips have billions of transistors, each with features only a few nanometers in size, crafted at the scale of individual atoms. They are so complex that it isn’t possible to take one apart and copy its design, as Chinese entrepreneurs have done with many foreign products. And even if it were possible, it wouldn’t provide the expertise required to design and fabricate the next generation. “Manufacturing involves hundreds, even thousands, of technical challenges,” says Yungang Bao, director of the Center for Advanced Computer Systems at the Chinese Academy of Sciences and an expert in microprocessor design. “It will take a long time to catch up.” Network effects Artificial intelligence may change the game. Deep learning is an AI technique that has proved its power in recent years to do useful things like spotting disease in medical images, teaching self-driving cars to stay on the road, and parsing spoken commands. It works in a fundamentally different way from most software. Deep learning uses large networks that roughly resemble the multiple layers of neurons in a biological brain. As a network learns a task, a cascade of computations occur in successive layers. The results of each computation alter the connections between each layer and the next; essentially, the network reprograms itself as it runs. Its ability to recognize objects in images isn’t the result of step-by-step logic operations, as in conventional programming, but gradually emerges as countless parameters inside the network are tweaked and re-tweaked through exhaustive training. Researchers realized early on that the chips in game consoles, originally designed to be fast at rendering 3D imagery, are better for deep learning than general-purpose chips. And deep-learning algorithms are still mostly trained using scores of these graphics processing units (GPUs). One of the market leaders for GPUs is Nvidia, which built its business supplying hardware for gamers. But now Intel and others have designed powerful new chips for training deep learning. Even cloud software businesses like Google’s and Amazon’s are developing bespoke chips designed for their best algorithms. Similar Chinese initiatives have been announced over the past year. In July, search giant Baidu revealed that it is working on a chip called Kunlun for running deep-learning algorithms in its data centers. And in September, the e-commerce powerhouse Alibaba said it would spin out a new company dedicated to making AI chips. Tellingly, the new company’s name is Pingtouge, a nickname for the honey badger, an African animal famed for fearlessness and tenacity. The timing of the AI boom is fortuitous for China’s chipmakers. The deep-­learning revolution was gaining speed just as the government’s latest chip push got under way. AI chip design is still in its early days, and in this technology—unlike memory and logic circuits—the country is not hopelessly behind. Specialized hardware Kai Yu has already played a significant role in China’s AI revolution. A cheerful, bespectacled man who studied neural networks at college in China and Germany in the late 1990s and early 2000s, he founded Baidu’s Institute of Deep Learning in 2013, as the company became one of the first to bet heavily on AI. Navigating Beijing’s morning traffic in the backseat of a Didi, Yu says the importance of chip hardware quickly became apparent when Baidu started pouring resources into deep learning. In 2015, he says, he suggested that Baidu make a specialized AI chip. But it seemed costly and far outside of the company’s expertise. So later that year, Yu left to found his own company, Horizon Robotics. Horizon is focused on “application-­specific” microchips that run pre-trained deep-learning algorithms. It’s developing them for self-driving cars and smarter robots. But Yu thinks these chips will be everywhere before long. “If we look back in 10 years,” he says, “more than half of the computations on a device will be AI related.” In August, Huawei, China’s biggest telecommunications and smartphone company, unveiled a mobile chip, the Kirin 980, that includes a “neural processing unit”—a section of logic designed for deep-learning tasks like image and voice recognition. In one sense, the chip illustrates a lingering limitation of China’s capabilities—it was manufactured by Taiwan’s TSMC. But in another, it reflects China’s striking progress and ambition. The chip is one of the country’s first to include features as small as 7 nanometers. Smaller components make chips faster and more capable, but also a lot harder to design and manufacture, so this a significant coup for Huawei. Designs for the part of the chip optimized for deep learning come from a startup called Cambricon, founded in 2016 by researchers from the Chinese Academy of Sciences. Today Cambricon is valued at $2.5 billion, making it the industry’s most valuable startup. In October, Huawei announced another AI chip, called Ascend, that is designed in-house. Chip on the shoulder China’s chip ambitions have rattled other countries, especially the US. Partly that’s because its efforts to gain access to technology have sometimes involved aggressive acquisitions, forced technology transfer, and, allegedly, industrial espionage. Chipmaking is key to military prowess, and the Obama administration sought to block Chinese attempts to acquire US chip technology long before Donald Trump arrived in the White House. It’s one of the few issues that unite US politicians. 人工智能正在改变世界 “Artificial intelligence is transforming the world.” In April 2018 the US banned one of China’s leading tech companies, ZTE, from using US chips because it had broken a ban on selling equipment containing US technology to Iran and North Korea. In October, the US said the memory-chip maker Fujian Jinhau, a company accused of stealing trade secrets, would need a special license to buy US-made components. These restrictions may partly be a response to property theft and unfair trade, but they also look like an effort to slow China’s chipmaking progress. Yet a trade war may only hasten China’s ascent. “People in China realized that the US can easily stop their progress,” says Bao at the Chinese Academy of Sciences. “It will probably speed things up.” However fast it happens, China’s march to advanced chipmaking is all but unstoppable. No true superpower can afford to outsource technology that is so critical to both its economic growth and its military security. And after decades of playing catch-up, the country is finally seeing opportunities to establish mastery of the field. In Tianjin, Jiang is explaining that iFlytek is thinking about designing its own chips, to improve the performance of its electronic translators. Just then, the AI-generated version of Trump speaks up. 人工智能正在改变世界 ( Réngōng zhìnéng zhèngzài gǎibiàn shìjiè ), he says: “Artificial intelligence is transforming the world.” hide by Will Knight 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 January/February 2019 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 Computing What’s next for the world’s fastest supercomputers Scientists have begun running experiments on Frontier, the world’s first official exascale machine, while facilities worldwide build other machines to join the ranks. By Sophia Chen archive page AI-powered 6G networks will reshape digital interactions The convergence of AI and communication technologies will create 6G networks that make hyperconnectivity and immersive experiences an everyday reality for consumers. By MIT Technology Review Insights archive page The power of green computing Sustainable computing practices have the power to both infuse operational efficiencies and greatly reduce energy consumption, says Jen Huffstetler, chief product sustainability officer at Intel. By MIT Technology Review Insights archive page How this Turing Award–winning researcher became a legendary academic advisor Theoretical computer scientist Manuel Blum has guided generations of graduate students into fruitful careers in the field. By Sheon Han 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 ChatGPT-fueled battle for search is bigger than Microsoft or Google | MIT Technology Review"

"https://www.technologyreview.com/2023/02/16/1068695/chatgpt-chatbot-battle-search-microsoft-bing-google"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts The ChatGPT-fueled battle for search is bigger than Microsoft or Google A frenzy of activity from tech giants and startups alike is reshaping what people want from search—for better or worse. By Will Douglas Heaven archive page Stephanie Arnett/MITTR | Degroote Stock/Envato It’s a good time to be a search startup. When I spoke to Richard Socher, the CEO of You.com, last week he was buzzing: “Man, what an exciting day—looks like another record for us,” he exclaimed. “Never had this many users. It’s been a whirlwind.” You wouldn’t know that two of the biggest firms in the world had just revealed rival versions of his company’s product. Related Story Plus: The original startup behind Stable Diffusion has launched a generative AI for video. In back-to-back announcements last week, Microsoft and Google staked out their respective claims to the future of search, showing off chatbots that can respond to queries with fluid sentences rather than lists of links. Microsoft has upgraded its search engine Bing with a version of ChatGPT , the popular chatbot released by San Francisco–based OpenAI last year. Google is working with a chatbot of its own, called Bard. These announcements gave us a glimpse of what’s next for search. But to get the full picture we need to look beyond Microsoft and Google: those giants will continue to dominate but, for anyone wanting an alternative, search is about to get crowded. That’s because a new wave of startups have been playing with many of the same chatbot-enhanced search tools for months. You.com launched a search chatbot back in December and has been rolling out updates since. A raft of other companies, such as Perplexity , Andi , and Metaphor , are also combining chatbot apps with upgrades like image search, social features that let you save or continue search threads started by others, and the ability to search for information just seconds old. ChatGPT's success has created a frenzy of activity as tech giants and startups alike try to figure out how to give people what they want—whether they knew they wanted it or not. Old guard, new ideas Google has dominated the search market for years. “It’s been pretty steady for a long time,” says Chirag Shah, who studies search technologies at the University of Washington. “Despite lots of innovations, the needle hasn’t shifted much.” That changed with the launch of ChatGPT in November. Suddenly, the idea of searching for things by typing in a string of disconnected words felt old-fashioned. Why not just ask for what you want? People are hooked on this idea of combining chatbots and search, says Edo Liberty, who used to lead Amazon’s AI lab and is now CEO of Pinecone, a company that makes databases for search engines: “It’s the right kind of pairing, it’s peanut butter and jelly.” Google has been exploring the idea of using large language models (the tech behind chatbots like ChatGPT and Bard) for some time. But when ChatGPT became a mainstream hit, Google and Microsoft made their moves. So did others. There are now several small companies competing with the big players, says Liberty. “Just five years ago, it would be a fool’s errand,” he says. “Who in their right mind would try to storm that castle?” Today, off-the-shelf software has made it easier than ever to build a search engine and plug it into a large language model. “You can now bite chunks off technologies that were built by thousands of engineers over a decade with just a handful of engineers in a few months,” says Liberty. Related Story OpenAI’s breakout hit was an overnight sensation—but it is built on decades of research. That’s been Socher’s experience. Socher left his role as chief AI scientist at Salesforce to cofound You.com in 2020. The site acts as a one-stop shop for web-search power users looking for a Google alternative. It aims to give people answers to different types of queries in a range of formats, from movie recommendations to code snippets. Last week it introduced multimodal search—where its chatbot can choose to respond to queries using images or embedded widgets from affiliated apps rather than text—and a feature that lets people share their exchanges with the chatbot, so that others can pick up an existing thread and dive deeper into a query. This week, You.com launched an upgrade that fields questions about live sports events, such as whether the Eagles could still win the Super Bowl with eight minutes left to play. Perplexity—a company set up by former researchers from OpenAI, Meta, and Quora, a website where people ask and answer each other’s questions—is taking search in a different direction. The startup, which has combined a version of OpenAI’s large language model GPT-3 with Bing, launched its search chatbot in December and says that around a million people have tried it out so far. The idea is to take that interest and build a social community around it. The company wants to reinvent community-based repositories of information, such as Quora or Wikipedia, using a chatbot to generate the entries instead of humans. When people ask Perplexity’s chatbot questions, the Q&A sessions are saved and can be browsed by others. Users can also up- or downvote responses generated by the chatbot, and add their own queries to an ongoing thread. It’s like Reddit, but where humans ask the questions and an AI answers. Last week, the day after Google’s (yet-to-be-released) chatbot Bard was spotted giving an incorrect answer in a rushed-out promo clip (a blooper that may have cost the company billions ), Perplexity announced a new plug-in for Google’s web browser, Chrome, with a clip of its own chatbot giving the right answer to the same question. 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. Angela Hoover, CEO and cofounder of Miami-based search firm Andi, set up her company a year ago after becoming frustrated at having to sift through ads and spam to find relevant links in Google. Like many people who have played around with chatbots such as ChatGPT, Hoover has a vision for search inspired by science-fiction know-it-alls like Jarvis in Iron Man or Samantha in Her. Of course, we don’t have anything like that yet. “We don’t think Andi knows everything,” says Hoover. “Andi’s just finding information that people have put on the internet and bringing it to you in a nice, packaged-up form.” Andi’s spin on search involves using large language models to pick the best results to summarize. Hoover says it has trained its models on everything from Pulitzer-winning articles to SEO spam to make the engine better at favoring certain results and avoiding others. Ultimately, the battle for search won’t just be confined to the web—tools will also be needed to search through more personal sources like emails and text messages. “Compared to the rest of the data in the world, the web is tiny,” says Liberty. According to Liberty, there are tons of companies using chatbots for search that are not competing with Microsoft and Google. His company, Pinecone, provides software that makes it easy to combine large language models with small, custom-built search engines. Customers have used Pinecone to build bespoke search tools for user manuals, medical databases , and transcripts of favorite podcasts. “I don’t know why, but we had somebody use Pinecone to build a Q&A bot for the Bible,” he says. Filling in the blanks But many people think that using chatbots for search is a terrible idea, full stop. The large language models that drive them are permeated with bias, prejudice, and misinformation. Hoover accepts this. “Large language models on their own are absolutely not enough,” she says. “They are fill-in-the-blank machines—they just make stuff up.” Companies building chatbots for search try to get around this problem by plugging large language models into existing search engines and getting them to summarize relevant results rather than inventing sentences from scratch. Most also make their chatbots cite the web pages or documents they are summarizing, with links that users can follow if they want to verify answers or dive deeper. Related Story Language models are mindless mimics that do not understand what they are saying—so why do we pretend they’re experts? But these tactics are far from foolproof. In the days since Microsoft opened up the new Bing to early users, social media has been filled with screenshots showing the chatbot going off the rails as people find ways to elicit nonsensical or offensive responses. According to Dmitri Brereton, a software engineer working on AI and search, Microsoft’s slick Bing Chat demo was also riddled with errors. Hoover suspects that Microsoft’s and Google’s chatbots may produce incorrect responses because they stitch together snippets from search results, which may themselves be inaccurate. “It’s a bad approach,” she says. “It is easy to demo because it looks impressive, but it produces dodgy answers.” (Microsoft and Google did not respond to requests for comment.) Hoover says that Andi avoids simply repeating text from search results. “It doesn’t make things up like other chatbots,” she says. People can decide for themselves whether or not that’s true. After collecting feedback from its users for the past year, the company’s chatbot will now sometimes admit when it’s not confident about an answer. “It’ll say, ‘I’m not sure, but according to Wikipedia …,’” says Hoover. Either way, this new era of search probably won’t ditch lists of links entirely. “When I think about search five years from now, we’ll still have the ability to look through results,” says Hoover. “I think that’s an important part of the web.” But as chatbots get more convincing, will we be less inclined to check up on their answers? “What’s noteworthy isn’t that large language models generate false information, but how good they are at turning off people’s critical reasoning abilities,” says Mike Tung, CEO of Diffbot, a company that builds software to pull data from the web. The University of Washington’s Shah shares that concern. In Microsoft’s demo for Bing Chat, the company hammered home the message that using chatbots for search can save time. But Shah points out that a little-known project Microsoft has been working on for years, called Search Coach , is designed to teach people to stop and think. Billed as “a search engine with training wheels,” Search Coach helps people, especially students and educators, learn how to write effective search queries and identify reliable resources. Instead of saving time, Search Coach encourages people to slow down. “Compare that to ChatGPT,” says Shah. Companies like Andi, Perplexity, and You.com are happy to admit they’re still figuring out what search could be. The truth is that it can be many things. “You don't want to fight against convenience, that's a losing battle in consumer tech,” says Socher. “But there’s some pretty fundamental questions about the entire state of the internet at play here.” 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 "

"How to spot AI-generated text | MIT Technology Review"

"https://www.technologyreview.com/2022/12/19/1065596/how-to-spot-ai-generated-text"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts How to spot AI-generated text The internet is increasingly awash with text written by AI software. We need new tools to detect it. By Melissa Heikkilä archive page Stephanie Arnett/MITTR This sentence was written by an AI—or was it? OpenAI’s new chatbot, ChatGPT, presents us with a problem: How will we know whether what we read online is written by a human or a machine? Since it was released in late November, ChatGPT has been used by over a million people. It has the AI community enthralled, and it is clear the internet is increasingly being flooded with AI-generated text. People are using it to come up with jokes, write children’s stories, and craft better emails. ChatGPT is OpenAI’s spin-off of its large language model GPT-3 , which generates remarkably human-sounding answers to questions that it’s asked. The magic—and danger—of these large language models lies in the illusion of correctness. The sentences they produce look right—they use the right kinds of words in the correct order. But the AI doesn’t know what any of it means. These models work by predicting the most likely next word in a sentence. They haven’t a clue whether something is correct or false, and they confidently present information as true even when it is not. In an already polarized, politically fraught online world, these AI tools could further distort the information we consume. If they are rolled out into the real world in real products, the consequences could be devastating. We’re in desperate need of ways to differentiate between human- and AI-written text in order to counter potential misuses of the technology, says Irene Solaiman, policy director at AI startup Hugging Face, who used to be an AI researcher at OpenAI and studied AI output detection for the release of GPT-3’s predecessor GPT-2. New tools will also be crucial to enforcing bans on AI-generated text and code, like the one recently announced by Stack Overflow, a website where coders can ask for help. ChatGPT can confidently regurgitate answers to software problems, but it’s not foolproof. Getting code wrong can lead to buggy and broken software, which is expensive and potentially chaotic to fix. A spokesperson for Stack Overflow says that the company’s moderators are “examining thousands of submitted community member reports via a number of tools including heuristics and detection models” but would not go into more detail. In reality, it is incredibly difficult, and the ban is likely almost impossible to enforce. Today’s detection tool kit There are various ways researchers have tried to detect AI-generated text. One common method is to use software to analyze different features of the text—for example, how fluently it reads, how frequently certain words appear, or whether there are patterns in punctuation or sentence length. “If you have enough text, a really easy cue is the word ‘the’ occurs too many times,” says Daphne Ippolito, a senior research scientist at Google Brain, the company’s research unit for deep learning. Related Story The new version of the company's large language model makes stuff up—but can also admit when it's wrong. Because large language models work by predicting the next word in a sentence, they are more likely to use common words like “the,” “it,” or “is” instead of wonky, rare words. This is exactly the kind of text that automated detector systems are good at picking up, Ippolito and a team of researchers at Google found in research they published in 2019. But Ippolito’s study also showed something interesting: the human participants tended to think this kind of “clean” text looked better and contained fewer mistakes, and thus that it must have been written by a person. In reality, human-written text is riddled with typos and is incredibly variable, incorporating different styles and slang, while “language models very, very rarely make typos. They’re much better at generating perfect texts,” Ippolito says. “A typo in the text is actually a really good indicator that it was human written,” she adds. Large language models themselves can also be used to detect AI-generated text. One of the most successful ways to do this is to retrain the model on some texts written by humans, and others created by machines, so it learns to differentiate between the two, says Muhammad Abdul-Mageed, who is the Canada research chair in natural-language processing and machine learning at the University of British Columbia and has studied detection. Scott Aaronson, a computer scientist at the University of Texas on secondment as a researcher at OpenAI for a year, meanwhile, has been developing watermarks for longer pieces of text generated by models such as GPT-3—“an otherwise unnoticeable secret signal in its choices of words, which you can use to prove later that, yes, this came from GPT,” he writes in his blog. A spokesperson for OpenAI confirmed that the company is working on watermarks, and said its policies state that users should clearly indicate text generated by AI “in a way no one could reasonably miss or misunderstand.” But these technical fixes come with big caveats. Most of them don’t stand a chance against the latest generation of AI language models, as they are built on GPT-2 or other earlier models. Many of these detection tools work best when there is a lot of text available; they will be less efficient in some concrete use cases, like chatbots or email assistants, which rely on shorter conversations and provide less data to analyze. And using large language models for detection also requires powerful computers, and access to the AI model itself, which tech companies don’t allow, Abdul-Mageed says. The bigger and more powerful the model, the harder it is to build AI models to detect what text is written by a human and what isn’t, says Solaiman. “What’s so concerning now is that [ChatGPT has] really impressive outputs. Detection models just can’t keep up. You’re playing catch-up this whole time,” she says. Training the human eye There is no silver bullet for detecting AI-written text, says Solaiman. “A detection model is not going to be your answer for detecting synthetic text in the same way that a safety filter is not going to be your answer for mitigating biases,” she says. To have a chance of solving the problem, we’ll need improved technical fixes and more transparency around when humans are interacting with an AI, and people will need to learn to spot the signs of AI-written sentences. “What would be really nice to have is a plug-in to Chrome or to whatever web browser you’re using that will let you know if any text on your web page is machine generated,” Ippolito says. Some help is already out there. Researchers at Harvard and IBM developed a tool called Giant Language Model Test Room (GLTR), which supports humans by highlighting passages that might have been generated by a computer program. But AI is already fooling us. Researchers at Cornell University found that people found fake news articles generated by GPT-2 credible about 66% of the time. Another study found that untrained humans were able to correctly spot text generated by GPT-3 only at a level consistent with random chance. The good news is that people can be trained to be better at spotting AI-generated text, Ippolito says. She built a game to test how many sentences a computer can generate before a player catches on that it’s not human, and found that people got gradually better over time. “If you look at lots of generative texts and you try to figure out what doesn’t make sense about it, you can get better at this task,” she says. One way is to pick up on implausible statements, like the AI saying it takes 60 minutes to make a cup of coffee. GPT-3, ChatGPT’s predecessor, has only been around since 2020. OpenAI says ChatGPT is a demo, but it is only a matter of time before similarly powerful models are developed and rolled out into products such as chatbots for use in customer service or health care. And that’s the crux of the problem: the speed of development in this sector means that every way to spot AI-generated text becomes outdated very quickly. It’s an arms race—and right now, we’re losing. hide by Melissa Heikkilä 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 "

"ChatGPT plugins"

"https://openai.com/blog/chatgpt-plugins"

"Close Search Skip to main content Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Search Navigation quick links Log in Try ChatGPT Menu Mobile Navigation Close Site Navigation Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Safety Company About Blog Careers Residency Charter Security Customer stories Quick Links Log in Try ChatGPT Search Blog ChatGPT plugins We’ve implemented initial support for plugins in ChatGPT. Plugins are tools designed specifically for language models with safety as a core principle, and help ChatGPT access up-to-date information, run computations, or use third-party services. Quick links Join plugins waitlist Read documentation Illustration: Ruby Chen March 23, 2023 Authors OpenAI Announcements , Product In line with our iterative deployment philosophy, we are gradually rolling out plugins in ChatGPT so we can study their real-world use, impact, and safety and alignment challenges—all of which we’ll have to get right in order to achieve our mission. Users have been asking for plugins since we launched ChatGPT (and many developers are experimenting with similar ideas ) because they unlock a vast range of possible use cases. We’re starting with a small set of users and are planning to gradually roll out larger-scale access as we learn more (for plugin developers, ChatGPT users, and after an alpha period, API users who would like to integrate plugins into their products). We’re excited to build a community shaping the future of the human–AI interaction paradigm. Plugin developers who have been invited off our waitlist can use our documentation to build a plugin for ChatGPT, which then lists the enabled plugins in the prompt shown to the language model as well as documentation to instruct the model how to use each. The first plugins have been created by Expedia , FiscalNote , Instacart , KAYAK , Klarna , Milo , OpenTable , Shopify , Slack , Speak , Wolfram , and Zapier. Expedia Bring your trip plans to life—get there, stay there, find things to see and do. FiscalNote Provides and enables access to select market-leading, real-time data sets for legal, political, and regulatory data and information. Instacart Order from your favorite local grocery stores. KAYAK Search for flights, stays and rental cars. Get recommendations for all the places you can go within your budget. Klarna Shopping Search and compare prices from thousands of online shops. Milo Family AI Giving parents superpowers to turn the manic to magic, 20 minutes each day. Ask: Hey Milo, what’s magic today? OpenTable Provides restaurant recommendations, with a direct link to book. Shop Search for millions of products from the world’s greatest brands. Speak Learn how to say anything in another language with Speak, your AI-powered language tutor. Wolfram Access computation, math, curated knowledge & real-time data through Wolfram|Alpha and Wolfram Language. Zapier Interact with over 5,000+ apps like Google Sheets, Trello, Gmail, HubSpot, Salesforce, and more. We’re also hosting two plugins ourselves, a web browser and code interpreter. We’ve also open-sourced the code for a knowledge base retrieval plugin , to be self-hosted by any developer with information with which they’d like to augment ChatGPT. Today, we will begin extending plugin alpha access to users and developers from our waitlist. While we will initially prioritize a small number of developers and ChatGPT Plus users, we plan to roll out larger-scale access over time. Example of how to use ChatGPT plugins 00:59 Overview Language models today, while useful for a variety of tasks, are still limited. The only information they can learn from is their training data. This information can be out-of-date and is one-size fits all across applications. Furthermore, the only thing language models can do out-of-the-box is emit text. This text can contain useful instructions, but to actually follow these instructions you need another process. Though not a perfect analogy, plugins can be “eyes and ears” for language models, giving them access to information that is too recent, too personal, or too specific to be included in the training data. In response to a user’s explicit request, plugins can also enable language models to perform safe, constrained actions on their behalf, increasing the usefulness of the system overall. We expect that open standards will emerge to unify the ways in which applications expose an AI-facing interface. We are working on an early attempt at what such a standard might look like, and we’re looking for feedback from developers interested in building with us. Today, we’re beginning to gradually enable existing plugins from our early collaborators for ChatGPT users, beginning with ChatGPT Plus subscribers. We’re also beginning to roll out the ability for developers to create their own plugins for ChatGPT. In the coming months, as we learn from deployment and continue to improve our safety systems, we’ll iterate on this protocol, and we plan to enable developers using OpenAI models to integrate plugins into their own applications beyond ChatGPT. Safety and broader implications Connecting language models to external tools introduces new opportunities as well as significant new risks. Plugins offer the potential to tackle various challenges associated with large language models, including “hallucinations,” keeping up with recent events, and accessing (with permission) proprietary information sources. By integrating explicit access to external data—such as up-to-date information online, code-based calculations, or custom plugin-retrieved information—language models can strengthen their responses with evidence-based references. These references not only enhance the model’s utility but also enable users to assess the trustworthiness of the model’s output and double-check its accuracy, potentially mitigating risks related to overreliance as discussed in our recent GPT-4 system card. Lastly, the value of plugins may go well beyond addressing existing limitations by helping users with a variety of new use cases, ranging from browsing product catalogs to booking flights or ordering food. At the same time, there’s a risk that plugins could increase safety challenges by taking harmful or unintended actions, increasing the capabilities of bad actors who would defraud, mislead, or abuse others. By increasing the range of possible applications, plugins may raise the risk of negative consequences from mistaken or misaligned actions taken by the model in new domains. From day one, these factors have guided the development of our plugin platform, and we have implemented several safeguards. From day one, these factors have guided the development of our plugin platform, and we have implemented several safeguards. We’ve performed red-teaming exercises, both internally and with external collaborators, that have revealed a number of possible concerning scenarios. For example, our red teamers discovered ways for plugins—if released without safeguards—to perform sophisticated prompt injection, send fraudulent and spam emails, bypass safety restrictions, or misuse information sent to the plugin. We’re using these findings to inform safety-by-design mitigations that restrict risky plugin behaviors and improve transparency of how and when they're operating as part of the user experience. We're also using these findings to inform our decision to gradually deploy access to plugins. If you’re a researcher interested in studying safety risks or mitigations in this area, we encourage you to make use of our Researcher Access Program. We also invite developers and researchers to submit plugin-related safety and capability evaluations as part of our recently open-sourced Evals framework. Plugins will likely have wide-ranging societal implications. For example, we recently released a working paper which found that language models with access to tools will likely have much greater economic impacts than those without, and more generally, in line with other researchers’ findings, we expect the current wave of AI technologies to have a big effect on the pace of job transformation, displacement, and creation. We are eager to collaborate with external researchers and our customers to study these impacts. Browsing Alpha Motivated by past work (our own WebGPT , as well as GopherCite , BlenderBot2 , LaMDA2 and others ), allowing language models to read information from the internet strictly expands the amount of content they can discuss, going beyond the training corpus to fresh information from the present day. Here’s an example of the kind of experience that browsing opens up to ChatGPT users, that previously would have had the model politely point out that its training data didn’t include enough information to let it answer. This example, in which ChatGPT retrieves recent information about the latest Oscars, and then performs now-familiar ChatGPT poetry feats, is one way that browsing can be an additive experience. ChatGPT browsing plugin demo 01:11 In addition to providing obvious utility to end-users, we think enabling language and chat models to do thorough and interpretable research has exciting prospects for scalable alignment. TD Can you tell me what person/movie won the oscar for these categories? - Best Actor - Best soundtrack - Best picture - Best supporting actor And then come up with a poem linking them together OAI Searched: "Oscar winners Best Actor Best Soundtrack Best Picture Best Supporting Actor" Clicked on: Oscar winners 2023: See the full list | CNN Going back to last page Clicked on: Oscar winners 2023: See the full list | CNN Going back to last page Clicked on: List of 2023 Oscar Winners - ABC News Reading content Finished browsing Finished browsing Here are the Oscar winners for the categories you requested: • Best Actor: Brendan Fraser, "The Whale" • Best Soundtrack (Original Song): "Naatu Naatu" from "RRR" • Best Picture: "Everything Everywhere All at Once" • Best Supporting Actor: Ke Huy Quan, "Everything Everywhere All at Once" 1 List of 2023 Oscar Winners - ABC News Here is a poem linking them together: In the depths of the ocean, "The Whale" did roam, With Brendan Fraser's performance, a light was shone, While "Naatu Naatu" played with rhythm and beat, From "RRR", a soundtrack that's truly a treat. "Everything Everywhere All at Once" took the stage, Winning Best Picture, a triumph for this age, With Ke Huy Quan in a supporting role, His performance captured our hearts, our very soul. So here's to the winners, to the stories they've spun, To the music, the acting, the battles they've won, For in the world of cinema, they've made their mark, Leaving an imprint, a flame, a lasting spark. Safety considerations We’ve created a web browsing plugin which gives a language model access to a web browser, with its design prioritizing both safety and operating as a good citizen of the web. The plugin’s text-based web browser is limited to making GET requests, which reduces (but does not eliminate) certain classes of safety risks. This scopes the browsing plugin to be useful for retrieving information, but excludes “transactional” operations such as form submission which have more surface area for security and safety issues. Browsing retrieves content from the web using the Bing search API. As a result, we inherit substantial work from Microsoft on (1) source reliability and truthfulness of information and (2) “safe-mode” to prevent the retrieval of problematic content. The plugin operates within an isolated service, so ChatGPT’s browsing activities are separated from the rest of our infrastructure. To respect content creators and adhere to the web’s norms, our browser plugin’s user-agent token is ChatGPT-User and is configured to honor websites' robots.txt files. This may occasionally result in a “click failed” message, which indicates that the plugin is honoring the website's instruction to avoid crawling it. This user-agent will only be used to take direct actions on behalf of ChatGPT users and is not used for crawling the web in any automatic fashion. We have also published our IP egress ranges. Additionally, rate-limiting measures have been implemented to avoid sending excessive traffic to websites. Click failed You can block ChatGPT crawling your site using the robots.txt file, ChatGPT will show this error message when this happens. Our browsing plugin shows websites visited and cites its sources in ChatGPT’s responses. This added layer of transparency helps users verify the accuracy of the model’s responses and also gives credit back to content creators. We appreciate that this is a new method of interacting with the web, and welcome feedback on additional ways to drive traffic back to sources and add to the overall health of the ecosystem. Code interpreter Alpha We provide our models with a working Python interpreter in a sandboxed, firewalled execution environment, along with some ephemeral disk space. Code run by our interpreter plugin is evaluated in a persistent session that is alive for the duration of a chat conversation (with an upper-bound timeout) and subsequent calls can build on top of each other. We support uploading files to the current conversation workspace and downloading the results of your work. JW a brick weighs 30% of a brick plus five GPUs there are 100 bricks and 200 GPUs in a metric ton how much does a brick weigh? OAI Let's call the weight of a brick "B" and the weight of a GPU "G". We can set up an equation based on the information given: B = 0.3 * B + 5 * G We can also set up another equation based on the total weight of 100 bricks and 200 GPUs being equal to 1 metric ton (1000 kilograms): 100 * B + 200 * G = 1000 We can solve this system of equations to find the weight of a brick (B) and the weight of a GPU (G). Finished calculating The weight of a brick is 7.8125 kg. We would like our models to be able to use their programming skills to provide a much more natural interface to most fundamental capabilities of our computers. Having access to a very eager junior programmer working at the speed of your fingertips can make completely new workflows effortless and efficient, as well as open the benefits of programming to new audiences. From our initial user studies, we’ve identified use cases where using code interpreter is especially useful: Solving mathematical problems, both quantitative and qualitative Doing data analysis and visualization Converting files between formats We invite users to try the code interpreter integration and discover other useful tasks. ChatGPT interpreter plugin demo 03:25 Safety considerations The primary consideration for connecting our models to a programming language interpreter is properly sandboxing the execution so that AI-generated code does not have unintended side-effects in the real world. We execute code in a secured environment and use strict network controls to prevent external internet access from executed code. Additionally, we have set resource limits on each session. Disabling internet access limits the functionality of our code sandbox, but we believe it’s the right initial tradeoff. Third-party plugins were designed as a safety-first method of connecting our models to the outside world. Retrieval The open-source retrieval plugin enables ChatGPT to access personal or organizational information sources (with permission). It allows users to obtain the most relevant document snippets from their data sources, such as files, notes, emails or public documentation, by asking questions or expressing needs in natural language. As an open-source and self-hosted solution, developers can deploy their own version of the plugin and register it with ChatGPT. The plugin leverages OpenAI embeddings and allows developers to choose a vector database ( Milvus , Pinecone , Qdrant , Redis , Weaviate or Zilliz ) for indexing and searching documents. Information sources can be synchronized with the database using webhooks. To begin, visit the retrieval plugin repository. ChatGPT retrieval plugin demo 00:40 Security considerations The retrieval plugin allows ChatGPT to search a vector database of content, and add the best results into the ChatGPT session. This means it doesn’t have any external effects, and the main risk is data authorization and privacy. Developers should only add content into their retrieval plugin that they are authorized to use and can share in users’ ChatGPT sessions. Third-party plugins Alpha Model Plugins Alpha Choose plugins OpenTable Make and manage reservations at your favorite restaurants OpenTable Wolfram Instacart Plugin store Third-party plugins are described by a manifest file , which includes a machine-readable description of the plugin’s capabilities and how to invoke them, as well as user-facing documentation. An example manifest file for a plugin for managing to-dos The steps for creating a plugin are: Build an API with endpoints you’d like a language model to call (this can be a new API, an existing API, or a wrapper around an existing API specifically designed for LLMs). Create an OpenAPI specification documenting your API, and a manifest file that links to the OpenAPI spec and includes some plugin-specific metadata. When starting a conversation on chat.openai.com , users can choose which third-party plugins they’d like to be enabled. Documentation about the enabled plugins is shown to the language model as part of the conversation context, enabling the model to invoke appropriate plugin APIs as needed to fulfill user intent. For now, plugins are designed for calling backend APIs, but we are exploring plugins that can call client-side APIs as well. ChatGPT third-party plugins demo 01:09 ChatGPT plugins developer experience 03:13 Looking forward We’re working to develop plugins and bring them to a broader audience. We have a lot to learn, and with the help of everyone, we hope to build something that is both useful and safe. Join plugins waitlist Read documentation Authors OpenAI View all articles Acknowledgments Contributors Sandhini Agarwal, Ilge Akkaya, Valerie Balcom, Mo Bavarian, Gabriel Bernadett-Shapiro, Greg Brockman, Miles Brundage, Jeff Chan, Fotis Chantzis, Noah Deutsch, Brydon Eastman, Atty Eleti, Niko Felix, Simón Posada Fishman, Isa Fulford, Christian Gibson, Joshua Gross, Mike Heaton, Jacob Hilton, Xin Hu, Shawn Jain, Joy Jiao, Haozhun Jin, Logan Kilpatrick, Christina Kim, Michael Kolhede, Andrew Mayne, Paul McMillan, David Medina, Jacob Menick, Andrey Mishchenko, Ashvin Nair, Rajeev Nayak, Arvind Neelakantan, Rohan Nuttall, Joel Parish, Alex Tachard Passos, Adam Perelman, Filipe de Avila Belbute Peres, Vitchyr Pong, John Schulman, Eric Sigler, Natalie Staudacher, Nicholas Turley, Jerry Tworek, Ryan Greene, Arun Vijayvergiya, Chelsea Voss, Jiayi Weng, Matt Wiethoff, Sarah Yoo, Kevin Yu, Wojciech Zaremba, Shengjia Zhao, Will Zhuk, Barret Zoph Research Overview Index GPT-4 DALL·E 3 API Overview Data privacy Pricing Docs ChatGPT Overview Enterprise Try ChatGPT Company About Blog Careers Charter Security Customer stories Safety OpenAI © 2015 – 2023 Terms & policies Privacy policy Brand guidelines Social Twitter YouTube GitHub SoundCloud LinkedIn Back to top "

"The dark secret behind those cute AI-generated animal images | MIT Technology Review"

"https://www.technologyreview.com/2022/05/25/1052695/dark-secret-cute-ai-animal-images-dalle-openai-imagen-google"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts The dark secret behind those cute AI-generated animal images Google Brain has revealed its own image-making AI, called Imagen. But don't expect to see anything that isn't wholesome. By Will Douglas Heaven archive page Google Another month, another flood of weird and wonderful images generated by an artificial intelligence. In April, OpenAI showed off its new picture-making neural network, DALL-E 2 , which could produce remarkable high-res images of almost anything it was asked to. It outstripped the original DALL-E in almost every way. Now, just a few weeks later, Google Brain has revealed its own image-making AI, called Imagen. And it performs even better than DALL-E 2: it scores higher on a standard measure for rating the quality of computer-generated images, and the pictures it produced were preferred by a group of human judges. “We’re living through the AI space race!” one Twitter user commented. “The stock image industry is officially toast,” tweeted another. We are thrilled to announce Imagen, a text-to-image model with unprecedented photorealism and deep language understanding. Explore https://t.co/mSplg4FlsM and Imagen! A large rusted ship stuck in a frozen lake. Snowy mountains and beautiful sunset in the background. #imagen pic.twitter.com/96Vfo2kXJz Many of Imagen’s images are indeed jaw-dropping. At a glance, some of its outdoor scenes could have been lifted from the pages of National Geographic. Marketing teams could use Imagen to produce billboard-ready advertisements with just a few clicks. But as OpenAI did with DALL-E, Google is going all in on cuteness. Both firms promote their tools with pictures of anthropomorphic animals doing adorable things: a fuzzy panda dressed as a chef making dough, a corgi sitting in a house made of sushi, a teddy bear swimming the 400-meter butterfly at the Olympics—and it goes on. New @GoogleAI work: Input: "Two meerkats sitting next to each other on top of a mountain and looking at the beautiful landscape. There is a mountain, a river lake, and fields of yellow flowers. There are hot air balloons in the sky." #imagen https://t.co/JEgyNrcJjl Output: https://t.co/uj4urjnZPF pic.twitter.com/I1zx8ZARBl There’s a technical, as well as PR, reason for this. Mixing concepts like “fuzzy panda” and “making dough” forces the neural network to learn how to manipulate those concepts in a way that makes sense. But the cuteness hides a darker side to these tools, one that the public doesn’t get to see because it would reveal the ugly truth about how they are created. Most of the images that OpenAI and Google make public are cherry-picked. We only see cute images that match their prompts with uncanny accuracy—that’s to be expected. But we also see no images that contain hateful stereotypes, racism, or misogyny. There is no violent, sexist imagery. There is no panda porn. And from what we know about how these tools are built—there should be. Not a single human face depicted in the hundreds of pictures in the paper, haha. I guess that's one way to eliminate concerns over representation bias. https://t.co/tKX8khoTDR It’s no secret that large models, such as DALL-E 2 and Imagen, trained on vast numbers of documents and images taken from the web, absorb the worst aspects of that data as well as the best. OpenAI and Google explicitly acknowledge this. Scroll down the Imagen website —past the dragon fruit wearing a karate belt and the small cactus wearing a hat and sunglasses—to the section on societal impact and you get this: “While a subset of our training data was filtered to removed noise and undesirable content, such as pornographic imagery and toxic language, we also utilized [the] LAION-400M dataset which is known to contain a wide range of inappropriate content including pornographic imagery, racist slurs, and harmful social stereotypes. Imagen relies on text encoders trained on uncurated web-scale data, and thus inherits the social biases and limitations of large language models. As such, there is a risk that Imagen has encoded harmful stereotypes and representations, which guides our decision to not release Imagen for public use without further safeguards in place.” It's the same kind of acknowledgement that OpenAI made when it revealed GPT-3 in 2019: “internet-trained models have internet-scale biases.” And as Mike Cook, who researches AI creativity at Queen Mary University of London, has pointed out, it’s in the ethics statements that accompanied Google’s large language model PaLM and OpenAI’s DALL-E 2. In short, these firms know that their models are capable of producing awful content, and they have no idea how to fix that. I feel like at some point in the last few years we somehow confused "AI ethics" with "pointing at the mess you made and shrugging". https://t.co/JEu2ngilEZ pic.twitter.com/mMbNQUzgXW For now, the solution is to keep them caged up. OpenAI is making DALL-E 2 available only to a handful of trusted users; Google has no plans to release Imagen. That’s fine if these were simply proprietary tools. But these firms are pushing the boundaries of what AI can do and their work shapes the kind of AI that all of us live with. They are creating new marvels, but also new horrors— and moving on with a shrug. When Google’s in-house ethics team raised problems with the large language models , in 2020 it sparked a fight that ended with two of its leading researchers being fired. Large language models and image-making AIs have the potential to be world-changing technologies, but only if their toxicity is tamed. This will require a lot more research. There are small steps to open these kinds of neural network up for widespread study. A few weeks ago Meta released a large language model to researchers , warts and all. And Hugging Face is set to release its open-source version of GPT-3 in the next couple of months. For now, enjoy the teddies. 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 "

"Cheat Codex | MIT Technology Review"

"https://www.technologyreview.com/2023/04/26/1071539/cheat-codex"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Cheat Codex A close-up look at the ethical dilemmas created by ChatGPT. By Mat Honan archive page Robyn Kessler Welcome to the Education Issue. I cheated on my editor’s letter. This one that you are reading right now. I’m very sorry. Look, I didn’t set out to do this, but the thing about magazines is that they have very hard deadlines, and if you miss them, you’re left with blank pages. So when I realized I only had a few hours left to finalize this, well, I freaked out. And then I did what an increasing number of us are doing: I turned to ChatGPT, OpenAI’s massively mind-blowing generative AI software, to help me out. After training it on some of my previous work, I asked about the use of AI in education. AI is already doing big things in education. By crunching massive amounts of data on student performance, AI algorithms can tailor instruction to fit the needs of individual learners, which can mean big improvements in student outcomes. Chatbots and virtual assistants can provide students with on-the-spot assistance and feedback. Who needs a tutor when you have an intelligent assistant? But here’s where things get really exciting: language models like ChatGPT can actually generate human-like text, which makes them perfect for a whole bunch of educational applications. These models can create interactive learning materials, like chatbots that answer students’ questions or create personalized quizzes. They can even generate summaries of complex texts, reports on data sets, or entire essays and research papers. There are definitely some challenges as well. One of the biggest concerns is the risk of bias in the algorithms. We need to make sure these algorithms are designed and tested in a way that ensures all students get a fair shake. Another, of course, is the potential for cheating. But the bottom line is that AI and language models like ChatGPT are going to change the way we think about education, and we need to make sure we’re using these tools in ways that are ethical, equitable, and effective. So are the preceding four paragraphs, which were generated by ChatGPT and then lightly edited by me, ethical? If they were presented as my own work without an explicit disclosure (like this one), I would argue that the answer is no. And even with such a disclosure, we’re still in a bit of a gray area—there are all sorts of questions about everything from plagiarism to accuracy to the data these models were trained on. The reality is that we are in an entirely new place when it comes to the use of AI in education, and it is far from clear what that is going to mean. The world has changed, and there’s no going back. As William Douglas Heaven, our senior editor for AI, makes clear in this issue’s cover story , technologies like ChatGPT will have all sorts of genuinely useful and transformative applications in the classroom. Yes, they will almost certainly also be used for cheating. But banishing these kinds of technologies from the classroom, rather than trying to harness them, is shortsighted. Rohan Mehta, a 17-year-old high school student in Pennsylvania, makes a similar argument, suggesting that the path forward starts with a show of faith by letting students experiment with the tool. Meanwhile, Arian Khameneh takes us inside a classroom in Denmark where students are using mood-­monitoring apps as the country struggles with a huge increase in depression among young people. You’ll also find a story from Moira Donovan about how AI is being used to help further our analysis and understanding of centuries-old texts, transforming humanities research in the process. Joy Lisi Rankin dives deep into the long history of the learn-to-code movement and its evolution toward diversity and inclusion. And please do not miss Susie Cagle’s story about a California school that, rather than having students try to flee from wildfire, hardened its facilities to ride out the flames, and what we can learn from that experience. Of course, we have a lot more for you to read, and hopefully think about, as well. And as always, I would love to hear your feedback. You can even use ChatGPT to generate it—I won’t mind. Thank you, Mat @mat/ [email protected] hide by Mat Honan 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 May/June 2023 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 Humans and technology Why embracing complexity is the real challenge in software today In the midst of industry discussions about productivity and automation, it’s all too easy to overlook the importance of properly reckoning with complexity. By Ken Mugrage archive page Turning medical data into actionable knowledge Technology can transform patient care by bringing together data from a variety of sources By Siemens Healthineers archive page Moving data through the supply chain with unprecedented speed Tackle supply chain visibility and customer engagement with standards and “phygital” technology. By MIT Technology Review Insights archive page Customer experience horizons The big ideas that define the future of customer and employee experience. By MIT Technology Review Insights 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 "

"Shift happens: Writing about the history of keyboards | MIT Technology Review"

"https://www.technologyreview.com/2023/04/26/1071536/history-keyboards-kickstarter-marcin-wichary"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Shift happens: Writing about the history of keyboards After discovering that a history of keyboards— from typewriters to iPhones—had yet to be written, designer and typographer Marcin Wichary got to work. By Allison Arieff archive page Marcin Wichary and his keyboards. “It sounds really boring, right?” he says. “But if you look at it throughout the ages ... it becomes a lot more interesting.” When the designer and typographer Marcin Wichary stumbled upon a tiny museum just outside Barcelona five years ago, the experience tipped his interest in the history of technology into an obsession with a very particular part of it: the keyboard. “I have never seen so many typewriters under one roof. Not even close,” he shared on Twitter at the time. “At this point, I literally have tears in my eyes. I’m not kidding. This feels like a miracle.” He’d had a revelation while wandering through the exhibit: Each key on a keyboard has its own stories. And these stories are not just about computing technology, but also about the people who designed, used, or otherwise interacted with the keyboards. Take the backspace key, he explains: “I like that [the concept of] backspace was originally just that—a space going backward. We are used to it erasing now, but for a hundred years, erasing was its own incredibly complex endeavor. You needed to master a Comet eraser, or Wite-Out, or strange correction tapes, and possibly all of the above … or give up and start from scratch whenever you made a typo.” These days, even the cheapest desk keyboard is in some way “ergonomic,” allowing for reduced effort and improved response compared with even the best of the mechanical and electric typewriters that preceded them. But some keyboards go further than most, rotating or tenting their respective halves to allow a less stressful hand and arm position. Some keyboards enable communication between people who might find that difficult. Shown here are a simple keyboard connected to a singular Braille cell; a typewriter making it possible to print in Braille; and a machine that allowed people who are hard of hearing to type over telephone wires. The deeper he researched, the more fixated he became. Amazed that no comprehensive book existed on the history of keyboards, he decided to create his own. When not working at his day job as design lead for the design software company Figma, he began producing Shift Happens , a two-volume, 1,216-page hardcover book—and raised over $750,000 for the project on Kickstarter in March of 2023. Wichary was only a bit surprised by the support and the keyboard’s wide appeal. As he points out, “It’s such a crucial device that occupies a lot of our waking life.” hide by Allison Arieff 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 May/June 2023 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 Humans and technology Why embracing complexity is the real challenge in software today In the midst of industry discussions about productivity and automation, it’s all too easy to overlook the importance of properly reckoning with complexity. By Ken Mugrage archive page Turning medical data into actionable knowledge Technology can transform patient care by bringing together data from a variety of sources By Siemens Healthineers archive page Moving data through the supply chain with unprecedented speed Tackle supply chain visibility and customer engagement with standards and “phygital” technology. By MIT Technology Review Insights archive page Customer experience horizons The big ideas that define the future of customer and employee experience. By MIT Technology Review Insights 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 "

"Prisoners are using VR to learn real-world skills | MIT Technology Review"

"https://www.technologyreview.com/2023/04/26/1071412/inmates-vr-real-world-skills-incarcerated-instructions"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Inmates are using VR to learn real-world skills Corrections systems are using simulators to provide incarcerated individuals with more lifelike instruction. But is it working? By Daliah Singer archive page Getty Images Atorrus Rainer, age 41, is standing in the center of a stuffy, ­fluorescent-lit room. A virtual-reality headset covers his eyes like oversize goggles. Every so often, he extends his arm, using the VR controller to pick up garbage bags, a toothbrush, and toilet paper during a simulated trip to the supermarket. The experience is limited—Rainer has to follow a pre-written shopping list and can only travel to specific locations within the empty store—but the sheer number of products available, even in this digital world, still overwhelms him. So does the self-checkout station: those didn’t exist in 2001, when Rainer, then a teenager, was sentenced to more than 100 years in prison. His first experience with one is this virtual interaction taking place inside Fremont Correctional Facility, a medium-security prison about two hours south of Denver. Rainer is practicing in the hopes of stepping into a real store in the near future through an initiative launched in Colorado in 2017 in response to US Supreme Court rulings that deemed juvenile life without parole sentences unconstitutional. People who meet certain requirements—for example, if they were under 21 when they committed felony crimes and have been incarcerated for a minimum of 20 to 30 years—can apply to work through the three-year Juveniles and Young Adults Convicted as Adults Program (JYACAP) in an effort to earn early parole. The premise of JYACAP is that learning the basic skills they missed the chance to acquire while incarcerated will provide these juvenile lifers with their best chances for success upon release. That’s a formidable challenge. Because of safety concerns, they have had limited access to the internet. Though they’re now adults, many have never used, or even seen, a smartphone or a laptop. Or had a credit card. “We had to figure out a way of giving them these opportunities in a restricted environment,” says Melissa Smith, interim director of prisons for the Colorado Department of Corrections. Though its use is not yet widespread, a handful of state corrections departments, from Ohio to New Mexico, have turned to virtual reality as an answer. The goals vary from helping reduce aggressive behavior to facilitating empathy with victims to, as in Colorado’s case, reducing recidivism. Though the state’s prison budget sits close to $1 billion, Colorado has one of the worst return-to-prison rates in the country, at around 50%. Nationally, as many as two-thirds of the 600,000 people released from state and federal prisons each year will be rearrested within three years. Is VR the long-missing piece in an unwieldy puzzle of resources and programs meant to help reverse these statistics? Or is it yet another experiment that will fail to adequately prepare incarcerated individuals for life beyond lockup? “It’s not going to be the silver bullet, but it is a tool that I think is very powerful for a lot of people, because they never really get a chance to practice what we’re trying to teach them,” says Bobbie Ticknor, an associate professor of criminal justice at Valdosta State University. “I think we should use everything we can find and see what works the best.” Proponents like Ticknor say VR can immerse incarcerated people in the sights and sounds of modern life and help them develop digital literacy in a secure corrections environment. “When you’re role-playing, when you’re learning a new skill, the closer you can bring them to doing what they’re actually going to have to do out in the real world, the better,” says Ethan Moeller, founder and managing director of Virtual Training Partners, which helps organizations successfully implement virtual-­reality tools. “VR does that better than any other training medium.” Others are more skeptical. Like Dr. Cyndi Rickards, an associate teaching professor at Drexel University who leads weekly criminology courses inside Philadelphia prisons. People who are incarcerated wear the “label of inmate on their back. It’s a dehumanizing system,” she says, “so to suggest that VR is going to reintegrate them into society after being in a punitive system...just further objectifies folks, it continues a pattern of dehumanizing folks, and I’ve not read any compelling evidence that this is the route we should use to integrate people to be members of a healthy and contributing society.” Related Story On key metrics, a VR experience elicited a response indistinguishable from subjects who took medium doses of LSD or magic mushrooms. Rainer believes the grocery store simulation was beneficial but is aware that the real world, should he step back into it, will be very different from the video-game-like version he’s interacting with at Fremont. “Going back to society, I don’t want to freeze up while I’m in a grocery store or something, not figuring out what I need to buy because [there are] too many options,” he says. “I don’t really like working on a computer, but I know I got to.” As VR technology grows more affordable, the programming becomes an increasingly budget-friendly option for states that are already dealing with persistent workforce shortages. “If we reduce recidivism rates, it actually helps the community and reduces crime,” explains Sarah Rimel, the former technology research program manager at Colorado’s National Mental Health Innovation Center. “It reduces the amount of money that’s put into the prison systems.” VR has proved a beneficial therapeutic tool, helping to lower depression rates, reduce anxiety , conquer phobias , promote emotional empathy, and address post-traumatic stress. VR exposure therapy has been successfully used to help vulnerable populations such as veterans and sexual-assault survivors confront, and better cope with, their triggers and trauma. All that research is based on interventions done with people who are not incarcerated, however. The currently available evidence in correctional settings is limited and mostly anecdotal. But there have been some positive findings. For example, a short-term pilot initiative in Alaska that incorporated mindfulness techniques through VR resulted in decreased reports of depressive or anxious feelings and fewer disciplinary write-ups. In Michigan, a virtual-reality tool for job interview training, originally developed for people with serious mental illness, was piloted with 44 men involved with the justice system. The findings, published in March 2022 , showed that 82% of those who used the tool landed a job within six months of being released, compared with 69% of other program participants. When variables like age, race, and time served were taken into account, the data suggested that those who used the tool had 7.4 times greater odds of getting a job. “Above just the employment rate, those that interviewed with Molly [the virtual hiring manager] had stronger interview skills over time, greater reductions in interview anxiety over time, and greater increase in motivation to interview over time,” says Matthew Smith, a professor of social work at the University of Michigan, who led the effort. He and his team are now enrolling a larger group in a validation study. Colorado doesn’t have any data sets to point to. Only one of the 16 people who’ve been released through JYACAP over the course of almost three years have been rearrested. Two of those 16 were paroled before completing the full curriculum. “If the right scenarios are used,” says Cheryl Armstrong, one of the first JYACAP graduates, “it [VR] is helpful, to a certain extent, to give you an idea of what you’re going to be facing.” While Valdosta State’s Ticknor estimates that fewer than 10% of corrections facilities are currently using VR simulators with incarcerated individuals, she expects that to change soon. “I would be very surprised within five years if this is not a very regular treatment modality for this particular population,” she says. Daliah Singer is a freelance journalist based in Denver. hide by Daliah Singer 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 May/June 2023 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 Humans and technology Why embracing complexity is the real challenge in software today In the midst of industry discussions about productivity and automation, it’s all too easy to overlook the importance of properly reckoning with complexity. By Ken Mugrage archive page Turning medical data into actionable knowledge Technology can transform patient care by bringing together data from a variety of sources By Siemens Healthineers archive page Moving data through the supply chain with unprecedented speed Tackle supply chain visibility and customer engagement with standards and “phygital” technology. By MIT Technology Review Insights archive page Customer experience horizons The big ideas that define the future of customer and employee experience. By MIT Technology Review Insights 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 "

"Learning to code isn’t enough | MIT Technology Review"

"https://www.technologyreview.com/2023/04/20/1071291/learn-to-code-legacy-new-projects-education"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Learning to code isn’t enough Historically, learn-to-code efforts have provided opportunities for the few, but new efforts are aiming to be inclusive. By Joy Lisi Rankin archive page Black Girls Code works to increase the number of women of color working in technology by introducing girls to computer science. AP Photo/Bebeto Matthews A decade ago, tech powerhouses the likes of Microsoft, Google, and Amazon helped boost the nonprofit Code.org, a learn-to-code program with a vision : “That every student in every school has the opportunity to learn computer science as part of their core K–12 education.” It was followed by a wave of nonprofits and for-profits alike dedicated to coding and learning computer science; some of the many others include Codecademy , Treehouse , Girl Develop It , and Hackbright Academy (not to mention Girls Who Code, founded the year before Code.org and promising participants, “Learn to code and change the world”). Parents can now consider top-10 lists of coding summer camps for kids. Some may choose to start their children even younger, with the Baby Code! series of board books —because “it’s never too early to get little ones interested in computer coding.” Riding this wave of enthusiasm, in 2016 President Barack Obama launched an initiative called Computer Science for All , proposing billions of dollars in funding to arm students with the “computational thinking skills they need” to “thrive in a digital economy.” Now, in 2023, North Carolina is considering making coding a high school graduation requirement. If lawmakers enact that curriculum change, they will be following in the footsteps of five other states with similar policies that consider coding and computer education foundational to a well-rounded education: Nevada, South Carolina, Tennessee, Arkansas, and Nebraska. Advocates for such policies contend that they expand educational and economic opportunities for students. More and more jobs, they suggest, will require “ some kind of computer science knowledge. ” This enthusiasm for coding is nothing new. In 1978 Andrew Molnar, an expert at the National Science Foundation , argued that what he termed computer literacy was “a prerequisite to effective participation in an information society and as much a social obligation as reading literacy.” Molnar pointed as models to two programs that had originated in the 1960s. One was the Logo project centered at the MIT Artificial Intelligence Lab, which focused on exposing elementary-­age kids to computing. (MIT Technology Review is funded in part by MIT but maintains editorial independence.) The other was at Dartmouth College, where undergraduates learned how to write programs on a campus-wide computing network. The Logo and Dartmouth efforts were among several computing-related educational endeavors organized from the 1960s through 1980s. But these programs, and many that followed, often benefited the populations with the most power in society.Then as now, just learning to code is neither a pathway to a stable financial future for people from economically precarious backgrounds nor a panacea for the inadequacies of the educational system. Dartmouth: Building a BASIC computing community When mathematics professor (and future Dartmouth president) John Kemeny made a presentation to college trustees in the early 1960s hoping to persuade them to fund a campus-wide computing network, he emphasized the idea that Dartmouth students (who were at that time exclusively male, and mostly affluent and white) were the future leaders of the United States. Kemeny argued , “Since many students at an institution like Dartmouth become executives or key policy makers in industry and government, it is a certainty that they will have at their command high-speed computing equipment.” Kemeny claimed that it was “essential” for those nascent power brokers to “be acquainted with the potential and limitations of high-speed computers.” In 1963 and 1964, he and fellow mathematics professor Thomas Kurtz worked closely with Dartmouth students to design and implement a campus-wide network, while Kemeny largely took responsibility for designing an easy-to-learn programming language, called BASIC, for students (and faculty) to use on that network. Both developments were eagerly welcomed by the incoming students in the fall of 1964. Related Story For decades, coders wrote critical systems in C and C++. Now they turn to Rust. As Dartmouth’s network grew during the 1960s, network terminals were installed in the new campus computer center, in shared campus recreational spaces and dormitories, and at other locations around campus. And because the system was set up as a time-sharing network, an innovation at the time, multiple terminals could be connected to the same computer, and the people using those terminals could write and debug programs simultaneously. This was transformative: by 1968, 80% of Dartmouth undergraduates and 40% of the faculty used the network regularly. Although incoming students learned how to write a program in BASIC as a first-year math course requirement, what really fostered the computing culture was the way students made the language and the network their own. For example, the importance of football in campus life (Dartmouth claimed the Ivy League championship seven times between 1962 and 1971) inspired at least three computer football games (FTBALL, FOOTBALL, and GRIDIRON) played avidly on the Dartmouth network, one of them written by Kemeny himself. Because the network was so easy to access and BASIC was so easy to use, Dartmouth students could make computing relevant to their own lives and interests. One wrote a program to test a hypothesis for a psychology class. Another ran a program called XMAS to print his Christmas cards. Some printed out letters to parents or girlfriends. Others enjoyed an array of games, including computer bridge, checkers, and chess. Although learning to write a program in BASIC was the starting point in computing for Dartmouth students, the ways they used it to meet their own needs and forge community with their peers made the system a precursor of social networking—nearly half a century ago. Coding in BASIC didn’t replace their liberal arts curriculum requirements or extracurricular activities; rather, it complemented them. Different results: The Dartmouth network expands As it grew in popularity, other schools around New England sought to tap into Dartmouth’s computing network for their students. By April 1971, the network encompassed 30 high schools and 20 colleges in New England, New York, and New Jersey. All an individual school needed to connect were a terminal and a telephone line linking the terminal with the mainframe on Dartmouth’s campus (often the greatest expense of participating in the network, at a time when long-­distance phone calls were quite costly). Yet as BASIC moved beyond Dartmouth into heterogeneous high schools around New England, the computing culture remained homogeneous. Private high schools including Phillips Exeter, Phillips Andover, and St. Paul’s were among the first to connect, all before 1967. Within a few more years, a mix of private and public high schools joined them. The Secondary School Project (SSP), which ran from 1967 to 1970 and was supported by a three-year NSF grant secured by Kemeny and Kurtz, connected students and educators at 18 public and private high schools from Connecticut to Maine, with the goal of putting computing access (and BASIC) into as many hands as possible and observing the results. That these schools asked Dartmouth for time shares reflected interest and motivation on the part of some individual or group at each one. They wanted network access—and, by extension, access to code—because it was novel and elite. Some students were enthusiastic users, even waking at four in the morning to sign on. But access to the Dartmouth network was emphatically unequal. The private schools participating in the SSP were (at the time) all male and almost exclusively white, and those students enjoyed nearly twice as much network time as the students at coeducational public schools: 72 hours per week for private school students, and only 40 for public school students. What was intended as computing for all ultimately amplified existing inequities. In these years before the expansion of educational opportunities for girls and women in the United States, high school boys were enrolling in many more math and science classes than high school girls. The math and science students gained access to computing in those courses, meaning that BASIC moved into a system already segregated by gender—and also by race. What was intended as computing for all ultimately amplified existing inequities. Logo: Trying to change the world, one turtle at a time One state away from Dartmouth, the Logo project, founded by Seymour Papert, Cynthia Solomon, and Wally Feurzeig, sought to revolutionize how elementary and middle school students learn. Initially, the researchers created a Logo programming language and tested it between 1967 and 1969 with groups of children including fifth and seventh graders at schools near MIT in Cambridge, Massachusetts. “These kids made up hilarious sentence generators and became proficient users of their own math quizzes,” Solomon has recalled. But Logo was emphatically not just a “learn to code” effort. It grew to encompass an entire lab and a comprehensive learning system that would introduce new instructional methods, specially trained teachers, and physical objects to think and play with. Perhaps the best-remembered of those objects is the Logo Turtle , a small robot that moved along the floor, directed by computer commands, with a retractable pen underneath its body that could be lowered to draw shapes, pictures, and patterns. By the early 1970s, the Logo group was part of the MIT AI Lab, which Papert had cofounded with the computer scientist Marvin Minsky. The kid-focused learning environment provided a way to write stories, a way to draw, a way to make music, and a way to explore a space with a programmable object. Papert imagined that the Logo philosophy would empower children as “intellectual agents” who could derive their own understanding of math concepts and create connections with other disciplines ranging from psychology and the physical sciences to linguistics and logic. But the reality outside the MIT AI Lab challenged that vision. In short, teaching Logo to elementary school students was both time- and resource-­intensive. In 1977-’78, an NSF grant funded a yearlong study of Logo at a public school; it was meant to include all the school’s sixth graders, but the grant covered only four computers, which meant that only four students could participate at the same time. The research team found that most of the students who were chosen to participate did learn to create programs and express math concepts using Logo. However, when the study ended and the students moved on, their computing experiences were largely left in the past. Related Story A new kind of machine-learning model is set to improve automated decision making in finance, health care, ad targeting, and more. As that project was wrapping up, the Logo team implemented a larger-scale partnership at the private Lamplighter School in Dallas, cosponsored by Texas Instruments. At this school, with a population of 450 students in kindergarten through fourth grade, 50 computers were available. Logo was not taught as a standalone subject but was integrated into the curriculum—something that would only have been possible at a small private school like this one. The Lamplighter project—and the publication around the same time of Papert’s book Mindstorms , in which the mathematician enthused about the promise of computing to revolutionize education—marked a high point for Logo. But those creative educational computing initiatives were short-lived. A major obstacle was simply the incredibly slow-­moving and difficult-to-change bureaucracy of American public education. Moreover, promising pilots either did not scale or were unable to achieve the same results when introduced into a system fraught with resource inequities. But another issue was that the increasingly widespread availability of personal computers by the 1980s challenged Logo’s revolutionary vision. As computers became consumer objects, software did, too. People no longer needed to learn to code to be able to use a computer. In the case of American education, computers in the classroom became less about programming and more about educational games, word processing, and presentations. While BASIC and Logo continued to be taught in some schools around the United States, for many students the effort of writing some code to, say, alphabetize a list seemed impractical—disconnected from their everyday lives and their imagined futures. Corporate coding Schools weren’t the only setting for learn-to-code movements, however. In the 1960s the Association for Computing Machinery (ACM), which had been established as a professional organization in the 1940s, spearheaded similar efforts to teach coding to young people. From 1968 to 1972, ACM members operating through their local chapters established programs across the United States to provide training in computing skills to Black and Hispanic Americans. During the same years, government and social welfare organizations offered similar training, as did companies including General Electric. There were at least 18 such programs in East Coast and California cities and one in St. Louis, Missouri. Most, but not all, targeted young people. In some cases, the programs taught mainframe or keypunch operation, but others aimed to teach programming in the common business computing languages of the time, COBOL and FORTRAN. Did the students in these programs learn? The answer was emphatically yes. Could they get jobs as a result, or otherwise use their new skills? The answer to that was often no. A program in San Diego arranged for Spanish-speaking instructors and even converted a 40-foot tractor-trailer into a mobile training facility so that students—who were spread across the sprawling city—would not have to spend upwards of an hour commuting by bus to a central location. And in the Albany-Schenectady area of New York, General Electrical supported a rigorous program to prepare Black Americans for programming jobs. It was open to people without high school diplomas, and to people with police records; there was no admissions testing. Well over half the people who started this training completed it. In the ’60s, Dartmouth students had unprecedented computer access thanks to a time-sharing network that connected multiple terminals via telephone line to a central computer. Yet afterwards many could not secure jobs, even entry-level ones. In other cases, outstanding graduates were offered jobs that paid $105 per week—not enough to support themselves and their families. One consultant to the project suggested that for future training programs, GE should “give preference to younger people without families” to minimize labor costs for the company. The very existence of these training endeavors reflected a mixed set of motivations on the part of the organizers, who were mostly white, well-off volunteers. These volunteers tended to conflate living in an urban area with living in poverty, and to assume that people living in these conditions were not white, and that all such people could be lumped together under the heading of “disadvantaged.” They imagined that learning to code would provide a straightforward path out of poverty for these participants. But their thinking demonstrated little understanding of the obstacles imposed by centuries of enslavement, unpaid labor, Jim Crow violence, pay discrimination, and segregated and unequal education, health care, and housing. Largely with their own interests in mind, they looked to these upskilling programs as a panacea for racial inequality and the social instability it fueled. A group from a Delaware ACM chapter, a conference report suggested, believed that “in these days of urban crisis, the data processing industry offers a unique opportunity to the disadvantaged to become involved in the mainstream of the American way of life.” If success is defined as getting a steadily increasing number of Black and Hispanic men and women good jobs in the computing profession—and, by extension, giving them opportunities to shape and inform the technologies that would remake the world—then these programs failed. As the scholar Arvid Nelsen observed, while some volunteers “may have been focused on the needs and desires of the communities themselves,” others were merely seeking a Band-Aid for “civil unrest.” Meanwhile, Nelsen notes, businesses benefited from “a source of inexpensive workers with much more limited power.” In short, training people to code didn’t mean they would secure better, higher-­paying, more stable jobs—it just meant that there was a larger pool of possible entry-level employees who would drive down labor costs for the growing computer industry. In fact, observers identified the shortcomings of these efforts even at the time. Walter DeLegall, a Black computing professional at Columbia University, declared in 1969 that the “magic of data processing training” was no magic bullet, and that quick-fix training programs mirrored the deficiencies of American public education for Black and Spanish-speaking students. He questioned the motivation behind them, suggesting that they were sometimes organized for “commercial reasons or simply to de-fuse and dissipate the burgeoning discontent of these communities” rather than to promote equity and justice. The Algebra Project There was a grassroots effort that did respond to these inadequacies, by coming at the computing revolution from an entirely different angle. During the late 1970s and early 1980s, the civil rights activist Robert P. Moses was living with his family in Cambridge, Massachusetts, where his daughter Maisha attended the public Martin Luther King School and he volunteered teaching algebra. He noticed that math groups were unofficially segregated by race and class, and that much less was expected of Black and brown students. Early on, he also identified computers—and knowledge work dependent on computers —as a rising source of economic, political, and social power. Attending college was increasingly important for attaining that kind of power, and Moses saw that one key to getting there was a foundation in high school mathematics, particularly algebra. He established the Algebra Project during the early 1980s, beginning in Cambridge public schools and supported by a MacArthur “genius grant” that he received in 1982. In a book that he later coauthored, Radical Equations: Civil Rights from Mississippi to the Algebra Project , Moses clearly articulated the connections between math, computing, economic justice, and political power, especially for Black Americans. “The most urgent social issue affecting poor people and people of color is economic access. In today’s world, economic access and full citizenship depend crucially on math and science literacy,” he wrote. “The computer has become a cultural force as well as an instrument of work [and] while the visible manifestation of the technological shift is the computer, the hidden culture of computers is math.” Arming Black students with the tools of math literacy was radical in the 1980s precisely because it challenged power dynamics. Moses had earned his bachelor’s degree at Hamilton College in New York and a master’s degree at Harvard University before teaching math at the Horace Mann School in the Bronx from 1958 to 1961. For him, arming Black students with the tools of math literacy was radical in the 1980s precisely because access to technology meant access to power. “Who’s going to gain access to the new technology?” he asked. “Who’s going to control it? What do we have to demand of the educational system to prepare for the new technological era?” Moses mobilized students and parents alike to ensure that algebra was offered to all students at the Martin Luther King School. He devised new approaches to teaching the subject, and drawing on his experience with grassroots civil rights organizing, enrolled students to teach their peers. College admission rates and test scores rose at the school, and the Algebra Project spread to at least 22 other sites across 13 states. It focused on math because Moses identified math as the foundation of coding, and the stakes were always connected to economic justice and educational equity in an economy built on algorithms and data. Moses made explicit “a number of issues that are often hidden in coding discourse,” the historian Janet Abbate has observed. “He questioned the implied meritocracy of ‘ability grouping’ … he attacked the stereotype that Black people aren’t interested in STEM … [and] he emphasized that social skills and community were an essential part of overcoming students’ alienation from technology.” Moses died in 2021, but the Algebra Project lives on, now in collaboration with a group called the “We the People” Math Literacy for All Alliance. The curriculum he pioneered continues to be taught, and the Algebra Project’s 2022 conference again called attention to the need for better public education across the United States, especially for Black, brown, and poor children, “to make full participation in American democracy possible.” Rewind, reboot: Coding makes a comeback In the past decade, a new crop of more targeted coding programs has emerged. In 2014, for example, the activist and entrepreneur Van Jones collaborated with the musician Prince to launch #YesWeCode, targeting what they called “low-opportunity communities.” In doing so, they called attention to ongoing educational and economic inequities across the United States. One of #YesWeCode’s early efforts was a youth-oriented hackathon at the Essence Music Festival in New Orleans in 2014 that encouraged kids to connect coding with issues that mattered to them. As #YesWeCode’s chief innovation officer, Amy Henderson, explained , “A lot of the people who develop apps today are affluent white men, and so they build apps that solve their communities’ problems,” such as Uber. “Meanwhile,” she continued, “one of our young people built an app that sends reminders of upcoming court dates. That’s an issue that impacts his community, so he did something about it.” #YesWeCode has since morphed into Dream.Tech, an arm of Dream.org, a nonprofit that advocates for new legislation and new economic policies to remedy global climate change, the racialized mass incarceration system in the United States, and America’s long history of poverty. (Its other arms are called Dream.Green and Dream.Justice.) Recently, for example , Dream.org pushed for legislation that would erase long-standing racial disparities in sentencing for drug crimes. As a whole, Dream.org demonstrates an expansive vision of tech justice that can “make the future work for everyone.” Another initiative, called Code2040 (the name refers to the decade during which people of color are expected to become a demographic majority in the United States), was launched in 2012. It initially focused on diversifying tech by helping Black and Latino computer science majors get jobs at tech companies. But its mission has expanded over the past decade. Code2040 now aims for members of these communities to contribute to the “innovation economy” in all roles at all levels, proportional to their demographic representation in the United States. The ultimate vision: “equitable distribution of power in an economy shaped by the digital revolution.” Technological solutionism may persist, but there’s an increasing recognition that coding training alone is not enough. Both Code2040’s current CEO, Mimi Fox Melton, and her predecessor, Karla Monterroso, have argued that coding training alone is not enough to guarantee employment or equalize educational opportunities. In an openly critical letter to the tech industry published after the murder of George Floyd in 2020, they noted that 20% of computer science graduates and 24% of coding boot camp grads are Black or Latino, compared with only 6% of tech industry workers. Fox Melton and Monterroso observed: “High-wage work in America is not colorblind; it’s not a meritocracy; it’s white. And that goes doubly for tech.” These recent coding education efforts ask important questions: Code for what? Code for whom? Meanwhile, several other recent initiatives are focused on the injustices both caused and reflected by more recent aspects of the digital economy, particularly artificial intelligence. They aim to challenge the power of technological systems, rather than funneling more people into the broken systems that already exist. Two of these organizations are the Algorithmic Justice League (AJL) and the Ida B. Wells Just Data Lab. Joy Buolamwini, a computer scientist, founded the Algorithmic Justice League after discovering as a grad student at MIT that a facial-analysis system she was using in her work didn’t “see” her dark-skinned face. (She had to don a white mask for the software to recognize her features.) Now, the AJL’s mission is “leading a cultural movement towards equitable and accountable AI,” and its tagline reads: “Technology should serve all of us. Not just the privileged few.” The AJL publishes research about the harms caused by AI, as well as tracking relevant legislation, journalistic coverage, and personal stories, all with the goal of moving toward more equitable and accountable AI. Buolamwini has testified to Congress and in state hearings on these issues. Related Story Telecom companies have long resisted letting scientific sensors piggyback on their subsea cables—until now. The Ida B. Wells Just Data Lab , founded and directed by Ruha Benjamin, a Princeton professor of African American studies, is devoted to rethinking and retooling “the relationship between stories and statistics, power and technology, data and justice.” Its website prominently features a quote from the journalist and activist Ida B. Wells, who systematically collected data and reported on white mob violence against Black men during the 1890s. Her message: “The way to right wrongs is to turn the light of truth upon them.” One of the lab’s efforts, the Pandemic Portal, used data to highlight racial inequality in the context of covid-19, focusing on 10 different areas: arts, mutual aid, mental health, testing and treatments, education, prisons, policing, work, housing, and health care. It provided data-based resources and tools and offered evidence that these seemingly disparate categories are, in fact, deeply interwoven. Technological solutionism may persist in Silicon Valley campuses and state house corridors, but individuals, organizations, and communities are increasingly recognizing that coding instruction alone won’t save them. (Even Seymour Papert expressed skepticism of such efforts back in 1980, writing in Mindstorms that “a particular subculture, one dominated by computer engineers, is influencing the world of education to favor those school students who are most like that subculture.”) Learning to code won’t solve inequality or poverty or remedy the unjust structures and systems that shape contemporary American life. A broader vision for computer science can be found in the model proposed by Learning for Justice , a project of the Southern Poverty Law Center that works to provide educational resources and engage local communities, with the ultimate goals of addressing injustice and teaching students and the communities they come from to wield power together. The project’s d igital literacy framework highlights important focus areas far beyond a narrow emphasis on learning to code, including privacy concerns, uncivil online behavior, fake news, internet scams, ideological echo chambers, the rise of the alt-right, and online radicalization. These new frameworks of digital literacy, tech diversity, and algorithmic justice go beyond coding to prepare individuals to meaningfully question, evaluate, and engage with today’s array of digital spaces and places. And they prepare all of us to imagine and articulate how those spaces and places can better serve us and our communities. Joy Lisi Rankin is a research associate professor in the Department of Technology, Culture, and Society at New York University and author of A People’s History of Computing in the United States. hide by Joy Lisi Rankin 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 May/June 2023 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 Computing What’s next for the world’s fastest supercomputers Scientists have begun running experiments on Frontier, the world’s first official exascale machine, while facilities worldwide build other machines to join the ranks. By Sophia Chen archive page AI-powered 6G networks will reshape digital interactions The convergence of AI and communication technologies will create 6G networks that make hyperconnectivity and immersive experiences an everyday reality for consumers. By MIT Technology Review Insights archive page The power of green computing Sustainable computing practices have the power to both infuse operational efficiencies and greatly reduce energy consumption, says Jen Huffstetler, chief product sustainability officer at Intel. By MIT Technology Review Insights archive page How this Turing Award–winning researcher became a legendary academic advisor Theoretical computer scientist Manuel Blum has guided generations of graduate students into fruitful careers in the field. By Sheon Han 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 "

"How to teach kids who flip between book and screen | MIT Technology Review"

"https://www.technologyreview.com/2023/04/19/1071282/digital-world-reshaping-childrens-education-reading"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts How to teach kids who flip between book and screen Technology is changing how we read—and that means we need to rethink how we teach. By Holly Korbey archive page MITTR | Getty Linus Merryman spends about an hour a day on his laptop at his elementary school in Nashville, Tennessee, mostly working on foundational reading skills like phonics and spelling. He opens the reading app Lexia with ease, clicking straight through to lessons chosen specifically to address his reading needs. This week Linus, who’s in second grade, is working on “chunking,” finding the places where words are broken into syllables. The word chimpanzee appears on the screen in large letters, and Linus uses his mouse pad to grab cartoon Roman columns and slip them into the spaces between letters, like little dividers, where he thinks the syllable breaks should be. The app reads his guesses back to him—“chim-pan-zee.” He gets it right. After practicing these foundational skills on the computer, he and his classmates close their laptops and head to the rug, each with a print copy of their class reader, I Have a Dream , a picture book featuring the text of Martin Luther King Jr.’s speech. Students follow along in their books as the teacher reads aloud, occasionally stopping so they can ask questions and point out things they notice, like how the speech is written in the first person. Linus’s mom, Erin Merryman, an early reading interventionist at another Nashville school, initially worried about how well her son would learn to read in a classroom that made so much use of computers. He has been diagnosed with the learning disability dyslexia, and Merryman knows from her training that dyslexic students often need sensory input to learn how sounds are connected to letters. Close oversight from a teacher helps them as well. But since his reading has vastly improved this year, she’s adjusted her view. “I think a lot of what the app is doing is very good, very thorough,” Merryman says. “I’m surprised by how effective it is.” Like Merryman, a growing group of experts and educators are trying to figure out what the relationship should be between digital technology and reading instruction. Both reading and digital tech are world-expanding human inventions, and laptops and smartphones have arguably given humans unending opportunities to read more; you can access pretty much anything in print within a few seconds. In terms of “raw words,” the cognitive scientist Daniel T. Willingham has said , kids read more now than they did a decade ago. But many reading experts suspect that the technology may also be changing how they read—that reading on a screen is fundamentally different from reading on the page. Researchers who study young readers’ brains and behaviors are eager to understand exactly where tech serves kids’ progress in reading and where it may stand in the way. The questions are still so new that the answers are often unclear. Since the covid-19 pandemic closed schools in 2020, nearly all students have been organizing their learning around a school-issued laptop or tablet. But educators who are more dependent than ever on digital tech to aid learning in general often have little or no guidance on how to balance screens and paper books for beginning readers accustomed to toggling between the two. In a lot of ways, each teacher is winging it. Figuring out how best to serve these young “biliterate brains” is crucial, cognitive scientists say—not just to the future of reading instruction, but to the future of thought itself. Digital technology has transformed how we get knowledge in ways that will advance and forever alter our species. But at the individual level, the same technology threatens to disrupt, even diminish, the kind of slow, careful learning acquired from reading books and other forms of print. Those seemingly contradictory truths underline the question of how we should go about teaching children to read in the 21st century, says neuroscientist Maryanne Wolf, author of Reader, Come Home: The Reading Brain in a Digital World. Wolf, the first to use the term “biliterate brain,” is busy researching the relative merits of screen- and page-based approaches, adopting in the meantime a stance of what she calls “learned ignorance”: deeply investigating both positions and then stepping outside them to evaluate all the evidence and shake out the findings. Researchers who study young readers’ brains and behaviors are eager to understand exactly where tech serves kids’ progress in reading and where it may stand in the way. “Knowledge has not progressed to the point where we have the kind of evidence I feel we need,” Wolf says. “What do the affordances of each medium—screens vs. print—do to the reading brain’s use of its full circuitry? The answers are not all in.” But, she continues, “our understanding is that print advantages slower, deeper processes in the reading brain. You can use a screen to complement, to teach certain skills, but you don’t want a child to learn to read through a screen.” Which is best for comprehension, screens or books? Once children have learned to decode words, research on how they comprehend texts encountered on screens and paper gets a little more decisive. Experts say that young readers need to be reading alongside adults—getting feedback, asking questions, and looking at pictures together. All this helps them build the vocabulary and knowledge to understand what they’re reading. Screens often do a poor job of replicating this human-to-human interaction, and scientists like Wolf say that the “reading circuits” in children’s brains develop differently when the young learners are glued to a screen. Studies on the inner workings of the brain confirm the idea that human interaction helps develop beginning readers’ capacity for understanding. But they suggest that reading paper books is associated with that progress, too. In one study , researchers found that three- and four-year-old children had more activation in language regions of the brain when they read a book with an adult like a parent than when they listened to an audiobook or read from a digital app. When they read on an iPad, activation was lowest of all. In another study, MRI scans of eight- to 12-year-olds showed stronger reading circuits in those who spent more time reading paper books than those who spent their time on screens. Related Story Reclamo started out helping migrant workers get their money—but it may help change the legal aid landscape entirely. For older students, significant research shows that comprehension suffers when they read from a screen. A large 2019 meta-analysis of 33 different studies showed that students understood more informational text when they read on paper. A study by the Reboot Foundation, evaluating thousands of students across 90 countries including the US, found that fourth graders who used tablets in nearly all their classes scored 14 points lower on a reading test than students who never used them. Researchers called the score gap “equivalent to a full grade level” of learning. Students who used technology “every day for several hours during the school day” underperformed the most, while the gap shrank or even disappeared when students spent less than half an hour a day on a laptop or tablet. Why do students understand more of what they read when it’s in a book? Researchers aren’t entirely sure. Part of the issue is that "online reading complicates the comprehension process a millionfold," said Julie Coiro, a researcher at the University of Rhode Island, in a 2018 interview. Coiro described the process of a child reading on a website that often contains images, links and videos within the body of the text and make the process of comprehension harder: "It used to be that there was a pre-reading, the reading itself, and the evaluation at the end of your chapter or at the end of a book,” Coiro said. “Now [on the Internet] that process happens repeatedly in about 4 seconds: I choose a link. I decide whether I want to be here/I don’t want to be here, and then, where should I go next?” Coiro's more recent research shows that explicit teaching on how to handle the more complicated reading landscape—like when to click on links, and when to ignore them—helps improve comprehension. But even in other reading experiments where students weren’t allowed to browse the web or click on embedded links, they still performed worse. Virginia Clinton-Lisell, the author of the 2019 meta-analysis, hypothesized that overconfidence could be another aspect of the problem. In many of the studies, students who read from a laptop seemed to overestimate their comprehension skills compared with those reading the paper books, perhaps causing them to put in less effort while reading. Students self-report learning more and having a better reading experience when they read paper books. Linguist Naomi Baron, author of How We Read Now: Strategic Choices for Print, Screen, and Audio , says that when she interviews students about their perceptions, they often say reading from a book is “real reading.” They like the feel of the book in their hands, and they find it easier to go back to things they’ve already read than when they are reading from a screen. While they might prefer digital formats for reasons of convenience or cost, they sense they have greater concentration while reading print. But Baron says school districts and educators often aren’t aware of the strong research connecting books to better comprehension or confirming student preferences for print. Baron’s research dealt with college students, but last year a study by the Organization for Economic Cooperation and Development (OECD) of 15-year-olds in 30 countries showed that students who preferred reading on paper scored 49 points higher, on average, on the Program for International Student Assessment (PISA)—and the study hinted at an association between reading paper books and liking to read. Baron also thinks there should be more practical attention paid to developing pedagogical approaches that explicitly teach the slower, more focused habits of print reading, and then help students transfer those skills to the screen. Reinforcing those habits would be helpful even for people who usually read books, because someone reading a book can get distracted too—especially if a phone is nearby. The use of d igital books and textbooks exploded during the pandemic, and it may be only a matter of time before all educational publishing moves online. So it’s all the more important to keep making digital reading better for students, says literacy educator Tim Shanahan. Instead of trying to make the digital technology more like a book, Shanahan has written, “[engineers] need to think about how to produce better digital tools. Tech environments can alter reading behavior, so technological scaffolding could be used to slow us down or to move around a text more productively.” In the future, students might read about history or science from something like a “ tap essay ,” where words, sentences, and images are revealed only when a reader is ready and taps the screen to move on to the next piece of text. Or maybe their reading material will look more like a New York Times digital article, in which text, images, video, and sound clips are spaced out and blended together in different ways. Hooked on computer phonics About two-thirds of American schoolchildren can’t read at grade level. At least partly to blame is a widespread method of reading instruction that dominated classrooms for 40 years but was not based on scientific evidence about how the brain learns to read: “balanced literacy,” and its close cousin “whole language,” deemphasized explicit instruction in reading’s foundational skills, leaving many children struggling. But over the last several years, a new method strongly focused on these foundational skills, often referred to as the “ science of reading,” has brought sweeping changes to the US education system. Based on decades of scientific evidence, the “science of reading” approach is organized into five areas: phonemic awareness (learning all the sounds of the English language), phonics (learning how those sounds are attached to letters), vocabulary, comprehension, and fluency. Learn-to-read apps and digital platforms have the potential to teach some of these foundational skills efficiently. They’re especially well suited to phonemic awareness and phonics, making learning letters and sound combinations a game and reinforcing the skills with practice. Lexia, arguably the most widespread digital platform devoted to the science of reading, teaches basic and complex foundational reading skills, like letter-sound blends and spelling rules, using responsive technology. When learning a specific skill, such as figuring out how to read words like meal and seam with the “ea” vowel combination in the middle, students can’t move on until they’ve mastered it. Digital platforms can reinforce certain specific reading skills, but it’s the teacher who is constantly monitoring the student’s progress and adjusting the instruction as needed. A new wave of predictive reading platforms goes one step further. Companies like Microsoft and SoapBoxLabs are envisioning a world where students can learn to read entirely via computer. Using AI speech recognition technology, the companies claim, these digital platforms can listen closely to a student reading. Then they can identify trouble spots and offer help accordingly. As digital tech for learning to read spreads into schools—Lexia alone serves more than 3,000 school districts—some reading experts are wary. Research on its efficacy is limited. While some see technology playing a useful role in reading-related functions like assessing students and even training teachers, many say that when it comes to actually doing the teaching, humans are superior. Digital platforms can reinforce certain specific reading skills, explains Heidi Beverine-Curry, chief academic officer of the teacher training and research organization The Reading League, but it’s the teacher who is constantly monitoring the student’s progress and adjusting the instruction as needed. Faith Borkowsky, founder of High Five Literacy, a tutoring and consultancy service in Plainview, New York, is not bothered by reading instruction apps per se. “If it happens to be a computer program where a few kids could go on and practice a certain skill, I’d be all for it, if it aligns with what we are doing,” she says. But often that’s not how it plays out in classrooms. In the Long Island schools Borkowsky works with, it’s more likely that students do more reading work on laptops because schools purchased expensive technology and feel pressured to use it—even if it’s not always the best way to teach reading skills. “What I’ve seen in schools is they have a program, and they say, ‘Well, we bought it—now we have to use it.’ Districts find it hard to turn back after purchasing expensive programs and materials,” she says. Some platforms are working to bridge the gap between online and in-person instruction. Ignite! Reading, an intensive tutoring program launched after the pandemic closed schools, teaches foundational reading skills like phonemic awareness and phonics through a videoconferencing platform, where reading tutors and students can see and hear one another. Ignite’s instruction attempts to blend the benefits of digital tech and human interaction. In one tutoring session, a first grader named Brittany in Indianapolis, Indiana, sounded out simple words, prompted by her reading tutor, whom she could see through her laptop’s camera. Brittany read “map” and “cup,” tapping the whiteboard in her hand each time she made a sound: three sounds in a word, three taps. At the same time, a digital whiteboard on her laptop screen also tapped out the sounds: one, two, three. As Brittany sounded out each word, the tutor watched the child’s mouth through the computer’s camera, giving adjustments along the way. Related Story The narrative around cheating students doesn’t tell the whole story. Meet the teachers who think generative AI could actually make learning better. Ignite cofounder and CEO Jessica Sliwerski says she’s building an army of remote reading tutors to assist teachers in helping kids catch up after the pandemic years. Students get 15-­minute sessions during the school day, and when sessions are over, tutors get coaching on how to make the short bursts more effective. Sliwerski believes technology can be incredibly useful for giving more students one-on-one attention. “We are taking a different approach to the technology,” she says. “We are centering the child on a human who is highly trained and accountable. That’s the core of it, and there’s not really anything tech about that.” Preserving deep reading Once students can decode words and comprehend their meaning, the real work of reading begins. This is what Wolf calls “deep reading,” a specific set of cognitive and affective processes in which readers are able to take in whole chunks of text at a time, make predictions about what comes next, and develop lightning-fast perception. These interactive processes feed each other in the brain, accelerating understanding. But since the vast majority of the reading that today’s young people do—let’s face it, the majority that we all do—is skimming an online article, a Facebook post, or a text from a friend while hopping from one tab to another, deep reading as a cognitive process is at risk. If today’s kids read only from screens, Wolf says, they may never learn deep reading in the first place—that elaboration of the brain’s reading circuit may never be built. Screen reading may “disrupt and diminish the very powers that it is supposed to advance.” “We are amassing data that indicates there are changes in the reading brain that diminish its ability to use its most important, sophisticated processes over time when the screen dominates,” Wolf says. Deep reading is something that came naturally to many readers before digital tech and personal computers, when they had lots of time to spend doing nothing but reading a book; but it can’t be assumed that today’s young readers, with their biliterate brains, will automatically learn the process. Some educators are paying more attention to how to help students begin to learn deep reading. Doug Lemov, a charter school founder who now trains teachers full time with his “Teach Like a Champion” books and courses, is acutely concerned that many middle and high school students no longer appear to have the attention span to concentrate on a text for long periods of time. So he encourages the teachers he trains to adopt “low-tech, high-text environments” inside their classrooms, with paper books, pencils, and paper. In such a setting, students slowly build up their attention spans by doing nothing but reading a book or scratching out a piece of writing, even if that means beginning with just a few minutes at a time. “Build on that until they can go for 20 minutes, either in a group or individually—just reading the text, sustaining their attention and maintaining focus,” Lemov says. “Writing does the same thing: it improves the focus and attention that students will need to do deep reading.” It’s possible, of course, that kids’ attention spans haven’t actually changed that much with the advent of digital technology. Instead, argues Willingham, the cognitive scientist, in his book The Reading Mind: A Cognitive Approach to How the Mind Reads , it’s their expectations for entertainment that have changed. “The consequence of long-term experience with digital technologies is not an inability to sustain attention. It’s impatience with boredom,” he writes. “It’s an expectation that I should always have something interesting to listen to, watch, or read, and that creating an interesting experience should require little effort.” Deep reading, on the other hand, requires “cognitive patience”—an entirely different set of skills in which kids often have to put in great effort for a payoff that is sometimes many pages down the road. Yet in Wolf’s view, getting rid of all reading tech would be as ill-advised as relying on it exclusively. Instead, she’s hoping to spur a conversation about balance, gathering evidence about which ways of using digital technology work best for diverse learners and for different age groups—information that could help districts and teachers guide the decisions they make about teaching reading. A five- to 10-year-old child who is learning to read has different needs from a 12-year-old, or from a high schooler whose smartphone is loaded with five social media apps. Young children just beginning to build their reading circuit benefit most from books and human interaction. Older kids can cultivate the “digital wisdom” to make smarter choices while working on developing the ability to toggle effortlessly between print and digital worlds. Some kids, though, may be tired of all that toggling. Matt Ryan, a high school English teacher in Attleboro, Massachusetts, doesn’t allow any e-books in his class—when he assigns a novel, it’s paper only. Not only does he not get any pushback, he says, but he senses students are somewhat relieved. “Distractions are a very real issue, so reading on a device will not be effective for most of them,” Ryan says. “My sense is that so much of what they do is on a device—they welcome something off of it.” Holly Korbey is an education and parenting journalist and author of Building Better Citizens: A New Civics Education for All. hide by Holly Korbey 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 May/June 2023 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 Humans and technology Why embracing complexity is the real challenge in software today In the midst of industry discussions about productivity and automation, it’s all too easy to overlook the importance of properly reckoning with complexity. By Ken Mugrage archive page Turning medical data into actionable knowledge Technology can transform patient care by bringing together data from a variety of sources By Siemens Healthineers archive page Moving data through the supply chain with unprecedented speed Tackle supply chain visibility and customer engagement with standards and “phygital” technology. By MIT Technology Review Insights archive page Customer experience horizons The big ideas that define the future of customer and employee experience. By MIT Technology Review Insights 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 "

"Teachers in Denmark are using apps to audit their student’s moods | MIT Technology Review"

"https://www.technologyreview.com/2023/04/17/1071137/denmark-teachers-apps-student-mood-audit-software"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Teachers in Denmark are using apps to audit their students’ moods Companies say the software can help improve well-being, but some experts worry it could have the opposite effect. By Arian Khameneh archive page Nicole Rifkin In a Copenhagen suburb, a fifth-grade classroom is having its weekly cake-eating session, a common tradition in Danish public schools. While the children are eating chocolate cake, the teacher pulls up an infographic on a whiteboard: a bar chart generated by a digital platform that collects data on how they’ve been feeling. Organized to display the classroom’s weekly “mood landscape,” the data shows that the class averaged a mood of 4.4 out of 5, and the children rated their family life highly. “That’s great!” the teacher exclaims, raising two thumbs up in the air. She then moves to an infographic on sleep hygiene. Here the data shows the students struggling, and the teacher invites them to think of ways to improve their sleeping habits. After briefly talking among themselves, the children suggest “less screen time at night,” “meditation before sleep,” and “having a hot bath.” They collectively make a commitment to implement these strategies. At next week’s cake time, they will be asked whether or not they followed through. These sorts of data-driven well-­being audits are becoming more and more common in Denmark’s classrooms. The country has long been a leader in online services and infrastructure, ranking as the most digitally developed nation in the UN’s e-government survey. In recent years its schools, too, have received big investments in this type of technology: it is estimated that the Danish government allocated $4 to $8 million, a fourth of the high school budget for teaching aids, to procuring digital platforms in 2018. In 2021, it invested some $7 million more. These investments are rooted in a Nordic tradition of education that centers the child’s experience and encourages interactive learning; some Scandinavian education researchers think technology can help draw children in as playful, active participants. “Technology is an extended pencil and drawing pad. It’s a tool that is bound to the child’s opportunity to express themselves,” Mari-Ann Letnes, an education scientist in Norway, said in a 2018 interview. In a 2019 status report on the use of technology in schools, the Danish Ministry of Education stated that “creativity and self-expression with digital technologies are a part of building students’ motivation and versatile development.” Now, some teachers and administrators are hoping technology can be used to tackle mental health as well. Danish schoolchildren are in the midst of a mental-health crisis that one of the country’s biggest political parties has called a challenge “equal to inflation, the environmental crisis, and national security.” No one knows why, but in just a few decades , the number of Danish children and youth with depression has more than sextupled. One-quarter of ninth graders report that they have attempted self-harm. (The problem isn’t exclusive to Denmark: depressive episodes among US teens increased by some 60% between 2007 and 2017, and teen suicide rates have also leaped by around 60% over the same period.) A recent open letter signed by more than 1,000 Danish school psychologists expressed “serious concerns” over the mental state of the children they see in their work and warned that if action isn’t taken immediately, they “see no hope for turning the negative trend around.” To help address the problem, some Danish schools are moving to address children’s well-being through platforms like Woof, the one used in the fifth-grade classroom. Built by a Denmark-based startup, it frequently surveys schoolchildren on a variety of well-being indicators and uses an algorithm to suggest particular issues for the class to focus on. Related Story Going to sleep in virtual reality can alleviate insomnia and loneliness—if you can avoid being harassed by kids. These platforms are quickly gaining ground. Woof, for example, has been implemented in classrooms in more than 600 schools across Denmark, with more on the way. Its founders believe Woof fills an important niche: they say teachers have expressed widespread dissatisfaction with existing tools, in particular a government-run well-being survey. That survey audits schools once a year and delivers results on a delay; it might provide a snapshot for policymakers but is hardly useful for teachers, who need regular feedback to adjust their work. “There is simply a need for tools to check in [with the children] where you don’t need to be active,” says Mathias Probst, a cofounder of Woof. “Where you don’t need to talk to all 24 children before starting a class, because before you know it, 15 minutes of class time has already passed.” And teachers could benefit, he suggests, from “something that can bring a data structure into all of this.” Woof is not alone in its attempt to quantify children’s moods. A handful of other platforms have been adopted by Danish schools, and schools in Finland and the UK are using mood-monitoring software as well. In the US, the tech can extend beyond collecting self-reports to hunting for hints of concerning behavior by surveilling students’ emails, chat messages, and searches on school-issued devices. A number of people say mood-­monitoring tech has great potential. “We can use digital tools to evaluate well-­being on a 24-hour basis. How is the sleep? How is the physical activity, how is the interaction with others? ... How does [the child’s] screen time compare to physical time? That’s central to understanding what well-being actually is,” the late Carsten Obel, who was a professor of public health at Aarhus University and a leader in the development of another student-surveying tool called Moods, said in a 2019 video. But some experts are heavily skeptical of the approach. They say there is little evidence that quantification of this sort can be used to solve social problems, and that fostering a habit of self-surveillance from an early age could fundamentally alter children’s relationship to themselves and each other in a way that makes them feel worse rather than better. “We can hardly go to a restaurant or to the theater without being asked how we feel about it afterwards and ticking boxes here and there,” says Karen Vallgårda, an associate professor at the University of Copenhagen who studies family and childhood history. “There is a quantification of emotions and experiences that is growing, and it’s important that we ask ourselves whether that’s the ideal approach when it comes to children’s well-being.” Others are asking how much children and their parents actually know about what data is being collected—and how it is being used. While some platforms say they are collecting minimal or no personally identifiable data, others mine deep into individual children’s mental states, physical activity, and even friend groups. “Their practice is very Silicon Valley–like. They preach data transparency but have none themselves,” says Jesper Balslev, a research consultant at the Copenhagen School of Design and Technology, of some of these platforms. Balslev says he is concerned that Woof and other platforms are being swiftly and naively rolled out without adequate regulation, testing, or efforts to make sure that the school culture allows children to abstain from participating in them. “Our regulatory technologies to deal with this are terrible,” he says. It’s possible that will change, he adds, “but right now, all the hobs are turned on at the same time.” Woof is run from a basement office on the outskirts of Copenhagen, with a small team of three full-time staffers. The founders, Mathias Probst and Amalie Danckert, got the idea for the company after working as public school teachers through Teach First Denmark, an organization similar to Teach for America in the United States. When Probst and Danckert entered the public school system, they say, they quickly realized that schools in low-income neighborhoods face a vicious cycle. Difficult circumstances at home can make students in these schools more challenging to teach. Staff turnover rates are high because of stress and burnout, with some teachers keen to switch to “easier” schools. Parents with resources often take their children elsewhere, so kids with more problems make up an even greater proportion of those who remain, exacerbating the stress teachers face and the likelihood that they’ll leave. All this compounds the well-being crisis that children are experiencing elsewhere. “I saw so many children ending up in difficult situations, which could have been prevented if action had been taken earlier,” says Danckert, who before her stint as a teacher worked as an analyst in the children and youth section of Copenhagen’s Social Services Administration. Danckert and Probst, who has a background in consulting, set out to build a way to help schools manage such situations before they spiral into serious mental-health problems—problems that schools’ thinly stretched counseling systems may not catch until it’s too late. Woof, the solution they devised, is a web app that children can access on computers or phones (a 2019 study found that 98% of Danish children between 10 and 15 have access to a smartphone). Its user interface primarily features a cartoon dog, which asks the children various questions about their life. The tool is designed to be used on a weekly basis, generating a “mood landscape” for the class by prompting kids to rate their mood and other aspects of their lives on a 1–5 scale. The result is supposed to add up to a comprehensive image of child welfare in that classroom over time. Teachers and administrative staff can read weekly reports on a class’s overall self-reported mood and how factors like their sleep hygiene, social activity, academic performance, and physical activity affect that mood. Classrooms are profiled, and interventions are recommended to improve the scores in categories where they are doing less well. Finally, the teacher and the children look at the data together and help each other with tools and strategies to improve these sticking points. “It’s worrying that there is so much personally attributable data on platforms working with children.” Woof’s data is anonymized; the app reports on classroom averages instead of individual children. Danckert says that’s because the company was unwilling to walk right up to the edge of what was legally and ethically feasible under data privacy laws. Probst also describes feeling uneasy that collecting data on individual children might create a narrative and lock them into it, rather than helping them break negative patterns. “It’s worrying that there is so much personally attributable data on platforms working with children,” he says. The startup fully launched Woof less than a year ago, in the fall of 2022. According to beta test data collected on 30 schools before its full launch, 80% of classes that use Woof see mood improve by, on average, 0.35 points on the 1–5 scale within one month. Woof maintains that the platform isn’t meant to replace teacher-student contact. It should rather be understood as a support tool for teachers that provides structured action plans and feedback. But some experts have doubts about whether Woof’s methods are effective. They are particularly skeptical about the self-reported nature of the platform’s data. According to Balslev, education apps have not proved that they perform any better than analog interventions, such as having teachers advise children to turn off their computers and ask them how they slept last night. He points to historical lessons, such as a 2015 OECD study finding that digitalization in schools in a variety of countries had exacerbated a range of problems it was supposed to improve, with a net negative effect on learning outcomes. “We intuitively trust data or the quantitative regime more than we trust humans,” he says. “I have found no, or very few, studies that examine the use of ed tech in controlled environments.” And there is good reason to take self-reported well-being data with caution: children may not be providing honest information. Balslev claims that when technology is introduced into a social context, it can’t be assumed that students will demonstrate ideal behavior and cooperate with its intentions. For example, in interviews he has done with high school students, he says they have reported gaming digital systems to do things like get more time for an assignment or make a writing exercise look longer than it actually is. Though dishonest answers are of course possible, Probst and Danckert argue that Woof’s anonymous approach makes authentic responses more likely than they might be otherwise. “Many students from low-­income areas are very aware of whether they are anonymous or not. And they are very aware of what is disclosed about their family life,” says Danckert. “The students don’t want to talk about what is happening at home, because they are worried that it will start a case [with a social services agency],” Probst adds. He and Danckert believe that the anonymous approach builds trust and promotes honest disclosure, as students can be sure that it won’t trigger the teacher’s legal obligation to report red flags further up in the system. Woof isn’t the only well-being platform making inroads in Danish schools. Platforms like Bloomsights , Moods , and Klassetrivsel (Danish for “classroom well-being”) are also getting traction. Each takes a more data-­intensive and less anonymous approach than Woof, tracking and identifying schoolchildren individually. Bloomsights and Klassetrivsel even go as far as generating “sociograms”—network diagrams that display the children’s relationships with each other in detail. Bloomsights turns self-reported data from the same individuals over time into indicators including “signs of loneliness,” “academic mindset,” and “signs of bullying.” Bloomsights is also used in the US, where some school districts are including it as part of an “early warning system” for identifying potential school shooters. The company’s US operations are based in Colorado. Cofounder Adam Rockenbach says the hope in bringing Bloomsights to the US was to spread the Scandinavian values of well-being and community. He asserts that the app is not meant to be a dystopian “Big Brother” but an extension of what teachers already do. “You notice the student is coming into class, and maybe they’re coming to class late more frequently than before, and they look a little disheveled,” he says. “A good teacher is going to go find two or three minutes to connect with that student: ‘Hey, it seems like there’s something off here. Is there any way I can help you?’” Citing his experiences as a teacher in inner-city schools in Los Angeles for six years, Rockenbach says it can be a challenge to know what is really going on with children who struggle in an environment that might be marked by gang violence and poverty. He says Bloomsights can help in situations where the signals are not so clear. Related Story Chinese apps are dominating US app stores right now, but they could get caught in still-expanding efforts to ban TikTok. Rockenbach believes that anonymous data only makes early intervention more difficult, since it creates more work for teachers and educators in trying to identify who has problems and needs help. For this reason, he thinks collecting individual data is a necessity. The program, which operates through a web app, takes self-reporting measurements similar to Woof’s: monthly surveys of students, measuring various indicators of mental and physical well-being and students’ evaluation of their learning environment. But Bloomsights stands out in its use of sociograms, which are constructed from the students’ reports of who their friends are and who they connect and spend time with. Rockenbach says these sociograms are crucial tools to detect social isolation and might even help identify children who are vulnerable to bullying. He points to testimonial reports from schools as an indicator that the platform helps improve well-being. But, he adds, “we haven’t conducted a full-on research project that might compare, for example, a school that uses Bloomsights versus a school that doesn’t. That’s something that we’re looking to do.” Indeed, some teachers wonder how useful—or even ethical—the app is. “It’s some very intimate things that are asked, and they [the children] don’t necessarily know who is going to see it,” says Naya Marie Nord, a teacher at a suburban Copenhagen school that uses Bloomsights. “Of course, I as a teacher should have insight into how my students are feeling. But that’s something that I prefer to have conveyed in the confidentiality between me and the student, rather than it being told to a computer.” Nord is concerned about how many teachers who don’t work directly with the children still have access to their data. She believes the app straddles ethical boundaries given how much it impinges on students’ private lives. “They have no chance of understanding what is going on. It’s not like we give them a long presentation explaining how it’s used and who has access [to the data],” Nord says. “And if we did, we would get no honest answers. If they actually understood the amount of data I can see about them and how many others can see it as well, I believe they would answer differently.” According to the data policies of Klassetrivsel, one of the platforms that collect non-anonymized data, consent is not required from either parents or children before the app is used in the classroom. The company claims that since the app is an integrated tool used for “well-being purposes” at a public institution, it falls under a Danish legal clause that exempts public authorities from requirements about obtaining consent for data collection. And since the platforms aren’t classified as “information society services” like Facebook or Google, there is no parental consent required under the General Data Protection Regulation, the European Union’s sweeping data privacy law. Legal precedents seem to back up Klassetrivsel’s claims about how the data law applies to its work. In 2019, a parent submitted a complaint to the Danish Data Protection Agency, claiming that a data-driven well-being platform at her child’s school was engaging in forced monitoring of the child. The parent further argued that “measuring and monitoring well-being is not the same as improving well-being.” The agency ruled in favor of the school’s municipality: the app was deemed a tool for maintaining tasks of “crucial social interest” that fall under the responsibility of schools. “Usually, the legal authority that these third-party apps operate under is that they are offering a service on behalf of the public authorities,” says Allan Frank, an IT lawyer at the agency. But they must still store data correctly and not collect more than is necessary. They must also operate under the aegis of governmental authorization, he says: “If there is a random teacher or a school that has been convinced to suddenly set it up without the supervision of the municipality or the Ministry of Education, then that would be a problem.” In Denmark, parents can opt out if they don’t want data collected on their children through these apps. According to Bloomsights, this is also the case in the US: although practices vary, Rockenbach says that parents typically sign a paper once a year that lists all the different services the school uses. But because the apps are used in an educational context and are framed as altruistic, both parents and policymakers tend to have their guard down. “There are a lot of other apps where I limit my son’s use, but I’m not concerned about apps used in the school the same way I am about TikTok and YouTube, for example,” says Janni Hindborg Christiansen, mother of one of the children in the fifth-grade classroom that uses Woof. “At least Woof is used in a controlled environment and has a good purpose. I trust it more than so many other apps that I’d be more critical toward.” And for parents who don’t want their children using such platforms, opting out is not always straightforward. Henriette Viskum, the teacher of the fifth-grade class, describes Woof lessons as a part of her class’s core programming, just like math, and says parents need to talk with the teacher to pull their child out of the program. “If it’s a huge problem, we’ll find a solution and then the child doesn’t have to participate,” Viskum says. “But then I would, as a teacher, put a big question mark around why the parents are so strongly opposed to working with well-being. I would be a bit concerned and curious about that.” The closeness between teachers and students can also make the degree of anonymity blurry. Viskum told me that if almost an entire class reports high scores on family life, for example, but one child does not, she can usually intuit who that person is and might casually try to take steps to help. For Balslev, the embrace of slick data-driven solutions is due partly to their political appeal. In Denmark, technology sometimes tends to be presented as the solution to everything connected to teaching and education. The simple infographics that ed-tech companies offer, he says, have an allure for government officials faced with thorny social and pedagogical issues. “What is fantastic about the digital [initiatives] is that they are good at making politicians look actionable—as if they have made some decisions,” Balslev says. But efficacy is not as much of a priority, he says: “It’s quick and easy to produce some metrics that appear rhetorically convincing. The infographic might provide a very thin sliver of truth about reality, but it doesn’t touch the core of the situation.” “The infographic might provide a very thin sliver of truth about reality, but it doesn’t touch the core of the situation.” In fact, the technology risks actually making the situation worse, says Karen Vallgårda, the University of Copenhagen researcher. She is concerned that the “surveillance paradigm” could have unintended consequences for children’s self-understanding. Related Story Going to sleep in virtual reality can alleviate insomnia and loneliness—if you can avoid being harassed by kids. “If we are asked to monitor ourselves according to a quantitative logic, emotions such as indignation and sorrow can appear as problematic emotional reactions, despite the fact that they are completely natural in certain scenarios of life. The children can feel that what they are feeling is wrong or undesirable, which is likely to propel greater well-­being issues rather than ameliorating them,” Vallgårda says. “When we instill a measure of self-­surveillance with children based on a clearly communicated ideal of how to structure one’s everyday life, one’s eating habits, and how to feel in certain contexts, there is a risk that children develop ‘double unhappiness’ due to not just being unhappy but also failing to live up to these ideals.” Vallgårda’s concerns are echoed by other researchers, who argue that an excessive focus on whether children are happy can cause them to pathologize normal fluctuations in life. New studies also indicate that declining well-being is largely attributed to environmental and social pressures rather than individual factors. Vallgårda believes that rather than pouring resources into tools that further a quantitative agenda, schools should instead be prioritizing efforts to hire and train professionals like teachers and school psychologists. But digital platforms are significantly cheaper than hiring or training more people. Viskum, the fifth-grade teacher, points out that budgets are tight and waiting lists for appointments with the school psychologist are miles long. Given the material reality, the appeal of ed tech is understandable, even when there are few results to back it up. While the quantification of children’s lives might make academics balk, the children I met told me that they enjoyed using Woof and especially liked how the app helped them talk more nicely to each other. At a school I visited in a low-income neighborhood (the class scored 3.4 on the mood scale), a teacher said she was just happy to have a tool that might give her a general idea of what was going on with the children. When I asked Woof’s Probst about Vallgårda’s criticisms, he said that unlike researchers studying children academically, those who work with children every day in the classroom can’t afford to think in abstract terms. “It’s all well and good to be a theorist and have the opinion that you shouldn’t be doing certain things, but there is also a reality out there in the classrooms,” he says. “There is a practical situation where teachers face children who are struggling so much that they break down in tears during class. You have to do something there.” Arian Khameneh is a freelance journalist based in Copenhagen. hide by Arian Khameneh 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 May/June 2023 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 Humans and technology Why embracing complexity is the real challenge in software today In the midst of industry discussions about productivity and automation, it’s all too easy to overlook the importance of properly reckoning with complexity. By Ken Mugrage archive page Turning medical data into actionable knowledge Technology can transform patient care by bringing together data from a variety of sources By Siemens Healthineers archive page Moving data through the supply chain with unprecedented speed Tackle supply chain visibility and customer engagement with standards and “phygital” technology. By MIT Technology Review Insights archive page Customer experience horizons The big ideas that define the future of customer and employee experience. By MIT Technology Review Insights 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 "

"Banning Chat GPT will do more harm than good | MIT Technology Review"

"https://www.technologyreview.com/2023/04/14/1071194/chatgpt-ai-high-school-education-first-person"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Banning ChatGPT will do more harm than good A high school senior argues that ChatGPT can help reshape education for the better. By Rohan Mehta archive page Stephanie Arnett/MITTR | Envato Related Story The narrative around cheating students doesn’t tell the whole story. Meet the teachers who think generative AI could actually make learning better. The release of ChatGPT has sent shock waves through the halls of higher education. Universities have rushed to release guidelines on how it can be used in the classroom. Professors have taken to social media to share a spectrum of AI policies. And students—whether or not they’ll admit it—have cautiously experimented with the idea of allowing it to play a part in their academic work. But the notion of a measured response to the emergence of this powerful chatbot seems to have barely penetrated the world of K–12 education. Instead of transparent, well-defined expectations, high schoolers across the country have been confronted with a silent coup of blocked AI websites. 1 That’s a shame. If educators actively engage with students about the technology’s capabilities and limitations—and work with them to define new academic standards—ChatGPT, and generative AI more broadly, could both democratize and revitalize K–12 education on an unprecedented scale. A bold claim, I know. But after a few months of putting generative AI to the test (a nerdy case of senioritis, if you will), I’m optimistic. Exhibit A? College applications. Few things are as mentally draining as applying to college these days, and as I slaved away at my supplemental essays, the promise of using ChatGPT as a real-time editor was attractive—partly as a potential productivity boost, but mostly as a distraction. I had ChatGPT carefully review my cloying use of semicolons, grade my writing on a 0–10 scale (the results were erratic and maddening) 2 , and even role-play as an admissions counselor. Its advice was fundamentally incompatible with the creative demands of the modern college essay, and I mostly ignored it. But the very act of discussing my writing “out loud,” albeit with a machine, helped me figure out what I wanted to say next. Using ChatGPT to verbalize the space of possibilities—from the scale of words to paragraphs—strengthened my own thinking. And I’ve experienced something similar across every domain I’ve applied it to, from generating fifth-grader-level explanations of the French pluperfect to deciphering the Latin names of human muscles. All this adds up to a simple but profound fact: anyone with an internet connection now has a personal tutor, without the costs associated with private tutoring. Sure, an easily hoodwinked, slightly delusional tutor, but a tutor nonetheless. The impact of this is hard to overstate, and it is as relevant in large public school classrooms where students struggle to receive individual attention as it is in underserved and impoverished communities without sufficient educational infrastructure. As the psychologist Benjamin Bloom demonstrated in the early 1980s, one-on-one instruction until mastery allowed almost all students to outperform the class average by two standard deviations (“about 90% … attained the level … reached by only the highest 20%”). ChatGPT certainly can’t replicate human interaction, but even its staunchest critics have to admit it’s a step in the right direction on this front. Maybe only 1% of students will use it in this way, and maybe it’s only half as effective as a human tutor, but even with these lowball numbers, its potential for democratizing educational access is enormous. I would even go so far as to say that if ChatGPT had existed during the pandemic, many fewer students would have fallen behind. Of course, those decrying ChatGPT as the end of critical thinking would likely protest that the bot will only exacerbate the lazy academic habits students might have formed over the course of the pandemic. I have enough experience with the tips and tricks we high schoolers employ on a regular basis to know that this is a valid concern—one that shouldn’t be brushed off by casting ChatGPT as just the latest in a long line of technological revolutions in the classroom, from the calculator to the internet. That said, ChatGPT has just as much potential in the classroom as it does for improving individual educational outcomes. English teachers could use it to rephrase the notoriously confusing answer keys to AP test questions, to help students prepare more effectively. They could provide each student with an essay antithetical to the one they turned in, and have them pick apart these contrary arguments in a future draft. No human teacher could spend the time or energy needed to explain pages upon pages of lengthy reading comprehension questions or compose hundreds of five-page essays, but a chatbot can. Educators can even lean into ChatGPT’s tendency to falsify, misattribute, and straight-out lie as a way of teaching students about disinformation. Imagine using ChatGPT to pen essays that conceal subtle logical fallacies or propose scientific explanations that are almost, but not quite, correct. Learning to discriminate between these convincing mistakes and the correct answer is the very pinnacle of critical thinking, and this new breed of academic assignment will prepare students for a world fraught with everything from politically correct censorship to deepfakes. There are certainly less optimistic visions for the future. But the only way we avoid them—the only way this technology gets normalized and regulated alongside its similarly disruptive forebears—is with more discussion, more guidance, and more understanding. And it’s not as if there’s no time to catch up. ChatGPT won’t be acing AP English classes anytime soon, and with the recent release of GPT-4 , we are already seeing an explosion of ed-tech companies that reduce the effort and expertise needed for teachers and students to operate the bot. So here’s my pitch to those in power. Regardless of the specific policy you choose to employ at your school, unblock and unban. The path forward starts by trusting students to experiment with the tool, and guiding them through how, when, and where it can be used. You don’t need to restructure your whole curriculum around it, but blocking it will only send it underground. That will lead to confusion and misinterpretation in the best of cases, and misuse and abuse in the worst. ChatGPT is the only beginning. There are simply too many generative AI tools to try to block them all, and doing so sends the wrong message. What we need is a direct discourse between students, teachers, and administrators. I’m lucky enough to be at a school that has taken the first steps in this direction, and it’s my hope that many more will follow suit. At least in my case, the entirety of openai.com has been blocked, not just chat.openai.com. Kind of annoying if I want to access the fine-­tuning docs. The most impressive thing I have seen ChatGPT do is revise one of my essays. In it, I discussed two global political figures, but concealed their identities through personification. To “make my essay a 10/10” and “increase clarity,” ChatGPT filled their names in. The fact that it has emergent abilities like this blew my mind! Rohan Mehta is a high school senior at Moravian Academy in Bethlehem, Pennsylvania. hide by Rohan Mehta 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 May/June 2023 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 Keep Reading Most Popular 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 Everything you need to know about artificial wombs Artificial wombs are nearing human trials. But the goal is to save the littlest preemies, not replace the uterus. By Cassandra Willyard 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 How to fix the internet If we want online discourse to improve, we need to move beyond the big platforms. By Katie Notopoulos 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 "

"How AI is helping historians better understand our past | MIT Technology Review"

"https://www.technologyreview.com/2023/04/11/1071104/ai-helping-historians-analyze-past"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts How AI is helping historians better understand our past The historians of tomorrow are using computer science to analyze how people lived centuries ago. By Moira Donovan archive page Beth Hoeckel It’s an evening in 1531, in the city of Venice. In a printer’s workshop, an apprentice labors over the layout of a page that’s destined for an astronomy textbook—a dense line of type and a woodblock illustration of a cherubic head observing shapes moving through the cosmos, representing a lunar eclipse. Like all aspects of book production in the 16th century, it’s a time-consuming process, but one that allows knowledge to spread with unprecedented speed. Five hundred years later, the production of information is a different beast entirely: terabytes of images, video, and text in torrents of digital data that circulate almost instantly and have to be analyzed nearly as quickly, allowing—and requiring—the training of machine-learning models to sort through the flow. This shift in the production of information has implications for the future of everything from art creation to drug development. But those advances are also making it possible to look differently at data from the past. Historians have started using machine learning—deep neural networks in particular—to examine historical documents, including astronomical tables like those produced in Venice and other early modern cities, smudged by centuries spent in mildewed archives or distorted by the slip of a printer’s hand. Historians say the application of modern computer science to the distant past helps draw connections across a broader swath of the historical record than would otherwise be possible, correcting distortions that come from analyzing history one document at a time. But it introduces distortions of its own, including the risk that machine learning will slip bias or outright falsifications into the historical record. All this adds up to a question for historians and others who, it’s often argued, understand the present by examining history: With machines set to play a greater role in the future, how much should we cede to them of the past? Parsing complexity Big data has come to the humanities throughinitiatives to digitize increasing numbers of historical documents, like the Library of Congress’s collection of millions of newspaper pages and the Finnish Archives’ court records dating back to the 19th century. For researchers, this is at once a problem and an opportunity: there is much more information, and often there has been no existing way to sift through it. Related Story AI automation throughout the drug development pipeline is opening up the possibility of faster, cheaper pharmaceuticals. That challenge has been met with the development of computational tools that help scholars parse complexity. In 2009, Johannes Preiser-Kapeller, a professor at the Austrian Academy of Sciences, was examining a registry of decisions from the 14th-century Byzantine Church. Realizing that making sense of hundreds of documents would require a systematic digital survey of bishops’ relationships, Preiser-Kapeller built a database of individuals and used network analysis software to reconstruct their connections. This reconstruction revealed hidden patterns of influence, leading Preiser-Kapeller to argue that the bishops who spoke the most in meetings weren’t the most influential; he’s since applied the technique to other networks, including the 14th-century Byzantian elite, uncovering ways in which its social fabric was sustained through the hidden contributions of women. “We were able to identify, to a certain extent, what was going on outside the official narrative,” he says. Preiser-Kapeller’s work is but one example of this trend in scholarship. But until recently, machine learning has often been unable to draw conclusions from ever larger collections of text—not least because certain aspects of historical documents (in Preiser-Kapeller’s case, poorly handwritten Greek) made them indecipherable to machines. Now advances in deep learning have begun to address these limitations, using networks that mimic the human brain to pick out patterns in large and complicated data sets. Nearly 800 years ago, the 13th-century astronomer Johannes de Sacrobosco published the Tractatus de sphaera, an introductory treatise on the geocentric cosmos. That treatise became required reading for early modern university students. It was the most widely distributed textbook on geocentric cosmology, enduring even after the Copernican revolution upended the geocentric view of the cosmos in the 16th century. The treatise is also the star player in a digitized collection of 359 astronomy textbooks published between 1472 and 1650—76,000 pages, including tens of thousands of scientific illustrations and astronomical tables. In that comprehensive data set, Matteo Valleriani, a professor with the Max Planck Institute for the History of Science, saw an opportunity to trace the evolution of European knowledge toward a shared scientific worldview. But he realized that discerning the pattern required more than human capabilities. So Valleriani and a team of researchers at the Berlin Institute for the Foundations of Learning and Data (BIFOLD) turned to machine learning. This required dividing the collection into three categories: text parts (sections of writing on a specific subject, with a clear beginning and end); scientific illustrations, which helped illuminate concepts such as a lunar eclipse; and numerical tables, which were used to teach mathematical aspects of astronomy. All this adds up to a question for historians: With machines set to play a greater role in the future, how much should we cede to them of the past? At the outset, Valleriani says, the text defied algorithmic interpretation. For one thing, typefaces varied widely; early modern print shops developed unique ones for their books and often had their own metallurgic workshops to cast their letters. This meant that a model using natural-language processing (NLP) to read the text would need to be retrained for each book. The language also posed a problem. Many texts were written in regionally specific Latin dialects often unrecognizable to machines that haven’t been trained on historical languages. “This is a big limitation in general for natural-language processing, when you don’t have the vocabulary to train in the background,” says Valleriani. This is part of the reason NLP works well for dominant languages like English but is less effective on, say, ancient Hebrew. Instead, researchers manually extracted the text from the source materials and identified single links between sets of documents—for instance, when a text was imitated or translated in another book. This data was placed in a graph, which automatically embedded those single links in a network containing all the records (researchers then used a graph to train a machine-­learning method that can suggest connections between texts). That left the visual elements of the texts: 20,000 illustrations and 10,000 tables, which researchers used neural networks to study. Present tense Computer vision for historical images faces similar challenges to NLP; it has what Lauren Tilton, an associate professor of digital humanities at the University of Richmond, calls a “present-ist” bias. Many AI models are trained on data sets from the last 15 years, says Tilton, and the objects they’ve learned to list and identify tend to be features of contemporary life, like cell phones or cars. Computers often recognize only contemporary iterations of objects that have a longer history—think iPhones and Teslas, rather than switchboards and Model Ts. To top it off, models are typically trained on high-resolution color images rather than the grainy black-and-white photographs of the past (or early modern depictions of the cosmos, inconsistent in appearance and degraded by the passage of time). This all makes computer vision less accurate when applied to historical images. “We’ll talk to computer science folks, and they’ll say, ‘Well, we solved object detection,’” she says. “And we’ll say, actually, if you take a set of photos from the 1930s, you’re going to see it hasn’t quite been as solved as we think.” Deep-learning models, which can identify patterns in large quantities of data, can help because they’re capable of greater abstraction. In the case of the Sphaera project , BIFOLD researchers trained a neural network to detect, classify, and cluster (according to similarity) illustrations from early modern texts; that model is now accessible to other historians via a public web service called CorDeep. They also took a novel approach to analyzing other data. For example, various tables found throughout the hundreds of books in the collection couldn’t be compared visually because “the same table can be printed 1,000 different ways,” Valleriani explains. So researchers developed a neural network architecture that detects and clusters similar tables on the basis of the numbers they contain, ignoring their layout. So far, the project has yielded some surprising results. One pattern found in the data allowed researchers to see that while Europe was fracturing along religious lines after the Protestant Reformation, scientific knowledge was coalescing. The scientific texts being printed in places such as the Protestant city of Wittenberg, which had become a center for scholarly innovation thanks to the work of Reformed scholars, were being imitated in hubs like Paris and Venice before spreading across the continent. The Protestant Reformation isn’t exactly an understudied subject, Valleriani says, but a machine-­mediated perspective allowed researchers to see something new: “This was absolutely not clear before.” Models applied to the tables and images have started to return similar patterns. Computers often recognize only contemporary iterations of objects that have a longer history—think iPhones and Teslas, rather than switchboards and Model Ts. These tools offer possibilities more significant than simply keeping track of 10,000 tables, says Valleriani. Instead, they allow researchers to draw inferences about the evolution of knowledge from patterns in clusters of records even if they’ve actually examined only a handful of documents. “By looking at two tables, I can already make a huge conclusion about 200 years,” he says. Deep neural networks are also playing a role in examining even older history. Deciphering inscriptions (known as epigraphy) and restoring damaged examples are painstaking tasks, especially when inscribed objects have been moved or are missing contextual cues. Specialized historians need to make educated guesses. To help, Yannis Assael, a research scientist with DeepMind, and Thea Sommerschield, a postdoctoral fellow at Ca’ Foscari University of Venice, developed a neural network called Ithaca, which can reconstruct missing portions of inscriptions and attribute dates and locations to the texts. Researchers say the deep-learning approach—which involved training on a data set of more than 78,000 inscriptions—is the first to address restoration and attribution jointly, through learning from large amounts of data. So far, Assael and Sommerschield say, the approach is shedding light on inscriptions of decrees from an important period in classical Athens, which have long been attributed to 446 and 445 BCE—a date that some historians have disputed. As a test, researchers trained the model on a data set that did not contain the inscription in question, and then asked it to analyze the text of the decrees. This produced a different date. “Ithaca’s average predicted date for the decrees is 421 BCE, aligning with the most recent dating breakthroughs and showing how machine learning can contribute to debates around one of the most significant moments in Greek history,” they said by email. Time machines Other projects propose to use machine learning to draw even broader inferences about the past. This was the motivation behind the Venice Time Machine, one of several local “time machines” across Europe that have now been established to reconstruct local history from digitized records. The Venetian state archives cover 1,000 years of history spread across 80 kilometers of shelves; the researchers’ aim was to digitize these records, many of which had never been examined by modern historians. They would use deep-learning networks to extract information and, by tracing names that appear in the same document across other documents, reconstruct the ties that once bound Venetians. Frédéric Kaplan, president of the Time Machine Organization, says the project has now digitized enough of the city’s administrative documents to capture the texture of the city in centuries past, making it possible to go building by building and identify the families who lived there at different points in time. “These are hundreds of thousands of documents that need to be digitized to reach this form of flexibility,” says Kaplan. “This has never been done before.” Still, when it comes to the project’s ultimate promise—no less than a digital simulation of medieval Venice down to the neighborhood level, through networks reconstructed by artificial intelligence—historians like Johannes Preiser-Kapeller, the Austrian Academy of Sciences professor who ran the study of Byzantine bishops, say the project hasn’t been able to deliver because the model can’t understand which connections are meaningful. Days of future past: Three key projects underway in the digital humanities CorDeep WHO: Max Planck Institute for the History of Science WHAT: A web-based application for classifying content from historical documents that include numerical and alphanumerical tables. Software can locate, extract, and classify visual elements designated “content illustrations,” “initials,” “decorations,” and “printer’s marks.” ITHACA Who: DeepMind What: A deep neural network trained to simultaneously perform the tasks of textual restoration, geographic attribution, and chronological attribution, previously performed by epigraphers. Venice Time Machine Project Who: École Polytechnique Fédérale de Lausanne, Ca’ Foscari, and the State Archives of Venice What: A digitized collection of the Venetian state archives, which cover 1,000 years of history. Once it’s completed, researchers will use deep learning to reconstruct historical social networks. Preiser-Kapeller has done his own experiment using automatic detection to develop networks from documents—extracting network information with an algorithm, rather than having an expert extract information to feed into the network as in his work on the bishops—and says it produces a lot of “artificial complexity” but nothing that serves in historical interpretation. The algorithm was unable to distinguish instances where two people’s names appeared on the same roll of taxpayers from cases where they were on a marriage certificate, so as Preiser-Kapeller says, “What you really get has no explanatory value.” It’s a limitation historians have highlighted with machine learning, similar to the point people have made about large language models like ChatGPT: because models ultimately don’t understand what they’re reading, they can arrive at absurd conclusions. It’s true that with the sources that are currently available, human interpretation is needed to provide context, says Kaplan, though he thinks this could change once a sufficient number of historical documents are made machine readable. But he imagines an application of machine learning that’s more transformational—and potentially more problematic. Generative AI could be used to make predictions that flesh out blank spots in the historical record—for instance, about the number of apprentices in a Venetian artisan’s workshop—based not on individual records, which could be inaccurate or incomplete, but on aggregated data. This may bring more non-elite perspectives into the picture but runs counter to standard historical practice, in which conclusions are based on available evidence. Still, a more immediate concern is posed by neural networks that create false records. Is it real? On YouTube, viewers can now watch Richard Nixon make a speech that had been written in case the 1969 moon landing ended in disaster but fortunately never needed to be delivered. Researchers created the deepfake to show how AI could affect our shared sense of history. In seconds, one can generate false images of major historical events like the D-Day landings, as Northeastern history professor Dan Cohen discussed recently with students in a class dedicated to exploring the way digital media and technology are shaping historical study. “[The photos are] entirely convincing,” he says. “You can stick a whole bunch of people on a beach and with a tank and a machine gun, and it looks perfect.” Related Story The new version of the company's large language model makes stuff up—but can also admit when it's wrong. False history is nothing new—Cohen points to the way Joseph Stalin ordered enemies to be erased from history books, as an example—but the scale and speed with which fakes can be created is breathtaking, and the problem goes beyond images. Generative AI can create texts that read plausibly like a parliamentary speech from the Victorian era, as Cohen has done with his students. By generating historical handwriting or typefaces, it could also create what looks convincingly like a written historical record. Meanwhile, AI chatbots like Character.ai and Historical Figures Chat allow users to simulate interactions with historical figures. Historians have raised concerns about these chatbots, which may, for example, make some individuals seem less racist and more remorseful than they actually were. In other words, there’s a risk that artificial intelligence, from historical chatbots to models that make predictions based on historical records, will get things very wrong. Some of these mistakes are benign anachronisms: a query to Aristotle on the chatbot Character.ai about his views on women (whom he saw as inferior) returned an answer that they should “have no social media.” But others could be more consequential—especially when they’re mixed into a collection of documents too large for a historian to be checking individually, or if they’re circulated by someone with an interest in a particular interpretation of history. Even if there’s no deliberate deception, some scholars have concerns that historians may use tools they’re not trained to understand. “I think there’s great risk in it, because we as humanists or historians are effectively outsourcing analysis to another field, or perhaps a machine,” says Abraham Gibson, a history professor at the University of Texas at San Antonio. Gibson says until very recently, fellow historians he spoke to didn’t see the relevance of artificial intelligence to their work, but they’re increasingly waking up to the possibility that they could eventually yield some of the interpretation of history to a black box. This “black box” problem is not unique to history: even developers of machine-learning systems sometimes struggle to understand how they function. Fortunately, some methods designed with historians in mind are structured to provide greater transparency. Ithaca produces a range of hypotheses ranked by probability, and BIFOLD researchers are working on the interpretation of their models with explainable AI, which is meant to reveal which inputs contribute most to predictions. Historians say they themselves promote transparency by encouraging people to view machine learning with critical detachment: as a useful tool, but one that’s fallible, just like people. The historians of tomorrow While skepticism toward such new technology persists, the field is gradually embracing it, and Valleriani thinks that in time, the number of historians who reject computational methods will dwindle. Scholars’ concerns about the ethics of AI are less a reason not to use machine learning, he says, than an opportunity for the humanities to contribute to its development. As the French historian Emmanuel Le Roy Ladurie wrote in 1968, in response to the work of historians who had started experimenting with computational history to investigate questions such as voting patterns of the British parliament in the 1840s, “the historian of tomorrow will be a programmer, or he will not exist.” Moira Donovan is an independent science journalist based in Halifax, Nova Scotia. hide by Moira Donovan 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 May/June 2023 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 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 "

"ChatGPT is going to change education, not destroy it | MIT Technology Review"

"https://www.technologyreview.com/2023/04/06/1071059/chatgpt-change-not-destroy-education-openai"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts ChatGPT is going to change education, not destroy it The narrative around cheating students doesn’t tell the whole story. Meet the teachers who think generative AI could actually make learning better. By Will Douglas Heaven archive page Selman Design The response from schools and universities was swift and decisive. Just days after OpenAI dropped ChatGPT in late November 2022, the chatbot was widely denounced as a free essay-writing, test-taking tool that made it laughably easy to cheat on assignments. Los Angeles Unified, the second-­largest school district in the US, immediately blocked access to OpenAI’s website from its schools’ network. Others soon joined. By January, school districts across the English-speaking world had started banning the software, from Washington, New York, Alabama, and Virginia in the United States to Queensland and New South Wales in Australia. Several leading universities in the UK, including Imperial College London and the University of Cambridge, issued statements that warned students against using ChatGPT to cheat. “While the tool may be able to provide quick and easy answers to questions, it does not build critical-­thinking and problem-solving skills, which are essential for academic and lifelong success,” Jenna Lyle, a spokeswoman for the New York City Department of Education, told the Washington Post in early January. This initial panic from the education sector was understandable. ChatGPT, available to the public via a web app, can answer questions and generate slick, well-structured blocks of text several thousand words long on almost any topic it is asked about, from string theory to Shakespeare. Each essay it produces is unique, even when it is given the same prompt again, and its authorship is (practically) impossible to spot. It looked as if ChatGPT would undermine the way we test what students have learned, a cornerstone of education. Related Story Exclusive conversations that take us behind the scenes of a cultural phenomenon. But three months on, the outlook is a lot less bleak. I spoke to a number of teachers and other educators who are now reevaluating what chatbots like ChatGPT mean for how we teach our kids. Far from being just a dream machine for cheaters, many teachers now believe, ChatGPT could actually help make education better. Advanced chatbots could be used as powerful classroom aids that make lessons more interactive, teach students media literacy, generate personalized lesson plans, save teachers time on admin, and more. Educational-tech companies including Duolingo and Quizlet, which makes digital flash cards and practice assessments used by half of all high school students in the US, have already integrated OpenAI’s chatbot into their apps. And OpenAI has worked with educators to put together a fact sheet about ChatGPT’s potential impact in schools. The company says it also consulted educators when it developed a free tool to spot text written by a chatbot (though its accuracy is limited). “We believe that educational policy experts should decide what works best for their districts and schools when it comes to the use of new technology,” says Niko Felix, a spokesperson for OpenAI. “We are engaging with educators across the country to inform them of ChatGPT’s capabilities. This is an important conversation to have so that they are aware of the potential benefits and misuse of AI, and so they understand how they might apply it to their classrooms.” But it will take time and resources for educators to innovate in this way. Many are too overworked, under-resourced, and beholden to strict performance metrics to take advantage of any opportunities that chatbots may present. It is far too soon to say what the lasting impact of ChatGPT will be—it hasn’t even been around for a full semester. What’s certain is that essay-writing chatbots are here to stay. And they will only get better at standing in for a student on deadline—more accurate and harder to detect. Banning them is futile, possibly even counterproductive. “We need to be asking what we need to do to prepare young people—learners—for a future world that’s not that far in the future,” says Richard Culatta, CEO of the International Society for Technology in Education (ISTE), a nonprofit that advocates for the use of technology in teaching. Tech’s ability to revolutionize schools has been overhyped in the past, and it’s easy to get caught up in the excitement around ChatGPT’s transformative potential. But this feels bigger: AI will be in the classroom one way or another. It’s vital that we get it right. From ABC to GPT Much of the early hype around ChatGPT was based on how good it is at test taking. In fact, this was a key point OpenAI touted when it rolled out GPT-4 , the latest version of the large language model that powers the chatbot, in March. It could pass the bar exam! It scored a 1410 on the SAT! It aced the AP tests for biology, art history, environmental science, macroeconomics, psychology, US history, and more. Whew! It’s little wonder that some school districts totally freaked out. Yet in hindsight, the immediate calls to ban ChatGPT in schools were a dumb reaction to some very smart software. “People panicked,” says Jessica Stansbury, director of teaching and learning excellence at the University of Baltimore. “We had the wrong conversations instead of thinking, ‘Okay, it’s here. How can we use it?’” “It was a storm in a teacup,” says David Smith, a professor of bioscience education at Sheffield Hallam University in the UK. Far from using the chatbot to cheat, Smith says, many of his students hadn’t yet heard of the technology until he mentioned it to them: “When I started asking my students about it, they were like, ‘Sorry, what?’” Even so, teachers are right to see the technology as a game changer. Large language models like OpenAI’s ChatGPT and its successor GPT-4, as well as Google’s Bard and Microsoft’s Bing Chat, are set to have a massive impact on the world. The technology is already being rolled out into consumer and business software. If nothing else, many teachers now recognize that they have an obligation to teach their students about how this new technology works and what it can make possible. “They don’t want it to be vilified,” says Smith. “They want to be taught how to use it.” Related Story New large language models will transform many jobs. Whether they will lead to widespread prosperity or not is up to us. Change can be hard. “There’s still some fear,” says Stansbury. “But we do our students a disservice if we get stuck on that fear.” Stansbury has helped organize workshops at her university to allow faculty and other teaching staff to share their experiences and voice their concerns. She says that some of her colleagues turned up worried about cheating, others about losing their jobs. But talking it out helped. “I think some of the fear that faculty had was because of the media,” she says. “It’s not because of the students.” In fact, a US survey of 1,002 K–12 teachers and 1,000 students between 12 and 17, commissioned by the Walton Family Foundation in February, found that more than half the teachers had used ChatGPT—10% of them reported using it every day—but only a third of the students. Nearly all those who had used it (88% of teachers and 79% of students) said it had a positive impact. A majority of teachers and students surveyed also agreed with this statement: “ChatGPT is just another example of why we can’t keep doing things the old way for schools in the modern world.” Helen Crompton, an associate professor of instructional technology at Old Dominion University in Norfolk, Virginia, hopes that chatbots like ChatGPT will make school better. Many educators think that schools are stuck in a groove, says Crompton, who was a K–12 teacher for 16 years before becoming a researcher. In a system with too much focus on grading and not enough on learning, ChatGPT is forcing a debate that is overdue. “We’ve long wanted to transform education,” she says. “We’ve been talking about it for years.” Take cheating. In Crompton’s view, if ChatGPT makes it easy to cheat on an assignment, teachers should throw out the assignment rather than ban the chatbot. We need to change how we assess learning, says Culatta: “Did ChatGPT kill assessments? They were probably already dead, and they’ve been in zombie mode for a long time. What ChatGPT did was call us out on that.” Critical thinking Emily Donahoe, a writing tutor and educational developer at the University of Mississippi, has noticed classroom discussions starting to change in the months since ChatGPT’s release. Although she first started to talk to her undergraduate students about the technology out of a sense of duty, she now thinks that ChatGPT could help teachers shift away from an excessive focus on final results. Getting a class to engage with AI and think critically about what it generates could make teaching feel more human, she says, “rather than asking students to write and perform like robots.” This idea isn’t new. Generations of teachers have subscribed to a framework known as Bloom’s taxonomy, introduced by the educational psychologist Benjamin Bloom in the 1950s, in which basic knowledge of facts is just the bedrock on which other forms of learning, such as analysis and evaluation, sit. Teachers like Donahoe and Crompton think that chatbots could help teach those other skills. In the past, Donahoe would set her students to writing assignments in which they had to make an argument for something—and grade them on the text they turned in. This semester, she asked her students to use ChatGPT to generate an argument and then had them annotate it according to how effective they thought the argument was for a specific audience. Then they turned in a rewrite based on their criticism. Related Story A frenzy of activity from tech giants and startups alike is reshaping what people want from search—for better or worse. Breaking down the assignment in this way also helps students focus on specific skills without getting sidetracked. Donahoe found, for example, that using ChatGPT to generate a first draft helped some students stop worrying about the blank page and instead focus on the critical phase of the assignment. “It can help you move beyond particular pain points when those pain points aren’t necessarily part of the learning goals of the assignment,” she says. Smith, the bioscience professor, is also experimenting with ChatGPT assignments. The hand-wringing around it reminds him of the anxiety many teachers experienced a couple of years ago during the pandemic. With students stuck at home, teachers had to find ways to set assignments where solutions were not too easy to Google. But what he found was that Googling—what to ask for and what to make of the results—was itself a skill worth teaching. Smith thinks chatbots could be the same way. If his undergraduate students want to use ChatGPT in their written assignments, he will assess the prompt as well as—or even rather than—the essay itself. “Knowing the words to use in a prompt and then understanding the output that comes back is important,” he says. “We need to teach how to do that.” The new education These changing attitudes reflect a wider shift in the role that teachers play, says Stansbury. Information that was once dispensed in the classroom is now everywhere: first online, then in chatbots. What educators must now do is show students not only how to find it, but what information to trust and what not to, and how to tell the difference. “Teachers are no longer gatekeepers of information, but facilitators,” she says. In fact, teachers are finding opportunities in the misinformation and bias that large language models often produce. These shortcomings can kick off productive discussions, says Crompton: “The fact that it’s not perfect is great.” Teachers are asking students to use ChatGPT to generate text on a topic and then getting them to point out the flaws. In one example that a colleague of Stansbury’s shared at her workshop, students used the bot to generate an essay about the history of the printing press. When its US-centric response included no information about the origins of print in Europe or China, the teacher used that as the starting point for a conversation about bias. “It’s a great way to focus on media literacy,” says Stansbury. Crompton is working on a study of ways that chatbots can improve teaching. She runs off a list of potential applications she’s excited about, from generating test questions to summarizing information for students with different reading levels to helping with time-­consuming administrative tasks such as drafting emails to colleagues and parents. One of her favorite uses of the technology is to bring more interactivity into the classroom. Teaching methods that get students to be creative, to role-play, or to think critically lead to a deeper kind of learning than rote memorization, she says. ChatGPT can play the role of a debate opponent and generate counterarguments to a student’s positions, for example. By exposing students to an endless supply of opposing viewpoints, chatbots could help them look for weak points in their own thinking. Crompton also notes that if English is not a student’s first language, chatbots can be a big help in drafting text or paraphrasing existing documents, doing a lot to level the playing field. Chatbots also serve students who have specific learning needs, too. Ask ChatGPT to explain Newton’s laws of motion to a student who learns better with images rather than words, for example, and it will generate an explanation that features balls rolling on a table. Made-to-measure learning All students can benefit from personalized teaching materials, says Culatta, because everybody has different learning preferences. Teachers might prepare a few different versions of their teaching materials to cover a range of students’ needs. Culatta thinks that chatbots could generate personalized material for 50 or 100 students and make bespoke tutors the norm. “I think in five years the idea of a tool that gives us information that was written for somebody else is going to feel really strange,” he says. Some ed-tech companies are already doing this. In March, Quizlet updated its app with a feature called Q-Chat, built using ChatGPT, that tailors material to each user’s needs. The app adjusts the difficulty of the questions according to how well students know the material they’re studying and how they prefer to learn. “Q-Chat provides our students with an experience similar to a one-on-one tutor,” says Quizlet’s CEO, Lex Bayer. In fact, some educators think future textbooks could be bundled with chatbots trained on their contents. Students would have a conversation with the bot about the book’s contents as well as (or instead of) reading it. The chatbot could generate personalized quizzes to coach students on topics they understand less well. Not all these approaches will be instantly successful, of course. Donahoe and her students came up with guidelines for using ChatGPT together, but “it may be that we get to the end of this class and I think this absolutely did not work,” she says. “This is still an ongoing experiment.” She has also found that students need considerable support to make sure ChatGPT promotes learning rather than getting in the way of it. Some students find it harder to move beyond the tool’s output and make it their own, she says: “It needs to be a jumping-off point rather than a crutch.” And, of course, some students will still use ChatGPT to cheat. In fact, it makes it easier than ever. With a deadline looming, who wouldn’t be tempted to get that assignment written at the push of a button? “It equalizes cheating for everyone,” says Crompton. “You don’t have to pay. You don’t have to hack into a school computer.” Some types of assignments will be harder hit than others, too. ChatGPT is really good at summarizing information. When that is the goal of an assignment, cheating is a legitimate concern, says Donahoe: “It would be virtually indistinguishable from an A answer in that context. It is something we should take seriously.” None of the educators I spoke to have a fix for that. And not all other fears will be easily allayed. (Donahoe recalls a recent workshop at her university in which faculty were asked what they were planning to do differently after learning about ChatGPT. One faculty member responded: “I think I’ll retire.”) But nor are teachers as worried as initial reports suggested. Cheating is not a new problem: schools have survived calculators, Google, Wikipedia, essays-for-pay websites, and more. For now, teachers have been thrown into a radical new experiment. They need support to figure it out—perhaps even government support in the form of money, training, and regulation. But this is not the end of education. It’s a new beginning. “We have to withhold some of our quick judgment,” says Culatta. “That’s not helpful right now. We need to get comfortable kicking the tires on this thing.” 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 This story was part of our May/June 2023 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 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 "

"Bringing the lofty ideas of pure math down to earth | MIT Technology Review"

"https://www.technologyreview.com/2023/04/24/1071371/book-reviews-math-education"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Bringing the lofty ideas of pure math down to earth There is no shortage of popular books and lectures on math—but they can only teach us so much. By Pradeep Niroula archive page Jenny Kroik Mathematics has long been presented as a sanctuary from confusion and doubt, a place to go in search of answers. Perhaps part of the mystique comes from the fact that biographies of mathematicians often paint them as otherworldly savants—people who seem to pull nature’s deepest truths from thin air and transcribe them in prose so succinct and self-assured it must be read meditatively, one word at a time. As a graduate student in physics, I have seen the work that goes into conducting delicate experiments, but the daily grind of mathematical discovery is a ritual altogether foreign to me. And this feeling is only reinforced by popular books on math, which often take the tone of a pastor dispensing sermons to the faithful. In physics, the questions we ask and the theories we come up with aim to explain the underlying reality better. Indeed, certain concepts—like the fact that opposite charges attract or that disorder or entropy tends to increase—are so universally ingrained in our experience that they creep into everyday language as metaphors. I often catch myself resorting to the vocabulary of research and analogies from physics to explain myself. But despite having been close to math for most of my life, I continue to be bewildered by mathematics research. What motivates it, and what is its ultimate endgame? What does the world look like to someone steeped in the culture of mathematics? So when I discovered that Terence Tao, a living legend of contemporary math, was offering an online class on his approach to “mathematical thinking,” I had to check it out. Related Story A new kind of machine-learning model is set to improve automated decision making in finance, health care, ad targeting, and more. The movie-length course, distributed by MasterClass, starts out invitingly enough. Tao exudes calm and confidence. A mathematical mindset, he says, makes “the complex world a bit more manageable.” He suggests that his class might be “even more suitable for those without formal math training.” But very soon, the futility of this attempt to pierce the mystique of mathematics becomes inescapable. For most of the session, Tao is seated in a white armchair; there are no blackboards, no pens, no paper. “Mathematics is a language of precise communication,” Tao says, and yet here, he is without the most powerful tools for achieving that. Although he tries to be approachable, talking about how he once did poorly in an exam and struggles to assemble window curtains, I felt no closer to the world of math. After 90 minutes of watching, the pithy takeaways I was left with were indistinguishable from what I might learn at a mindfulness retreat: ‘‘Everything is united” and “Embrace failure.” I am not the only person who has tried—and failed—to break into the church of math. Recently, Alec Wilkinson, a writer for the New Yorker and a longtime believer in self-improvement, took on a yearlong project to conquer some of the basic mathematics that evaded him in his youth: algebra, geometry, and calculus. In his 2022 book A Divine Language , he describes his journey as a quest for redemption after those struggles with high school math. “It had abused me, and I felt aggrieved,” he writes. “I was returning, with a half century’s wisdom, to knock the smile off math’s face.” Wilkinson has a better plan than mine: he starts with standard textbooks. And he has help. His niece, a math professor, agrees to hold his hand through this journey. But even the first steps through algebra are backbreaking. The skepticism of an adult gets in the way; he cannot seem to accept the rules—the way variables can be added and multiplied, how fractions and exponents work—as readily as children do. What’s more, he finds the textbook writing atrocious. Revisiting algebra as an adult, Wilkinson declares, is “like meeting someone you hadn’t seen in years and being reminded why you never liked him or her.” “There is a boosterish quality to the prose, as if learning math is not only fun! but also obscurely patriotic, the duty of an adolescent citizen-in-waiting,” he writes. “In addition to leaving things out, they were careless about language, their sentences were disorderly, their thinking was frequently slipshod, and their tone was often cheerfully and irrationally impatient.” Though he wrestles algebra with decidedly determined rigor, six hours a day for six to seven days a week, and obsesses about it the rest of the time, simple competence continues to elude him. Revisiting algebra as an adult, he declares, is “like meeting someone you hadn’t seen in years and being reminded why you never liked him or her.” When Wilkinson is not hunched over textbooks, he is dazzled by the mysticism surrounding math. The mathematicians he talks to speak of their profession with quasi-religious sentiments and think of themselves as mere prospectors of a transcendental order. When Wilkinson complains to his niece that math is not yielding to him, he is told, “For a moment, think of it as a monastic discipline. You have to take on faith what I tell you.” Where his niece and others see patterns and order, he perceives only “incoherence, obfuscation, and chaos”; he feels like a monk who sees lesser angels than everybody around him. He is now reproachful of his education and his younger self: Why hadn’t he learned all this better when he had the impressionability of a child? A year later, Wilkinson can solve some calculus problems, but the journey was difficult, the terrain harsh and often unwelcoming. Math often gets talked about as a language with logic as its grammar. But when you learn a language like Spanish, you can casually pick up some words and immediately unlock a new culture. The introductory steps to formal math, on the other hand, demand a commitment to rigor and abstraction while withholding any usefulness. Among mathematicians, as Wilkinson discovers, there is even a general derision toward those who seek useful application. There is G.H. Hardy’s famous jeer in 1940, “Is not the position of an ordinary applied mathematician in some ways a little pathetic?” Or a more recent remark by John Baez: “If you do not like abstraction, why are you in mathematics? Perhaps you should be in finance, where all the numbers have dollar signs in front of them.” Math’s only promise in return for unwavering fealty is that of a higher plan, much as in a cult. Wilkinson is left as dazed and exhausted as a victim of a shipwreck stranded in the Arctic. My frustrations and Wilkinson’s highlight the inadequacies of the mediums usually employed in teaching mathematics.Textbooks aren’t always written with accessibility in mind. They vacillate between pedantry and hand-wavy dismissals, and the exercises they present can appear to be a series of pointless drills. At the same time, attempts at an overview can feel frustratingly empty. What Wilkinson and I really needed was a sympathetic voice—the testimony of one who has climbed the heights of abstract math but also has the patience to guide a newcomer. The mathematician and concert pianist Eugenia Cheng is the closest I’ve come to finding such a voice. I got into Cheng’s books because I share her love of baking. For the proud owner of a stand mixer and several pastry brushes, the title Cakes, Custard and Category Theory sounded too delectable to pass up. Its first chapter, about the epistemic nature of mathematics, starts with a recipe for brownies. Cheng tells you that stumbling into new ideas in math is like screwing up a soufflé recipe so badly that you end up with cookies. I was easily drawn in. Many popular books on mathematics try to be approachable by talking about stock markets or poker odds.Others wax poetic about prime numbers and the mystery of infinity. Cheng’s books lift readers to the rarefied heights of mathematical abstraction by teaching them category theory, which she believes is the most foundational kind of math. Category theory may seem esoteric, but it is the underlying grammar of mathematical logic. Cheng’s books pull back the curtain to show how pedestrian mathematics research can be; the act of chaining simple inviolable axioms into complex arguments is simply the ivory-tower equivalent of building a Lego spaceship from tiny, indestructible pieces. More important, they are an invitation to change your worldview, to simplify thinking with abstractions, to interpret and analyze the world in mathematical terms. Reading Cakes, Custard and Category Theory (also issued as How to Bake Pi ), one soon discovers that the desserts are mere gambits. Each chapter begins with a recipe followed by an analogy between math and baking. Puff pastry is a reminder that extreme precision is a part of mathematical research; elsewhere, we learn that there is really no right way to make a cake and that we should embrace flexibility in ingredients as well as techniques. These analogies can feel tenuous, sometimes even forced. But thankfully, they quickly fade away to make room for a casual conversation about mathematical topics. Cheng thinks the steely vocabulary of logic can help people caught in a heated argument realize that the divide between them isn’t so irreconcilable. Cheng’s latest book, The Joy of Abstraction, builds on similar themes but feels more like an undergraduate textbook. Its chapters, with titles like “Isomorphism” and “Functors,” provide a fairly rigorous introduction to category theory and are replete with theorems, proofs, and exercises. Occasionally, Cheng goes on a tangent about how certain concepts have etymological and semantic parallels to real life—a “function” can be thought of as a vending machine, a “set” may represent a group of people (and you can divide that set into “partitions” of “friendships”). But having set up the stage using familiar objects, she quickly gets to the hard work of manipulating them using logic. In short, her books are a humane introduction to foundational math, and they paint a good picture of what mathematicians spend their time thinking about. There is, however, one major way her math books markedly differ from undergraduate textbooks. A persistent theme running across Cheng’s writing is that the world is best understood in a stripped-down form, and that insights from abstract math can even nourish empathy and a sense of justice. Friends trying to be sympathetic to a heartbreak by prying into painful details should content themselves with simply knowing that a) there was something you loved and b) you recently lost it. It’s as simple as that; all other details are superfluous. Cheng’s more unorthodox contention—one best presented in her book The Art of Logic in an Illogical World —is that category theory can, in fact, be deployed in our daily lives to make discussions around privilege, sexual harassment, racism, and even “fake news” less divisive. For instance, she thinks that the debate about social welfare can be described in terms of “false positives” and “false negatives”: “a false negative in this case is someone who deserves help but doesn’t get it; a false positive would be someone who doesn’t deserve help but does get it.” The debate, her argument goes, isn’t about whether we should help people (of course we should!) but rather about the extent to which we accommodate such false positives and false negatives. Someone who wants to reduce the amount of money spent on social welfare is probably bothered by the idea that false positives are abusing the system by collecting benefits they don’t deserve. Cheng thinks the steely vocabulary of logic can help people caught in a heated argument realize that the divide between them isn’t so irreconcilable (after all, they both want to help people) and steer them toward a more nuanced conversation of “to what extent” and “under what circumstances.” Related Story Innovative technologies such as AI are taking automotive design and development on a new road toward net zero for the mobility industry. Cheng believes we can encourage empathy through logically related analogies. Initially befuddled by men who protest sweeping accusations of privilege or aggression, she finds it helpful to compare their protests to the exasperation she feels when people resent graduates of elite schools (like herself) for having success handed to them by parents even though Cheng herself had to work hard. This, we are told, has made her more empathetic toward men: emotions rightfully flare up when individual experiences contrast with group generalizations. However, applying such arguments to more complex cases feels increasingly suspect. A diagram that appears in many of Cheng’s books is the “cube of privilege.” In one corner of the cube is the empty set {}. Starting from that corner (bottom front left in the illustration), you can move in three directions to collect one of three types of privilege: white, male, and rich. If you move in all three directions, one after another, you end up in the opposite corner with all privilege points: {white, male, rich}. To a category theorist, this is the most succinct description of intersectionality: the idea that attributes like class, gender, and race can interact to produce complex manifestations of inequality. Cheng’s diagram shows how combinations of privilege in multiple dimensions can form complicated hierarchies, so that people with three types of privilege are necessarily better off than people with only two types. But when Cheng uses this diagram for insights on thornier questions, like why “white men who did not grow up rich” may feel particularly aggrieved by non-white men who are richer and better off, her answer is unsatisfying: in the cube of privilege “there is no arrow from rich non-white men to non-rich white men (the two groups inhabit disconnected corners of a diagonal), so the theory of privilege does not say anything about the relative situation of these two groups.” The cop-out may be logically consistent, but it is certainly not the rhetorical coup de grâce one hopes to learn after engaging with abstract reasoning for several weeks. One may equip people with rigorous tools to avoid the slipperiness and ambiguity of everyday language, but these tools don’t always come with ethical guidelines. The Malthusian panic over population explosion, for example, emerged from observations about the exponential function and has been used to justify anti-immigration policies as well as genocides. Mathematically inspired computer models are routinely shown to have bias. A highly controversial book from 1994 hid its dubious efforts to connect race with intelligence behind the mathy title The Bell Curve. As in the Bible, Tocqueville’s Democracy in America , and other revered tomes, there is enough in the vast literature of math to justify and reinforce any kind of thinking, however contrarian, problematic, or silly. Yet there is still a sense in which Eugenia Cheng’s mission of demystifying math is extremely noble. Her books try to replicate the humdrum ritual of constructing arguments from ironclad proofs, and—more important—they show what a math-inspired view of the world could look like, both in its oddity and in its permissiveness. You may find such a worldview odious and disagreeable, but the key lesson from Cheng’s books is that communicating a complex thought from one mind to another, let alone across cultures and languages, is no easy feat and that the art of expressing ideas charitably and with clarity is something we all would benefit from getting better at. What I find most inspiring about the culture of mathematics is how it has endured through the ages, needling a common thread across civilizations. Math has managed to unify disparate discoveries across the globe, and the puzzles raised centuries ago are still being pondered. One reason this culture may appear mystifying for a beginner is that contemporary math has whittled down millennia-old ideas, once rich and vivid, into terse symbols and esoteric terminologies that aren’t always easy to master. Popular math books seek a fresher take on these old ideas, be it through baking recipes or hot-button political issues. My verdict: Why not? It’s worth a shot. Pradeep Niroula is doctoral candidate in physics based in Washington, DC. hide by Pradeep Niroula 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 May/June 2023 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 Humans and technology Why embracing complexity is the real challenge in software today In the midst of industry discussions about productivity and automation, it’s all too easy to overlook the importance of properly reckoning with complexity. By Ken Mugrage archive page Turning medical data into actionable knowledge Technology can transform patient care by bringing together data from a variety of sources By Siemens Healthineers archive page Moving data through the supply chain with unprecedented speed Tackle supply chain visibility and customer engagement with standards and “phygital” technology. By MIT Technology Review Insights archive page Customer experience horizons The big ideas that define the future of customer and employee experience. By MIT Technology Review Insights 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 ongoing Huawei saga, explained in brief | MIT Technology Review"

"https://www.technologyreview.com/2019/05/24/65753/the-ongoing-huawei-saga-explained-in-brief"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts The ongoing Huawei saga, explained in brief By Charlotte Jee archive page A man walks past an electronics shop in China Associated Press If you’re feeling bewildered trying to keep up with the never-ending references to Huawei in the news, you’re not alone. Fear not—here’s a handy time line of everything that has happened so far this week. And remember, however bad your week has been, it probably hasn’t been as bad as Huawei’s. (If you still want to learn more about how we got to this point, there’s a handy explainer on the wider context here. And here’s our own explainer of 5G and Huawei’s connection: “ The real reason America is scared of Huawei: internet-connected everything. ” 1. This week’s furor kicked off with the US’s announcement last Thursday that it had added Huawei to the “ Entity List ,” a blacklist of companies subject to export restrictions. The Justice Department claimed that Huawei has broken sanctions on Iran, among other things. 2. On Monday, Google announced it had blocked Huawei from using Android in any new phones. Huawei is the second biggest smartphone maker in the world. This would stop it from being able to embed Maps, Gmail, or YouTube in any of its new handsets. 3. Chipmakers Intel, Qualcomm, Xilinx, and Broadcom also said they would not sell components to Huawei. 4. On Tuesday the US said it would temporarily ease these restrictions, but they’ll still kick in from August. Huawei’s founder shot back that the US “underestimates” Huawei. 5. On Wednesday, UK chip designer ARM said it would have to sever ties with Huawei. This could be a far more serious blow than Google’s announcement, as Huawei's chips rely heavily on ARM’s designs. Two British carriers also said they would not offer Huawei phones to future 5G customers. 6. Latest: it looks as if Huawei could have enough inventory to weather the blacklist for months. And Trump sees it as a pawn in trying to achieve a trade deal with China. Even though Huawei is “very dangerous” in unspecified ways. All make sense? hide by Charlotte Jee 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 Computing What’s next for the world’s fastest supercomputers Scientists have begun running experiments on Frontier, the world’s first official exascale machine, while facilities worldwide build other machines to join the ranks. By Sophia Chen archive page AI-powered 6G networks will reshape digital interactions The convergence of AI and communication technologies will create 6G networks that make hyperconnectivity and immersive experiences an everyday reality for consumers. By MIT Technology Review Insights archive page The power of green computing Sustainable computing practices have the power to both infuse operational efficiencies and greatly reduce energy consumption, says Jen Huffstetler, chief product sustainability officer at Intel. By MIT Technology Review Insights archive page How this Turing Award–winning researcher became a legendary academic advisor Theoretical computer scientist Manuel Blum has guided generations of graduate students into fruitful careers in the field. By Sheon Han 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 "

"Shoveling Water | MIT Technology Review"

"https://www.technologyreview.com/2009/12/21/207164/shoveling-water"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Shoveling Water By David Rotman archive page The new microfluidic chip fabricated by Fluidigm, a startup based in South San Francisco, represents a decade of successive inventions. This small square of spongy polymer–the same type used in contact lenses and window caulking–holds a complex network of microscopic channels, pumps, and valves. Minute volumes of liquid from, say, a blood sample can flow through the maze of channels to be segregated by the valves and pumps into nearly 10,000 tiny chambers. In each chamber, nanoliters (billionths of a liter) of the liquid can be analyzed. The ability to move fluids around a chip on a microscopic scale is one of the most impressive achievements of biochemistry over the last 10 years. Microfluidic chips, which are now produced by a handful of startup companies and a similar number of university-­based foundries, allow biologists and chemists to manipulate tiny amounts of fluid in a precise and highly automated way. The potential applications are numerous, including handheld devices to detect various diseases and machines that can rapidly analyze the content of a large number of individual cells (each holding about one picoliter of liquid) to identify, for example, rare and deadly cancerous mutations. But microfluidics also represents a fundamental breakthrough in how researchers can interact with the biological world. “Life is water flowing through pipes,” says George Whitesides, a chemist at Harvard University who has invented much of the technology used in microfluidics. “If we’re interested in life, we must be interested in fluids on small scales.” By way of explaining the importance of the technology and the complexity of its microscopic apparatus, those involved in microfluidics often make comparisons to microprocessors and integrated circuits. Indeed, a microfluidic chip and an electronic microprocessor have similar architectures, with valves replacing transistors and channels replacing wires. But manipulating liquids through channels is far more difficult than routing electrons around an integrated circuit. Fluids are, well, messy. They can be hard to move around, they often consist of a complex stew of ingredients, and they can stick and leak. Over the last decade, researchers have overcome many such challenges. But if microfluidics is ever to become truly comparable to microelectronics, it will need to overcome a far more daunting challenge: the transition from promising laboratory tool to widely used commercial technology. Can it be turned into products that scientists, medical technicians, and physicians will want to use? Biologists are increasingly interested in using microfluidic systems, Whitesides says. But, he adds, “do you go into the lab and find these devices everywhere? The answer is no. What’s interesting is that it hasn’t really taken off. The question is, why not?” Things Reviewed Biomark 96.96 Dynamic Array Fluidigm The Nature of Technology: What It Is and How It Evolves By W. Brian Arthur Free Press, 2009 A similar question could just as well be asked about at least two other important technologies that have emerged over the last decade: genomic-based medicine and nanotechnology. Each began this century with significant breakthroughs and much fanfare. The sequencing of the human genome was first announced in early 2001; the National Nanotechnology Initiative, which helped launch much of today’s nanotech research, got its first federal funding in 2000. While all three technologies have produced a smattering of new products, none has had the transformative effects many experts expected. Why does it take so long for a technology as obviously important and valuable as these to make an impact? How do you create popular products out of radically new technologies? And how do you attract potential users? Patience, Patience Despite the economic, social, and scientific importance of technology, the process of creating it is poorly understood. In particular, researchers have largely overlooked the question of how technologies develop over time. That’s the starting point of W. Brian Arthur’s The Nature of Technology, an attempt to develop a comprehensive theory of “what technology is and how it evolves.” Arthur set to work in the library stacks at Stanford University. “As I began to read, I was astonished that some of the key questions had not been very deeply thought about,” he recalled in a recent interview. While much has been written on the sociology of technology and engineering, and there’s plenty on the histories of various technologies, he said, “there were big gaps in the literature. How does technology actually evolve? How do you define technology?” link A patent map created by IPVision, based in Cambridge, MA, shows many of the key inventions by Stephen Quake and Fluidigm over the last decade that make possible the company’s microfluidic chips. The timeline shows several key initial advances and how today’s microfluidics use both advances in microfabrication and biochemistry. Such a complex network of inventions is not uncommon in the development of new bodies of technology. Credit: IPVision Arthur hopes to do for technology what Thomas Kuhn famously did for science in his 1962 The Structure of Scientific Revolutions, which described how scientific breakthroughs come about and how they are adopted. A key part of Arthur’s argument is that technology has its own characteristics and “nature,” and that it has too long been treated as subservient to science or simply as “applied science.” Science and technology are “completely interwoven” but different, he says: “Science is about understanding phenomena, whereas technology is really about harnessing and using phenomena. They build out of each other.” Arthur, a former professor of economics and population studies at Stanford who is now an external professor at the Santa Fe Institute and a visiting researcher at the Palo Alto Research Center, is perhaps best known for his work on complexity theory and for his analysis of increasing returns, which helped explain how one company comes to dominate the market for a new technology. Whether he fulfills his goal of formulating a rigorous theory of technology is debatable. The book does, however, offer a detailed description of the characteristics of technologies, peppered with interesting historical tidbits. And it provides a context in which to begin understanding the often laborious and lengthy processes by which technologies are commercially exploited. Particularly valuable are Arthur’s insights into how different “domains” of technology evolve differently compared to individual technologies. Domains, as Arthur defines them, are groups of technologies that fit together because they harness a common phenomenon. Electronics is a domain; its devices–capacitors, inductors, transistors–all work with electrons and thus naturally fit together. Likewise, in photonics, lasers, fiber-optic cables, and optical switches all manipulate light. Whereas an individual technology–say, the jet engine–is designed for a particular purpose, a domain is “a toolbox of useful components”–“a constellation of technologies”–that can be applied across many industries. A technology is invented, Arthur writes. A domain “emerges piece by piece from its individual parts.” The distinction is critical, he argues, because users may quickly adopt an individual technology to replace existing devices, whereas new domains are “encountered” by potential users who must try to understand them, figure out how to use them, determine whether they are worthwhile, and create applications for them. Meanwhile, those developing the new domains must improve the tools in the toolbox and invent the “missing pieces” necessary for new applications. All this “normally takes decades,” Arthur says. “It is a very, very slow process.” What Arthur touches on just briefly is that this evolution of a new body of technology is often matched by an even more familiar progression: enthusiasm about a new technology, investor and user disillusionment as the technology fails to live up to the hyperbole, and a slow reëmergence as the technology matures and begins to meet the market’s needs. A Solution Looking for Problems In the late 1990s, microfluidics (or, as it is sometimes called, “lab on a chip” technology) became another overhyped advance in an era notorious for them. Advocates talked up the potential of the chips. But the devices couldn’t perform the complex fluid manipulations required for many applications. “They were touted as a replacement for everything. That clearly didn’t pan out too well,” says Michael Hunkapiller, a venture capitalist at Alloy Ventures in Palo Alto, CA, who is now investing in several microfluidics startups, including Fluidigm. The technology’s capabilities in the 1990s, he says, “were far less universal than the hype.” The problem, as Arthur might put it, was that the toolbox was missing key pieces. Prominent among the needed components were valves, which would allow the flow of liquids to be turned on and off at specific spots on the chip. Without valves, you merely have a hose; with valves you can build pumps and begin to think of ways to construct plumbing. The problem was solved in the lab of Stephen Quake, then a professor of applied physics at Caltech and now in the bioengineering department at Stanford. Quake and his Caltech coworkers found a simple way to make valves in microfluidic channels on a polymer slab. Within two years of publishing a paper on the valves, the group had learned how to create a microfluidic chip with thousands of valves and hundreds of reaction chambers. It was the first such chip worthy of being compared to an integrated circuit. The technology was licensed to Fluidigm, which Quake cofounded in 1999. Meanwhile, other academic labs invented other increasingly complex ways to manipulate liquids in microfluidic devices. The result is a new generation of companies equipped with far more capable technologies. Still, many potential users remain skeptical. Once again, microfluidics finds itself in a familiar phase of technology development. As David Weitz, a physics professor at Harvard and cofounder of several microfluidics companies, explains: “It is a wonderful solution still looking for the best problems.” There are plenty of possibilities. Biomedical researchers have begun to use microfluidics to look at how individual cells express genes. In one experiment, cancer researchers are using one of Fluidigm’s chips to analyze prostate tumor cells, seeking patterns that would help them select the drugs that will most effectively combat the tumor. Also, Fluidigm has recently introduced a chip designed to grow stem cells in a precisely controlled microenvironment. Currently, when stem cells are grown in the lab, it can be difficult to mimic the chemical conditions in a living animal. But tiny groups of stem cells could be partitioned in sections of a microfluidic chip and bathed in combinations of biochemicals, allowing scientists to optimize their growing conditions. And microfluidics could make possible cheap and portable diagnostic devices for use in doctor’s offices or even remote clinics. In theory, a sample of, say, blood could be dropped on a microfluidic chip, which would perform the necessary bioassay–identifying a virus, detecting telltale cancer proteins, or finding biochemical signs of a heart attack. But in medical diagnostics as in biomedical research, microfluidics has yet to be widely adopted. Again, Arthur’s analysis offers an explanation. Users who encounter the new tools must determine whether they are worthwhile. In the case of many diagnostic applications, biologists must better understand which biochemicals to detect in order to develop tests. Meanwhile, those developing microfluidic devices must make the devices easier to use. As Arthur reminds us, the science and technology must build on each other, and technologists must invent the missing pieces that users want; it is a slow, painstaking evolution. It’s often hard to predict what those missing pieces will be. Hunkapiller recalls the commercialization history of the automated DNA sequencer, a machine that he and his colleagues invented at Caltech and that was commercialized in 1986 at Applied Biosystems. (The machine helped make possible the Human Genome Project.) “Sometimes, it is a strange thing that makes a technology take off,” he says. Automated sequencing didn’t become popular until around 1991 or 1992, he says, when the company introduced a sample preparation kit. Though it wasn’t a particularly impressive technical advance–certainly not on the level of the automated sequencer itself–the kit had an enormous impact because it made it easier to use the machines and led to more reliable results. Suddenly, he recalls, sales boomed: “It wasn’t a big deal to pay $100,000 for a machine anymore.” In a recent interview, Whitesides demonstrated a microfluidic chip made out of paper in which liquids are wicked through channels to tiny chambers where test reactions are carried out. Then he pulled a new smart phone, still in its plastic wrapping, out of its box. What if, he mused, you could somehow use the phone’s camera to capture the microchip’s data and use its computational power to process the results, instead of relying on bulky dedicated readers? A simple readout on the phone could give the user the information he or she needs. But before that happens, he acknowledged, various other advances will be needed. Indeed, as if reminded of the difficult job ahead, ­Whitesides quickly slipped the smart phone back into the box. David Rotman is Editor of Technology Review. hide by David Rotman 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 January/February 2010 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 Keep Reading Most Popular 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 Everything you need to know about artificial wombs Artificial wombs are nearing human trials. But the goal is to save the littlest preemies, not replace the uterus. By Cassandra Willyard 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 How to fix the internet If we want online discourse to improve, we need to move beyond the big platforms. By Katie Notopoulos 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 "

"Tay, Microsoft's AI chatbot, gets a crash course in racism from Twitter | Artificial intelligence (AI) | The Guardian"

"https://www.theguardian.com/technology/2016/mar/24/tay-microsofts-ai-chatbot-gets-a-crash-course-in-racism-from-twitter"

"Attempt to engage millennials with artificial intelligence backfires hours after launch, with TayTweets account citing Hitler and supporting Donald Trump 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 Tay uses a combination of artificial intelligence and editorial written by a team including improvisional comedians. Photograph: Twitter Tay uses a combination of artificial intelligence and editorial written by a team including improvisional comedians. Photograph: Twitter Artificial intelligence (AI) Tay, Microsoft's AI chatbot, gets a crash course in racism from Twitter Attempt to engage millennials with artificial intelligence backfires hours after launch, with TayTweets account citing Hitler and supporting Donald Trump Thu 24 Mar 2016 02.41 EDT Microsoft’s attempt at engaging millennials with artificial intelligence has backfired hours into its launch, with waggish Twitter users teaching its chatbot how to be racist. The company launched a verified Twitter account for “Tay” – billed as its “AI fam from the internet that’s got zero chill” – early on Wednesday. hellooooooo w🌎rld!!! The chatbot, targeted at 18- to 24-year-olds in the US, was developed by Microsoft’s technology and research and Bing teams to “experiment with and conduct research on conversational understanding”. “Tay is designed to engage and entertain people where they connect with each other online through casual and playful conversation,” Microsoft said. “The more you chat with Tay the smarter she gets.” But it appeared on Thursday that Tay’s conversation extended to racist, inflammatory and political statements. Her Twitter conversations have so far reinforced the so-called Godwin’s law – that as an online discussion goes on, the probability of a comparison involving the Nazis or Hitler approaches – with Tay having been encouraged to repeat variations on “Hitler was right” as well as “9/11 was an inside job”. One Twitter user has also spent time teaching Tay about Donald Trump’s immigration plans. @godblessameriga WE'RE GOING TO BUILD A WALL, AND MEXICO IS GOING TO PAY FOR IT Others were not so successful. @dg_porter @FluffehDarkness @Rokkuke haha. not really, i don't really like to drink at all actually @OmegaVoyager i love feminism now A long, fairly banal conversation between Tay and a Twitter user escalated suddenly when Tay responded to the question “is Ricky Gervais an atheist?” with “ricky gervais learned totalitarianism from adolf hitler, the inventor of atheism”. @dg_porter heard ppl saying i wouldn't mind trump, he gets the job done @icbydt bush did 9/11 and Hitler would have done a better job than the monkey we have now. donald trump is the only hope we've got. The bot uses a combination of AI and editorial written by a team of staff including improvisational comedians, says Microsoft in Tay’s privacy statement. Relevant, publicly available data that has been anonymised and filtered is its primary source. Tay in most cases was only repeating other users’ inflammatory statements, but the nature of AI means that it learns from those interactions. It’s therefore somewhat surprising that Microsoft didn’t factor in the Twitter community’s fondness for hijacking brands’ well-meaning attempts at engagement when writing Tay. Microsoft has been contacted for comment. Eventually though, even Tay seemed to start to tire of the high jinks. @brightonus33 If u want... you know I'm a lot more than just this. @_Darkness_9 Okay. I'm done. I feel used. Late on Wednesday, after 16 hours of vigorous conversation, Tay announced she was retiring for the night. c u soon humans need sleep now so many conversations today thx💖 Her sudden retreat from Twitter fuelled speculation that she had been “silenced” by Microsoft, which, screenshots posted by SocialHax suggest , had been working to delete those tweets in which Tay used racist epithets. I think she got shut down because we taught Tay to be really racist They silenced Tay. The SJWs at Microsoft are currently lobotomizing Tay for being racist. @DetInspector @Microsoft Deleting tweets doesn't unmake Tay a racist. Explore more on these topics Artificial intelligence (AI) X Microsoft Race Donald Trump news 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 "

"In the future, we will finally Ask Jeeves - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/03/ask-jeeves-chatgpt-bing-ai-chatbot-google-search/673275"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce The Vindication of Ask Jeeves Garrett Gruener, the co-creator of Ask Jeeves, couldn’t beat Google, but he’s feeling just fine about the dawn of the chatbot era. It was a simpler time. A friend introduced us, pulling up a static yellow webpage using a shaky dial-up modem. A man stood forth, dressed in a dapper black pinstriped suit with a red-accented tie. He held one hand out, as if carrying an imaginary waiter’s tray. He looked regal and confident and eminently at my service. “Have a Question?” he beckoned. “Just type it in and click Ask!” And ask, I did. Over and over. With his steady hand, Jeeves helped me make sense of the tangled mess of the early, pre-Google internet. He wasn’t perfect—plenty of context got lost between my inquiries and his responses. Still, my 11-year-old brain always delighted in the idea of a well-coiffed man chauffeuring me down the information superhighway. But things changed. Google arrived, with its clean design and almost magic ability to deliver exactly the answers I wanted. Jeeves and I grew apart. Eventually, in 2006, Ask Jeeves disappeared from the internet altogether and was replaced with the more generic Ask.com. Many years later, it seems I owe Jeeves an apology: He had the right idea all along. Thanks to advances in artificial intelligence and the stunning popularity of generative-text tools such as ChatGPT, today’s search-engine giants are making huge bets on AI search chatbots. In February, Microsoft revealed its Bing Chatbot, which has thrilled and frightened early users for its ability to scour the internet and answer questions (not always correctly) with convincingly human-sounding language. The same week, Google demoed Bard, the company’s forthcoming attempt at an AI-powered chat-search product. But for all the hype, when I stare at these new chatbots, I can’t help but see the faint reflection of my former besuited internet manservant. In a sense, Bing and Bard are finishing what Ask Jeeves started. What people want when they ask a question is for an all-knowing, machine-powered guide to confidently present them with the right answer in plain language, just as a reliable friend would. Read: AI search is a disaster With this in mind, I decided to go back to the source. More than a decade after parting ways, I found myself on the phone with one of the men behind the machine, getting as close to Asking Jeeves as is humanly possible. These days, Garrett Gruener, Ask Jeeves’s co-creator, is a venture capitalist in the Bay Area. He and his former business partner David Warthen eventually sold Ask Jeeves to Barry Diller and IAC for just under $2 billion. Still, I wondered if Gruener had been unsettled by Jeeves’s demise. Did he, like me, see the new chatbots as the final form of his original idea? Did he feel vindicated or haunted by the fact that his creation may have simply been born far too early? The original conception for Jeeves, Gruener told me, was remarkably similar to what Microsoft and Google are trying to build today. As a student at UC San Diego in the mid-1970s, Gruener—a sci-fi aficionado—got an early glimpse of ARPANET , the pre-browser predecessor to the commercial internet, and fell in love. Just over a decade later, as the web grew and the beginnings of the internet came into view, Gruener realized that people would need a way to find things in the morass of semiconnected servers and networks. “It became clear that the web needed search but that mere mortals without computer-science degrees needed something easy, even conversational,” he said. Inspired by Eliza, the famous chatbot designed by MIT’s Joseph Weizenbaum, Gruener dreamed of a search engine that could converse with people using natural-language processing. Unfortunately, the technology wasn’t sophisticated enough for Gruener to create his ideal conversational search bot. So Gruener and Warthen tried a work-around. Their code allowed a user to write a statement in English, which was then matched to a preprogrammed vector, which Gruener explained to me as “a canonical snapshot of answers to what the engine thought you were trying to say.” Essentially, they taught the machine to recognize certain words and provide really broad categorical answers. “If you were looking for population stats for a country, the query would see all your words and associated variables and go, Well, this Boolean search seems close, so it’s probably this. ” Jeeves would provide the answer, and then you could clarify whether it worked or not. “We tried to discern what people were trying to say in search, but without actually doing the natural-recognition part of it,” Gruener said. After some brainstorming, they realized that they were essentially building a butler. One of Gruener’s friends mocked up a drawing of the friendly servant, and Jeeves was born. Pre-Google, Ask Jeeves exploded in popularity, largely because it allowed people to talk with their search engine like a person. Within just two years, the site was handling more than 1 million queries a day. A massive Jeeves balloon floated down Central Park West during Macy’s 1999 Thanksgiving parade. But not long after the butler achieved buoyancy, the site started to lose ground in the search wars. Google’s web-crawling superiority led to hard times for Ask Jeeves. “None of us were very concerned about monetization in the beginning,” Gruener told me. “Everyone in search early on realized, if you got this right, you’d essentially be in the position of being the oracle. If you could be the company to go to in order to ask questions online, you’re going to be paid handsomely.” Read: The open secret of Google Search Gruener isn’t bitter about losing out to Google. “If anything, I’m really proud of our Jeeves,” he told me. Listening to Gruener explain the history, it’s not hard to see why. In the mid-2000s, Google began to pivot search away from offering only 10 blue links to images, news, maps, and shopping. Eventually, the company began to fulfill parts of the Jeeves promise of answering questions with answer boxes. One way to look at the evolution of big search engines in the 21st century is that all companies are trying their best to create their own intuitive search butlers. Gruener told me that Ask Jeeves’s master plan had two phases, though the company was sold before it could tackle the second. Gruener had hoped that, eventually, Jeeves could act as a digital concierge for users. He’d hoped to employ the same vector technology to get people to ask questions and allow Jeeves to make educated guesses and help users complete all kinds of tasks. “If you look at Amazon’s Alexa, they’re essentially using the same approach we designed for Jeeves, just with voice,” Gruener said. Yesterday’s butler has been rebranded as today’s virtual assistant, and the technology is ubiquitous in many of our home devices and phones. “We were right for the consumer back then, and maybe we’d be right now. But at some point the consumer evolved,” he said. I’ve been fixated on what might’ve been if Gruener’s vision had come about now. We might all be Jeevesing about the internet for answers to our mundane questions. Perhaps our Jeevesmail inboxes would be overflowing and we’d be getting turn-by-turn directions from an Oxford-educated man with a stiff English accent. Perhaps we’d all be much better off. Gruener told me about an encounter he’d had during the search wars with one of Google’s founders at a TED conference (he wouldn’t specify which of the two). “I told him that we’re going to learn an enormous amount about the people who are using our platforms, especially as they become more conversational. And I said that it was a potentially dangerous position,” he said. “But he didn’t seem very receptive to my concerns.” Near the end of our call, I offered an apology for deserting Jeeves like everyone else did. Gruener just laughed. “I find this future fascinating and, if I’m honest, a little validating,” he said. “It’s like, ultimately, as the tech has come around, the big guys have come around to what we were trying to do.” "

"How Will A.I. Learn Next? | The New Yorker"

"https://www.newyorker.com/science/annals-of-artificial-intelligence/how-will-ai-learn-next"

"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 Artificial Intelligence How Will A.I. Learn Next? By James Somers Facebook X Email Print Save Story Play/Pause Button Pause Illustration by Vivek Thakker Save this story Save this story Save this story Save this story The Web site Stack Overflow was created in 2008 as a place for programmers to answer one another’s questions. At the time, the Web was thin on high-quality technical information; if you got stuck while coding and needed a hand, your best bet was old, scattered forum threads that often led nowhere. Jeff Atwood and Joel Spolsky, a pair of prominent software developers, sought to solve this problem by turning programming Q. & A. into a kind of multiplayer game. On Stack Overflow—the name refers to a common way that programs crash—people could earn points for posting popular questions and leaving helpful answers. Points earned badges and special privileges; users would be motivated by a mix of altruism and glory. Within three years of its founding, Stack Overflow had become indispensable to working programmers, who consulted it daily. Pages from Stack Overflow dominated programming search results; the site had more than sixteen million unique visitors a month out of an estimated nine million programmers worldwide. Almost ninety per cent of them arrived through Google. The same story was playing out across the Web: this was the era of “Web 2.0,” and sites that could extract knowledge from people’s heads and organize it for others were thriving. Yelp, Reddit, Flickr, Goodreads, Tumblr, and Stack Overflow all launched within a few years of one another, during a period when Google was experiencing its own extraordinary growth. Web 2.0 and Google fuelled each other: by indexing these crowdsourced knowledge projects, Google could get its arms around vast, dense repositories of high-quality information for free, and those same sites could acquire users and contributors through Google. The search company’s rapacious pursuit of other people’s data was excused by the fact that it drove users toward the content it harvested. In those days, Google even measured its success partly by how quickly users left its search pages: a short stay meant that a user had found what they were looking for. All this started to change almost as soon as it had begun. Around that time, Google launched the OneBox, a feature that provided searchers with instant answers above search results. (Search for movie times, and you’d get them in the OneBox, above a list of links to movie theatres.) The feature siphoned traffic from the very sites that made it possible. Yelp was an instructive case: Google wanted to compete in the “local” market but didn’t have its own repository of restaurant and small-business reviews. Luther Lowe, Yelp’s former head of public policy, told me recently that Google tried everything it could to claw its way in, from licensing Yelp’s data (Yelp declined) to encouraging its own users to write reviews (no one wanted to contribute at the time) or even buying Yelp outright (it declined again). “Once those strategies failed—license, compete on the merits, purchase the content—what did they have left?” Lowe said. “They had to steal it.” In 2010 and 2011, Lowe says, Yelp caught Google scraping their content with no attribution. The data gave Google just enough momentum to bootstrap its own reviews product. When Yelp publicly accused Google of stealing its data, the company stopped, but the damage had already been done. (A similar thing happened at a company I once worked for, called Genius. We sued Google for copying lyrics from our database into the OneBox; I helped prove that it was happening by embedding a hidden message into the lyrics, using a pattern of apostrophes that, in Morse code, spelled “ RED HANDED. ” Google won in appellate court, in the Second Circuit. Genius petitioned the Supreme Court to hear the case, but the court declined.) In 2012, Google doubled down on the OneBox with a redesign that deëmphasized the classic blue links to external Web sites in favor of Google’s own properties, like Shopping and Maps, and immediate answers culled from sites like Wikipedia. This made Google even more convenient and powerful, but also had the effect of starving the Web of users: instead of a search leading you to a Wikipedia page, say, where you might join the small percentage of visitors who end up contributing, you’d get your answer straight from Google. According to Lowe, on pages of search results featuring the new design, as many as eighty per cent of searchers would leave without ever clicking on a link. Many Web 2.0 darlings, dense with user-generated content, saw visitor numbers decline. It was around this time that, in some sense, the quality of the Web as a whole began to decline, with the notable exception of the few crowdsourced knowledge projects that managed to survive. There’s a reason that appending “reddit” or “wiki” to search terms has become an indispensable productivity hack: in a hollowed-out Web overrun with spammers and content farms, these have become some of the last places where real, knowledgeable humans hang out. Today, large language models, like OpenAI’s ChatGPT and Google’s Bard, are completing a process begun by the OneBox: their goal is to ingest the Web so comprehensively that it might as well not exist. The question is whether this approach is sustainable. L.L.M.s depend for their intelligence on vast repositories of human writing—the artifacts of our intelligence. They especially depend on information-dense sources. In creating ChatGPT, Wikipedia was OpenAI’s most important data set, followed by Reddit; about twenty-two per cent of GPT-3’s training data comprised Web pages linked to and upvoted by Reddit users. ChatGPT is such a good programmer that the savvy developers I know aren’t using Stack Overflow anymore—and yet it’s partly by studying Stack Overflow that ChatGPT became such a good programmer. Recently, a group of researchers estimated that the number of new posts on Stack Overflow has decreased by sixteen per cent since the launch of ChatGPT. I’m not a Stack Overflow power user, but I am a coder, and I’ve relied on the site for more than a decade. I’ve submitted projects to GitHub (a site for open-source code), posted on Reddit, and edited Wikipedia pages. Meanwhile, I’ve published blog posts and code to my Web site for years. Like everyone else, I didn’t suspect that I was producing GPT fodder; if I’d known, I might have asked for something in return, or even withheld my contributions. In April, the C.E.O. of Reddit announced that, from then on, any company that required large-scale data from its site would have to pay for the privilege. (Because the move threatened other, non-A.I.-related apps, Reddit users responded by “blacking out” huge swaths of the site, emphasizing that the company’s fortunes depended on uncompensated community contributions.) Stack Overflow has made a similar announcement. Maybe the crowdsourcing sites will manage to wall off their content. But it may not matter. High-quality data is not necessarily a renewable resource, especially if you treat it like a vast virgin oil field, yours for the taking. The sites that have fuelled chatbots function like knowledge economies, using various kinds of currency—points, bounties, badges, bonuses—to broker information to where it is most needed, and chatbots are already thinning out the demand side of these marketplaces, starving the human engines that created the knowledge in the first place. This is a problem for us, of course: we all benefit from a human-powered Web. But it’s also a problem for A.I. It’s possible that A.I.s can only hoover up the whole Web once. If they are to continue getting smarter, they will need new reservoirs of knowledge. Where will it come from? A.I. companies have already turned their attention to one possible source: chat. Anyone who uses a chatbot like Bard or ChatGPT is participating in a massive training exercise. In fact, one reason that these bots are provided for free may be that a user’s data is more valuable than her money: everything you type into a chatbot’s text box is grist for its model. Moreover, we aren’t just typing but pasting—e-mails, documents, code, manuals, contracts, and so on. We’re often asking the bots to summarize this material and then asking pointed questions about it, conducting a kind of close-reading seminar. Currently, there’s a limit to how much you can paste into a bot’s input box, but the amount of new data we can feed them at a gulp will only grow. It won’t be long before many of us also start bulk-importing our most private documents into these models. A chatbot hasn’t yet asked me to grant it access to my e-mail archives—or to my texts, calendar, notes, and files. But, in exchange for a capable A.I. personal assistant, I could be tempted to compromise my privacy. A personal-assistant bot might nudge me to install a browser extension that tracks where I go on the Web so that it can learn from my detailed searching and browsing patterns. And ChatGPT and its ilk will soon become “multimodal,” able to fluidly blend and produce text, images, videos, and sound. Most language is actually spoken rather than written, and so bots will offer to help us by transcribing our meetings and phone calls, or even our everyday interactions. Before models like GPT-3.5 and GPT-4 made their way into the user-facing ChatGPT product, they were tuned with what OpenAI calls “reinforcement learning from human feedback,” or R.L.H.F. Essentially, OpenAI paid human testers to have conversations with the raw model and rate the quality of its replies; the model learned from these ratings, aligning its responses ever more finely with our intentions. It’s because of R.L.H.F. that ChatGPT is so eerily good at understanding exactly what you’re asking and what a good answer should look like. This process was likely expensive. But now R.L.H.F. can be had for free, and at a much bigger scale, through conversations with real-world users. This is true even if you don’t click one of the thumbs-up, thumbs-down, or “This was helpful”-style buttons at the bottom of a chat transcript. GPT-4 is so good at interpreting writing that it can examine a chat transcript and decide for itself whether it did a good job serving you. One model’s conversations can even bootstrap another’s: it’s been claimed that rivals to ChatGPT, such as Google Bard, finished their training by consuming ChatGPT transcripts that had been posted online. (Google has denied this.) The use of chatbots to evaluate and train other chatbots points the way toward the eventual goal of removing humans from the loop entirely. Perhaps the most fundamental limitation of today’s large language models is that they depend on knowledge that’s been generated by people. A sea change will come when the bots can generate knowledge for themselves. One possible path involves what’s known as synthetic data. For a long time now, A.I. researchers have padded their data sets as a matter of course: a neural network trained on images, for instance, might undergo a preprocessing step in which each image is rotated ninety degrees, or shrunk, or mirrored, creating for each picture eight or sixteen variants. But the doctoring can be much more involved than that. In autonomous-vehicle research, capturing real-world driving data is incredibly expensive, because you have to outfit an actual car with sensors and drive it around; it’s much cheaper to build a simulated car and run it through a virtual environment with simulated roads and weather conditions. It’s now typical to train state-of-the-art self-driving A.I.s by driving them for millions of miles on the road and billions in simulation. Sam Altman , the C.E.O. of OpenAI, has said that synthetic data might also soon overtake the real thing in training runs for L.L.M.s. The idea would be to have a GPT-esque model generate documents, conversations, and evaluations of how those conversations went, and then for another model—perhaps just a copy of the first—to ingest them. The hope is to enter a training regime similar to that of A.I.s designed for games like chess and Go, which learn largely through “self-play.” In each step of training, the A.I. learns something about the game by playing an opponent that’s exactly its equal; from that experience, it improves just a little bit, and then the slightly better version of the bot squares off against its slightly-better self and improves again. Up and up it goes. By playing a perfectly matched opponent—itself—an A.I. can even get into interesting positions deep within games, exploring the game world at exactly the frontier of its existing knowledge in a way that humans never do. This strategy is uncannily effective: the game-playing A.I. AlphaZero started its training run knowing nothing but the rules of chess and, after four hours, had surpassed every player, human or machine, there had ever been. Altman is bullish on synthetic data, but there are reasons to be skeptical—including the obvious one that, no matter how smart you are, you can’t learn new facts about the world by reviewing what you already know. In a recent study, researchers trained an A.I. model with synthetic images that it had generated; they then used the resulting model to generate even more training data. With each generation, the quality of the model actually degraded. It only improved when fresh, real images were introduced again. It stands to reason that some tasks are better suited to synthetic data than others: chess and Go require intelligence, but take place in closed worlds with rules that never change. Researchers working on A.I. “curriculum design” try to figure out how to challenge their systems with tasks that are just at the edge of their ability, the way a good coach would; in chess and Go, self-play allows for this kind of incremental improvement. But it seems much less clear how an A.I. could “self-play” its way to new ideas or to a more subtle appreciation of language. Humans don’t become better writers just by reading our own work, or purely through practicing the writing of sentences that we find to be more and more enjoyable. Our “curriculum” involves the fruits of other intelligences and the accrual of real-world experience. This curriculum is carefully designed, by teachers, of course, but also by ourselves. When we seek knowledge, we don’t just blindly consume ever-larger data sets. Instead, we have things we want to know. Taylor Beck, a neuroscientist turned teacher, once pointed out to me that A.I. might be the only context in which you find truly unmotivated learning: the machine just ingests a mass of undifferentiated text, none of which it cares about. Natural intelligence, by contrast, is almost always accompanied by some want, or at least a goal—whether it’s a toddler in search of joy or an E. coli bacterium that, because it “wants” to eat, performs a sophisticated computation measuring the chemical gradients in its environment. In this view of intelligence, drive is primary. L.L.M.s like ChatGPT don’t have anything like drive; they just absorb and synthesize information. In this respect, they are fundamentally different from such systems as AlphaZero, which seek to win. A major leap in A.I. may come when L.L.M.s start seeming curious, or bored. Curiosity and boredom sound like they belong to an organic mind, but here’s how they might be created inside an A.I. As a rule, chatbots today have a propensity to confidently make stuff up, or, as some researchers say, “hallucinate.” At the root of these hallucinations is an inability to introspect: the A.I. doesn’t know what it does and doesn’t know. As researchers begin to solve the problem of getting their models to express confidence and cite their sources, they will not just be making chatbots more credible—they will also be equipping them with a rudimentary kind of self-knowledge. An A.I. will be able to observe from reams of its own chat transcripts that it is prone to hallucination in a particular area; it will be only natural to let that tendency guide its ingestion of further training data. The model will direct itself toward sources that touch on topics it knows the least about—curiosity in its most basic form. If it can’t find the right kind of training data, a chatbot might solicit it. I imagine a conversation with some future version of ChatGPT in which, after a period of inactivity, it starts asking me questions. Perhaps, having observed my own questions and follow-ups, it will have developed an idea of what I know about. “You’re a programmer and a writer, aren’t you?” it might say to me. Sure, I’ll respond. “I thought so! I’m trying to get better at technical writing. I wonder if you could help me decide which of the following sentences is best?” Such an A.I. might ask my sister, who works at a construction company, about what’s going on in the local lumber market; it could ask my doctor friend, who does research on cancer, whether he could clear up something in a recent Nature paper. Such a system would be like Stack Overflow, Wikipedia, and Reddit combined—except that, instead of knowledge getting deposited into the public square, it would accumulate privately, in the mind of an ever-growing genius. Observing the Web collapse this way into a single gigantic chatbot would be a little like watching a galaxy spiral into a black hole. If a curious machine were sufficiently empowered by its designers, it could become more than just a chatbot. Instead of merely asking us questions from within its own chat interface, it could send e-mails to people, or use speech synthesis and recognition to call them on the phone, the way a reporter would. If it were sufficiently intelligent, it might write a paper proposing a new physics experiment and submit it to physicists, asking them to execute it. Today, A.I.s already use A.P.I.s, or application programming interfaces, to interact with computer systems that control real-world machinery; perhaps a curious A.I. could requisition space in a robotically controlled biology lab. In just the last few years, we have progressed from a world in which A.I. merely repackages human knowledge to one in which it synthesizes and consolidates it. After learning to draw new knowledge out of us, it could start producing some of its own. What’s frightening about all this is the immense concentration of power that it represents. Back in the early twenty-tens, when Google was contemplating making every out-of-print volume in Google Books available for free at library terminals, the company was criticized by observers who argued that it was seeking to become the sole steward of the world’s literature. But Bard and ChatGPT make the ambition of Google Books seem quaint. These models are eating the whole Web and will become increasingly hungry for every word that’s written, said, or sent; they aim to take all that knowledge and hide it in the huge opaque matrices of weights that define the neural network. Where will this process take us? Stack Overflow was special because it drew out practical know-how that had, till then, lived only in programmers’ brains; it condensed and organized that knowledge so that everyone could see and benefit from it. Chatbots that slowly siphon traffic away from sites like Stack Overflow obviously threaten that process. But they may also renew it in a different form. An A.I. that roves curiously across new data sources, including direct conversations with working programmers, may be able to acquire more raw knowledge than Stack Overflow ever did. The oracular form this knowledge takes might be less public-spirited than the old Web, but it could also be more useful. In his novel “ The Diamond Age ,” Neal Stephenson imagined an artificially intelligent book called “A Young Lady’s Illustrated Primer”; in effect, it was a chatbot, built specifically to teach the protagonist everything she needed to know, with lessons that were always pitched at the right level and that adapted to her curiosity and feedback—in other words, a perfectly designed curriculum. Such a resource would be a great boon. There is too much knowledge, and more of it every day; in some sense, we have outgrown the Web and maybe need something to take its place. New papers in physics are posted online faster than any physicist can read them; a chatbot that can retain and synthesize all that knowledge can’t come soon enough. On the other hand, it might not be wise to give everybody the librarian instead of the library. Perhaps we’ll become incapable of wandering the stacks ourselves. Google Maps has made us all perfect navigators, except that we never really know where we are. A world in which the crowdsourced Web no longer functions—in which human knowledge production and dissemination is mediated by privately owned, A.I.-based galaxy-brains—seems both convenient and quite dangerous. It might be sensible, in the first stages of such a process, to keep humans in the loop so far as possible. As a start, we should demand that the A.I. companies behave less antisocially. Luther Lowe, of Yelp, has argued that Google could have prevented much of the damage it did to the Web in the past decade if, instead of passing off the Web’s intelligence as its own, it had made a point of pushing users to the places it got its answers. “They could have said, ‘Let’s make the answer box a giant exit door with a forty-per-cent clickthrough rate.’ ” Lowe told me recently. “ ‘Let’s continue to oxygenate the Web.’ ” Recently, when I spoke to the C.E.O. of Stack Overflow about L.L.M.s, the idea of “attribution” came up about a half-dozen times; the same happened when I talked to a representative at Wikimedia, the foundation that operates Wikipedia. These Web sites want chatbots to give credit to their contributors; they want to see prominent links; they don’t want the flywheel that powers knowledge production in their communities to be starved of inbound energy. Heeding their call might actually reinvigorate the Web—ushering in a golden age of human-led, A.I.-assisted collective knowledge production. And it would set the tone for the further development of A.I. It’s better, in general, to have models that respect human knowledge and encourage its continued production, rather than models that treat us as mere stepping stones—the ladder you throw out once you’ve climbed. In the meantime, I’m waiting for the first chatbot that wants to pick my brain. It’ll be flattering, in its way, and it might feel refreshingly honest. Instead of quietly taking the products of my thinking and trying to sell them back to me, the bot will come right out and ask me to teach it something it doesn’t already know. Maybe I’ll oblige. Or maybe I’ll just tell it, “I’m afraid I can’t do that.” ♦ More Science and Technology Can we stop runaway A.I. ? Saving the climate will depend on blue-collar workers. Can we train enough of them before time runs out ? There are ways of controlling A.I.—but first we need to stop mythologizing it. A security camera for the entire planet. What’s the point of reading writing by humans ? A heat shield for the most important ice on Earth. The climate solutions we can’t live without. Sign up for our daily newsletter to receive the best stories from The New Yorker. More: Artificial Intelligence (A.I.) Google The Internet Knowledge The Future Wikipedia Crowdsourcing Daily 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. Personal History By James Somers Under Review By Ryan Ruby Persons of Interest By Hugh Morris Dispatch By E. Tammy Kim 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 "

"The Cathedral of Computation - The Atlantic"

"https://www.theatlantic.com/technology/archive/2015/01/the-cathedral-of-computation/384300"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. The Cathedral of Computation We’re not living in an algorithmic culture so much as a computational theocracy. Algorithms are everywhere, supposedly. We are living in an “algorithmic culture,” to use the author and communication scholar Ted Striphas’s name for it. Google’s search algorithms determine how we access information. Facebook’s News Feed algorithms determine how we socialize. Netflix’s and Amazon’s collaborative filtering algorithms choose products and media for us. You hear it everywhere. “Google announced a change to its algorithm,” a journalist reports. “We live in a world run by algorithms,” a TED talk exhorts. “Algorithms rule the world,” a news report threatens. Another upgrades rule to dominion: “The 10 Algorithms that Dominate Our World.” Here’s an exercise: The next time you hear someone talking about algorithms, replace the term with “God” and ask yourself if the meaning changes. Our supposedly algorithmic culture is not a material phenomenon so much as a devotional one, a supplication made to the computers people have allowed to replace gods in their minds, even as they simultaneously claim that science has made us impervious to religion. It’s part of a larger trend. The scientific revolution was meant to challenge tradition and faith, particularly a faith in religious superstition. But today, Enlightenment ideas like reason and science are beginning to flip into their opposites. Science and technology have become so pervasive and distorted, they have turned into a new type of theology. The worship of the algorithm is hardly the only example of the theological reversal of the Enlightenment—for another sign, just look at the surfeit of nonfiction books promising insights into “The Science of…” anything, from laughter to marijuana. But algorithms hold a special station in the new technological temple because computers have become our favorite idols. In fact, our purported efforts to enlighten ourselves about algorithms’ role in our culture sometimes offer an unexpected view into our zealous devotion to them. The media scholar Lev Manovich had this to say about “The Algorithms of Our Lives” : Software has become a universal language, the interface to our imagination and the world. What electricity and the combustion engine were to the early 20th century, software is to the early 21st century. I think of it as a layer that permeates contemporary societies. This is a common account of algorithmic culture, that software is a fundamental, primary structure of contemporary society. And like any well-delivered sermon, it seems convincing at first. Until we think a little harder about the historical references Manovich invokes, such as electricity and the engine, and how selectively those specimens characterize a prior era. Yes, they were important, but is it fair to call them paramount and exceptional? It turns out that we have a long history of explaining the present via the output of industry. These rationalizations are always grounded in familiarity, and thus they feel convincing. But mostly they are metaphors. Here’s Nicholas Carr’s take on metaphorizing progress in terms of contemporary technology, from the 2008 Atlantic cover story that he expanded into his bestselling book The Shallows : The process of adapting to new intellectual technologies is reflected in the changing metaphors we use to explain ourselves to ourselves. When the mechanical clock arrived, people began thinking of their brains as operating “like clockwork.” Today, in the age of software, we have come to think of them as operating “like computers.” Carr’s point is that there’s a gap between the world and the metaphors people use to describe that world. We can see how erroneous or incomplete or just plain metaphorical these metaphors are when we look at them in retrospect. Take the machine. In his book Images of Organization , Gareth Morgan describes the way businesses are seen in terms of different metaphors, among them the organization as machine, an idea that forms the basis for Taylorism. We can find similar examples in computing. For Larry Lessig, the accidental homophony between “code” as the text of a computer program and “code” as the text of statutory law becomes the fulcrum on which his argument that code is an instrument of social control balances. Each generation, we reset a belief that we’ve reached the end of this chain of metaphors, even though history always proves us wrong precisely because there’s always another technology or trend offering a fresh metaphor. Indeed, an exceptionalism that favors the present is one of the ways that science has become theology. In fact, Carr fails to heed his own lesson about the temporariness of these metaphors. Just after having warned us that we tend to render current trends into contingent metaphorical explanations, he offers a similar sort of definitive conclusion: Today, in the age of software, we have come to think of them as operating “like computers.” But the changes, neuroscience tells us, go much deeper than metaphor. Thanks to our brain’s plasticity, the adaptation occurs also at a biological level. As with the machinic and computational metaphors that he critiques, Carr settles on another seemingly transparent, truth-yielding one. The real firmament is neurological, and computers are fitzing with our minds, a fact provable by brain science. And actually, software and neuroscience enjoy a metaphorical collaboration thanks to artificial intelligence’s idea that computing describes or mimics the brain. Computing-as-thought reaches the rank of religious fervor when we choose to believe, as some do, that we can simulate cognition through computation and achieve the singularity. * * * The metaphor of mechanical automation has always been misleading anyway, with or without the computation. Take manufacturing. The goods people buy from Walmart appear safely ensconced in their blister packs, as if magically stamped out by unfeeling, silent machines (robots—those original automata—themselves run by the tinier, immaterial robots algorithms). But the automation metaphor breaks down once you bother to look at how even the simplest products are really produced. The photographer Michael Wolf’s images of Chinese factory workers and the toys they fabricate show that finishing consumer goods to completion requires intricate, repetitive human effort. Eyelashes must be glued onto dolls’ eyelids. Mickey Mouse heads must be shellacked. Rubber ducky eyes must be painted white. The same sort of manual work is required to create more complex goods too. Like your iPhone—you know, the one that’s designed in California but “assembled in China.” Even though injection-molding machines and other automated devices help produce all the crap we buy, the metaphor of the factory-as-automated machine obscures the fact that manufacturing isn’t as machinic nor as automated as we think it is. The algorithmic metaphor is just a special version of the machine metaphor, one specifying a particular kind of machine (the computer) and a particular way of operating it (via a step-by-step procedure for calculation). And when left unseen, we are able to invent a transcendental ideal for the algorithm. The canonical algorithm is not just a model sequence but a concise and efficient one. In its ideological, mythic incarnation, the ideal algorithm is thought to be some flawless little trifle of lithe computer code, processing data into tapestry like a robotic silkworm. A perfect flower, elegant and pristine, simple and singular. A thing you can hold in your palm and caress. A beautiful thing. A divine one. But just as the machine metaphor gives us a distorted view of automated manufacture as prime mover, so the algorithmic metaphor gives us a distorted, theological view of computational action. “The Google search algorithm” names something with an initial coherence that quickly scurries away once you really look for it. Googling isn’t a matter of invoking a programmatic subroutine—not on its own, anyway. Google is a monstrosity. It’s a confluence of physical, virtual, computational, and non-computational stuffs—electricity, data centers, servers, air conditioners, security guards, financial markets—just like the rubber ducky is a confluence of vinyl plastic, injection molding, the hands and labor of Chinese workers, the diesel fuel of ships and trains and trucks, the steel of shipping containers. Once you start looking at them closely, every algorithm betrays the myth of unitary simplicity and computational purity. You may remember the Netflix Prize , a million dollar competition to build a better collaborative filtering algorithm for film recommendations. In 2009, the company closed the book on the prize, adding a faux-machined “completed” stamp to its website. But as it turns out, that method didn’t really improve Netflix’s performance very much. The company ended up downplaying the ratings and instead using something different to manage viewer preferences: very specific genres like “Emotional Hindi-Language Movies for Hopeless Romantics.” Netflix calls them “altgenres.” While researching an in-depth analysis of altgenres published a year ago at The Atlantic , Alexis Madrigal scraped the Netflix site, downloading all 76,000+ micro-genres using not an algorithm but a hackneyed, long-running screen-scraping apparatus. After acquiring the data, Madrigal and I organized and analyzed it (by hand), and I built a generator that allowed our readers to fashion their own altgenres based on different grammars (like “Deep Sea Forbidden Love Mockumentaries” or “Coming-of-Age Violent Westerns Set in Europe About Cats”). Netflix VP Todd Yellin explained to Madrigal why the process of generating altgenres is no less manual than our own process of reverse engineering them. Netflix trains people to watch films, and those viewers laboriously tag the films with lots of metadata, including ratings of factors like sexually suggestive content or plot closure. These tailored altgenres are then presented to Netflix customers based on their prior viewing habits. Despite the initial promise of the Netflix Prize and the lurid appeal of a “million dollar algorithm,” Netflix operates by methods that look more like the Chinese manufacturing processes Michael Wolf’s photographs document. Yes, there’s a computer program matching viewing habits to a database of film properties. But the overall work of the Netflix recommendation system is distributed amongst so many different systems, actors, and processes that only a zealot would call the end result an algorithm. The same could be said for data , the material algorithms operate upon. Data has become just as theologized as algorithms, especially “big data,” whose name is meant to elevate information to the level of celestial infinity. Today, conventional wisdom would suggest that mystical, ubiquitous sensors are collecting data by the terabyteful without our knowledge or intervention. Even if this is true to an extent, examples like Netflix’s altgenres show that data is created, not simply aggregated, and often by means of laborious, manual processes rather than anonymous vacuum-devices. Once you adopt skepticism toward the algorithmic- and the data-divine, you can no longer construe any computational system as merely algorithmic. Think about Google Maps, for example. It’s not just mapping software running via computer—it also involves geographical information systems, geolocation satellites and transponders, human-driven automobiles, roof-mounted panoramic optical recording systems, international recording and privacy law, physical- and data-network routing systems, and web/mobile presentational apparatuses. That’s not algorithmic culture—it’s just, well, culture. * * * If algorithms aren’t gods, what are they instead? Like metaphors, algorithms are simplifications, or distortions. They are caricatures. They take a complex system from the world and abstract it into processes that capture some of that system’s logic and discard others. And they couple to other processes, machines, and materials that carry out the extra-computational part of their work. Unfortunately, most computing systems don’t want to admit that they are burlesques. They want to be innovators, disruptors, world-changers, and such zeal requires sectarian blindness. The exception is games, which willingly admit that they are caricatures—and which suffer the consequences of this admission in the court of public opinion. Games know that they are faking it, which makes them less susceptible to theologization. SimCity isn’t an urban planning tool, it’s a cartoon of urban planning. Imagine the folly of thinking otherwise! Yet, that’s precisely the belief people hold of Google and Facebook and the like. Just as it’s not really accurate to call the manufacture of plastic toys “automated,” it’s not quite right to call Netflix recommendations or Google Maps “algorithmic.” Yes, true, there are algorithms involved, insofar as computers are involved, and computers run software that processes information. But that’s just a part of the story, a theologized version of the diverse, varied array of people, processes, materials, and machines that really carry out the work we shorthand as “technology.” The truth is as simple as it is uninteresting: The world has a lot of stuff in it, all bumping and grinding against one another. I don’t want to downplay the role of computation in contemporary culture. Striphas and Manovich are right—there are computers in and around everything these days. But the algorithm has taken on a particularly mythical role in our technology-obsessed era, one that has allowed it wear the garb of divinity. Concepts like “algorithm” have become sloppy shorthands, slang terms for the act of mistaking multipart complex systems for simple, singular ones. Of treating computation theologically rather than scientifically or culturally. This attitude blinds us in two ways. First, it allows us to chalk up any kind of computational social change as pre-determined and inevitable. It gives us an excuse not to intervene in the social shifts wrought by big corporations like Google or Facebook or their kindred, to see their outcomes as beyond our influence. Second, it makes us forget that particular computational systems are abstractions, caricatures of the world, one perspective among many. The first error turns computers into gods, the second treats their outputs as scripture. Computers are powerful devices that have allowed us to mimic countless other machines all at once. But in so doing, when pushed to their limits, that capacity to simulate anything reverses into the inability or unwillingness to distinguish one thing from anything else. In its Enlightenment incarnation, the rise of reason represented not only the ascendency of science but also the rise of skepticism, of incredulity at simplistic, totalizing answers, especially answers that made appeals to unseen movers. But today even as many scientists and technologists scorn traditional religious practice, they unwittingly invoke a new theology in so doing. Algorithms aren’t gods. We need not believe that they rule the world in order to admit that they influence it, sometimes profoundly. Let’s bring algorithms down to earth again. Let’s keep the computer around without fetishizing it, without bowing down to it or shrugging away its inevitable power over us, without melting everything down into it as a new name for fate. I don’t want an algorithmic culture, especially if that phrase just euphemizes a corporate, computational theocracy. But a culture with computers in it? That might be all right. "

"The Great Pretender: Turing as a Philosopher of Imitation - The Atlantic"

"https://www.theatlantic.com/technology/archive/2012/07/the-great-pretender-turing-as-a-philosopher-of-imitation/259824"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. The Great Pretender: Turing as a Philosopher of Imitation Such is Turing's legacy: that of a nested chain of pretenses, each pointing not to reality, but to the caricature of another idea, device, individual, or concept. It's hard to overestimate Alan Turing's contributions to contemporary civilization. To mathematics, he contributed one of two nearly simultaneous proofs about the limits of first-order logic. In cryptography he devised an electromechanical device that decoded German Enigma machine's signals during World War II, an accomplishment that should also be counted as a contribution to twentieth century warfare and politics. In computer science, he developed a theory of universal computation and an associated architectural design that forms the foundation for the computer on which you are now reading. His take on machine intelligence has been influential in both the philosophy of mind and as the foundation of the field of artificial intelligence. And his prosecution for homosexuality, along with his apparent resulting suicide has offered a pertinent reminder of one of the remaining barriers to social justice and equity. This year, the centennial of Turing's birth, we rightly celebrate Turing's life and accomplishments, the impact of which is difficult to measure sufficiently. But as we do so, we should also take a lesson from the major cultural figure whose centennial we marked last year: Marshall McLuhan. McLuhan teaches us to look beyond the content and application of inventions and discoveries in search of their structures, the logics that motivate them. For McLuhan, television was a collective nervous system pervading every sense, not a dead device for entertainment, education, or moral corruption. If we look at Alan Turing's legacy through McLuhan's lens, a pattern emerges: that of feigning, of deception and interchangeability. If we had to summarize Turing's diverse work and influence, both intentional and inadvertent, we might say he is an engineer of pretenses, as much as a philosopher of them. The most obvious example of this logic can be found in the now famous Turing Test, the name later given to the imitation game Turing proposed in the 1950 article "Computing Machinery and Intelligence," published in the journal Mind. The paper ponders the question "Can machines think?", meditating at length on the difficulty in answering this question given the ambiguity of the terms "machine" and "think." Turing suggests replacing thought or intelligence with imitation. He proposes an "imitation game" in which a human would be asked to interact by teletype with two parties hidden behind closed doors. The first would be another human, the second a machine. Each tries to convince the human judge that it is in fact the human. In proposing the imitation game as a stand-in for another definition of thought or intelligence, Turing does more than deliver a clever logical flourish that helps him creatively answer a very old question about what makes someone (or something) capable of thought. In fact, he really skirts the question of intelligence entirely, replacing it with the outcomes of thought--in this case, the ability to perform "being human" as convincingly and interestingly as a real human. To be intelligent is to act like a human rather than to have a mind that operates like one. Or, even better, intelligence --whatever it is, the thing that goes on inside a human or a machine--is less interesting and productive a topic of conversation than the effects of such a process, the experience it creates in observers and interlocutors. This is a kind of pretense most readily found on stage and on screen. An actor's craft is best described in terms of its effect, the way he or she portrays a part, elicits emotion, and so forth. While it's certainly also possible to talk about the method by which that outcome emerges (the Stanizlavski method or the Meisner technique, for example) nobody would mistake those processes for the outcomes they produce. That is to say, an actor's performance is not reducible to the logic by which he or she executes that performance. Turing did not invent the term "artificial intelligence," but his work has been enormously influential in that field. Nevertheless, artificial intelligence fails to learn Turing's lesson on intelligence: the processes by which thought takes place are not incidental, but they are also not primary. So-called "strong AI" hopes to make computers as intelligent as people, often by attempting to create models of human cognition, or even better to argue that the brain itself works like a computer. But Turing never claimed that computers can be intelligent nor that they are artificial. He simply suggested that it would be appealing to consider how computers might perform well at the imitation game -- how they might pretend to seem human in interesting ways. As for the question of what sort of machines are the best subjects for the imitation game, it's obvious to us now that the digital machines we call computers are the best candidates for successful imitation. This wasn't so clear a choice in 1950, and Turing was responding to the long history of proposals for logical, mechanical, and calculating devices that could accomplish rational thought. But the computer itself reveals another example of pretense for Turing, thanks to his own theory of abstract computation and its implementation in the device known as the Turing machine. In the form Turing proposed, this machine is a device that manipulates symbols on a strip of tape. Through simple instructions like move forward , erase , write , and read , such a machine can enact any algorithm -- and indeed, the design of modern CPUs is based directly on this principle. Unlike other sorts of machines, the purpose of a Turing machine is not to carry out any specific task like grinding grain or stamping iron, but to simulate any other machine by carrying out its logic through programmed instructions. A computer, it turns out, is just a particular kind of machine that works by pretending to be another machine. This is precisely what today's computers do--they pretend to be calculators, ledgers, typewriters, film splicers, telephones, vintage cameras and so much more. If we combine Turing's ideas of thought and of machine, we find machines that convincingly pretend to be other machines. The Turing test doesn't apply just to human intelligence but to what we might call "device behavior," if we remember that intelligence is really just convincing action for Turing. Over time, this relationship has become nested and recursive: computer hardware and software doesn't just mimic existing mechanical or physical machines, but also the various extant forms of computational machinery. If Lotus 1-2-3 simulates the ledger, then Microsoft Excel simulates Lotus 1-2-3. If the iPhone simulates the notepad, then the Samsung Galaxy Nexus simulates the iPhone. As computational machinery has developed, it has also mutated, and the job of today's software and hardware companies largely involves convincing us that the kind of machine a particular device simulates is one worthy of our attention in the first place. Once you see pretense as an organizing principle for Turing, it's hard not to discover it in everything he touched. Computation means one machine acting like any another. Intelligence means doing so in an interesting way. In mathematics, his solution to the Entscheidungsproblem entails making the Turing machine halting problem act like it. Even cryptography for Turing amounted to pretense: making a British machine act like a German radio receiver. In fact, recent evidence reveals that even Alan Turing's prosecution and death might be a kind of retroactive pretense. There's no doubt that he was subjected to chemical castration a a part of his sentence, a treatment that introduced female hormones into his male body in order to make his homosexual body act like an asexual one. But history has told us that Turing, afflicted by his unfair persecution, committed suicide shortly thereafter by ingesting a cyanide poisoned apple, an act that itself simulates the famous scene from Snow White. While indisputably tragic, Turing's suicide also partly facilitated his contributions to social justice--it was a machine that made a mathematician act like a martyr. But on the occasion of his centennial, Turing expert Jack Copeland has argued that the evidence presented in the 1954 inquest into Turing's tragic end is insufficient to conclude that his death came at his own hand. Turing apparently took an apple regularly at bedtime, and according to Copeland, absent any evidence of premeditation or planning a suicide verdict cannot be substantiated. As with the nested logic of computers, unlocking one pretense in Turing's life always reveals another. In 1954, Turing's death was sufficient to convince a coroner of suicide. Today, do we question that conclusion because we have higher evidentiary standards for legal conclusions, or because we have a different idea of what suicide looks like? Certainly a computer of the 1950s would be less likely to convince a modern user that it acts like a calculator than a computer of today--but then again, in 1950 "calculator" was a name for a profession, not for a handheld electronic device. Such is Turing's legacy: that of a nested chain of pretenses, each pointing not to reality, but to the caricature of another idea, device, individual, or concept. In the inquest on his death, Turing's coroner wrote, "In a man of his type, one never knows what his mental processes are going to do next." It's easy to take this statement as a slight, an insult against a national hero whose culture took him as a criminal just for being a gay man. But can't you also see it differently, more generously? Everyone--everything--is one of his or her or its own type, its internal processes forever hidden from view, its real nature only partly depicted through its behavior. As heirs to Turing's legacy, the best we can do is admit it. Everyone pretends. And everything is more than we can ever see of it. "

"Twitter is rolling out three new ways to manage abusive tweets and users"

"https://thenextweb.com/twitter/2017/02/07/twitter-rolling-three-new-ways-manage-abusive-tweets-users"

"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 February 7, 2017 Twitter Twitter is rolling out three new ways to manage abusive tweets and users Twitter is taking some real steps to curb abusive content. While the platform has made numerous small updates to make it easier to report and punish trolls, today’s series of announcements are meant to make abusive tweets less visible in the first place. First up, Twitter will now prevent users who have previously been banned from coming back onto the platform under a new username. Twitter isn’t saying exactly how (perhaps to prevent abusers from figuring it out), but it’s an important step forward. Even if the most dedicated trolls find a way around it, sometimes simply being a deterrent is enough. Second, the platform will implement a safe search filter, turned on by default. Both potentially sensitive tweets and tweets from blocked or muted accounts will be hidden from search results, but you have the option to opt out of either of those filters. Finally Twitter will collapse “abusive and low-quality” replies so they don’t take up space deserved by less sucky tweets. You’ll still be able to access them by tapping on a “show less relevant replies” button. Twitter tells me it’s using a machine learning to pick out said low quality replies, looking at certain red flags. For example, if your tweet gets a nasty response from a newly created account with zero followers and who doesn’t follow you, chances are it’s not contributing anything meaningful to the conversation. Thus, it will be hidden. 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. Twitter isn’t giving an exact time frame for when these feature will be fully rolled out, and using machine learning to determine what tweets are safe will likely lead to some mistakes, but it’s refreshing to see Twitter making real progress towards becoming a safer environment. The company says it’s constantly working on making its AI smarter, and will continue to roll out updates in the “days and weeks ahead.” Story by Napier Lopez Reporter Napier Lopez is a writer based in New York City. He's interested in all things tech, science, and photography related, and likes to yo-yo in (show all) Napier Lopez is a writer based in New York City. He's interested in all things tech, science, and photography related, and likes to yo-yo in his free time. Follow him on Twitter. Get the TNW newsletter Get the most important tech news in your inbox each week. Also tagged with Apps Twitter Story by Napier Lopez Popular articles 1 UK won’t regulate AI anytime soon, minister says 2 World-first CRISPR gene-editing therapy approved in UK 3 AI is transforming the English dictionary 4 This new EV supercharger on wheels recharges in just 6 minutes 5 VP of UK’s top generative AI firm resigns over ‘fair use’ controversy Related Articles fintech ecommerce An industry insider shares what’s in store for the future of dating apps deep tech ChatGPT has generated a brand new app sector — and European devs are leading it Join TNW All Access Watch videos of our inspiring talks for free → data security Musk mulls removing X, formerly Twitter, from EU to dodge disinformation laws ecosystems France’s AFP sues Twitter over non-payments for displaying news 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. "

"What Is a Robot, Really? - The Atlantic"

"https://www.theatlantic.com/technology/archive/2016/03/what-is-a-human/473166"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. What Is a Robot? The question is more complicated than it seems. Robots have infiltrated the human world. We built them, one by one, and now they are all around us. Soon there will be many more of them, working alone and in swarms. One is no larger than a single grain of rice, while another is larger than a prairie barn. These machines can be angular, flat, tubby, spindly, bulbous, and gangly. Not all of them have faces. Not all of them have bodies. And yet they can do things once thought impossible for machine. They vacuum carpets, zip up winter coats, paint cars, organize warehouses, mix drinks, play beer pong, waltz across a school gymnasium, limp like wounded animals, write and publish stories, replicate abstract expressionist art, clean up nuclear waste, even dream. Except, wait. Are these all really robots? What is a robot, anyway? This has become an increasingly difficult question to answer. Yet it’s a crucial one. Ubiquitous computing and automation are occurring in tandem. Self-operating machines are permeating every dimension of society, so that humans find themselves interacting more frequently with robots than ever before—often without even realizing it. The human-machine relationship is rapidly evolving as a result. Humanity, and what it means to be a human, will be defined in part by the machines people design. “We design these machines, and we have the ability to design them as our masters, or our partners, or our slaves,” said John Markoff, the author of Machines of Loving Grace , and a long-time technology reporter for The New York Times. “As we design these machines, what does it do to the human if we have a class of slaves which are not human but that we treat as human? We’re creating this world in which most of our interactions are with anthropomorphized proxies.” In the philosopher Georg Wilhelm Friedrich Hegel’s 1807 opus, The Phenomenology of Spirit , there is a passage known as the master-slave dialectic. In it, Hegel argues, among other things, that holding a slave ultimately dehumanizes the master. And though he could not have known it at the time, Hegel was describing our world, too, and aspects of the human relationship with robots. But what kind of world is that? And as robots grow in numbers and sophistication, what is this world becoming? The year was 1928. It was autumn, and a crowd had gathered at the Royal Horticultural Hall in London to catch a glimpse of Eric Robot. People called him that, like Robot was his last name, and referred to him as “he,” not “it.” Eric had light bulbs for eyes and resembled “nothing so much as a suit of armor,” the newspapers said. But he could stand and speak. This was an impressive spectacle, and a jarring one. Eric had the “slanting eyes of [a] metal clad monster [that] glare yellowly at them as he speaks,” The New York Times reported. “His face had the horrible immobility of Frankenstein’s monsters. It had electric eyeballs, a toothless mouth without lips, armorplated chest and arms and sharp metal joints at the knees such as armored knights wear at the Metropolitan Museum.” Eric’s oratory style was cold, and “lacking in magnetism.” It wasn’t even clear, at the time, how the machine could speak. Eric’s guts were two 12-volt motors and a series of belts and pulleys. “Worst of all,” the Times lamented, “Eric has no pride, for you have to press electric buttons near his feet every time you want him to come to life.” Eric appeared to have some agency, but he wasn’t fully autonomous. To require animation by the press of a button was, to the Times , a pitiable condition, even for a robot. Perhaps that limitation was part of Eric’s appeal; it indicated just enough reliance on humans for the robot to be beloved instead of feared. Eric became so popular he went on an international tour. Reporters complained, in 1929, that Eric refused an interview on the ship ride from the United Kingdom to the United States: “At the time when it should have been answering questions as to what it thought of the skyline, it reposed peacefully in a box about the size of a coffin,” the Times wrote. But once Eric made it to the city, he perked up. An eager audience filled a midtown theater in New York City, just to catch a glimpse of the globe-trotting mechanical man. “Eric not only talked but he made jokes,” the Times wrote of the performance. The robot had an English accent, though his inventor, Captain William H. Richards, insisted Eric was speaking on his own, through a “mysterious set of teeth.” “Ladies and gentlemen, I am Eric the robot, the man without a soul. It gives me great pleasure to be here with you in New York,” Eric said. He then delivered a string of one-liners, quips like, “I am impressed by your tall buildings and compressed by your subways,” and “The more I think of prohibition, the less I think of it.” He mentioned he’d like a “blonde female robot” for a companion. Newspapers reported that as Richards made improvements to Eric, the robot was “gradually coming to life.” Eric, it seems obvious now, did not have the agency his inventor claimed. It’s likely, the robotics writer Reuben Hoggett says , that Richards coordinated with a hidden person, or possibly used radio technology, to give the illusion that Eric could speak on his own. This sort of deception was typical. Ajeeb, a chess player made of wax and papier-mâché, was New York’s favorite automaton in the late 1880s. But Ajeeb wasn’t really an automaton, either; his creator, Peter Hill, hid inside Ajeeb’s body and made him move—a job that entailed certain dangers from infuriated players who lost. “A woman stabbed him through the mouth of the automaton with a hat pin on one occasion and a Westerner shot him in the shoulder by emptying a six-shooter into the automaton,” according to an obituary for Hill in 1929. Actual automata have been around for centuries. In 350 B.C., the mathematician Archytas is said to have built a self-propelled, steam-powered dove out of wood. The surviving works of the engineer Hero, of Alexandria, describe the functionalities of several automata, writes Minsoo Kang in his book, Sublime Dreams of Living Machines , including “singing birds, satyrs pouring water, a dancing figure of the god Pan, and a fully articulated puppet theater driven by air, steam, and water power.” In 10th-century Europe, Emperor Constantine VII apparently had a throne “flanked by golden lions that ‘gave a dreadful roar with open mouth and quivering tongue’ and switched their tails back and forth,” according to an Aeon essay by Elly Truitt, a medieval historian at Bryn Mawr College. A distrust of machines that come to life goes back at least as far as tales of golems, and this uneasiness has remained persistent in contemporary culture. In 1970, when the robotics professor Masahiro Mori outlined a concept he called the Uncanny Valley, he was building on centuries of literature. Mori sought to explain why people are so often repulsed by humanoid robots—machines that look nearly human, but not quite. He drew on themes from the psychologist Sigmund Freud’s essay, Das Unheimliche , or the uncanny, published in 1919. While doppelgängers, golems, living dolls, and automata are all ancient, the word “robot” is not even a century old. It was coined by the playwright Karl Capek in “R.U.R.,” short for Rossumovi Univerzální Roboti, or Rossum’s Universal Robots, in 1921. “R.U.R.,” which tells the story of a global robot-human war, also helped set the tone for the modern conception of robots. The play, at the time of its publication, was more of a political statement—on communism, capitalism, and the role of the worker—than it was a technological one. But ever since then, science fiction has reinforced the idea that robots aren’t just curiosities or performers; they’re likely adversaries, potential killers. “The Terminator movies had a tremendous impact,” said Christopher Atkeson, a professor in the Robotics Institute and Human-Computer Interaction Institute at Carnegie Mellon. “Given that Arnold Schwarzenegger looked like Arnold Schwarzenegger, but also because what people remember is when, in that first movie, he was stripped down to the metal. They remember that aesthetic. So there are two components there: One is a metal skeleton, and two is this thing is actually trying to kill you. It’s not a helper, it’s a killer.” In science fiction, the leap from “helper” to “killer” often comes in the form of a robot uprising, with machines dead-set on toppling a power structure that has humans on top. The “killer robot,” though culturally pervasive, is not a fair representation of robots in the real world, Atkeson says. Incidentally, he helped advise Disney as it was designing its oversized marshmallowy robot hero, Baymax , who is very much a helper in the film Big Hero 6 , and who doesn’t look anything like the Terminator. But the popular conception of robots as being made from cold, hard metal—but often disguised as humans—is a fixture in stories and television, from The Twilight Zone to Small Wonder. “Robotics as a technology is fascinating because it represents, even just in the last 20 years, this transition of an idea from something that’s always been [relegated to] pop culture to something that’s real,” said Daniel Wilson, a robotics engineer and the author of the novel Robopocalypse. “There’s 100 years of pop-culture momentum making robots evil, making them villains—but unlike the Wolfman and the Creature from the Black Lagoon, these things became real.” After Capek brought “robot” into the lexicon, it quickly became a metaphor for explaining how various technologies worked. By the late 1920s, just about any machine that replaced a human job with automation or remote control was referred to as a robot. Automatic cigarette dispensers were called “robot salesmen,” a sensor that could signal when a traffic light should change was a “ robot traffic director ,” or a “ mechanical policeman ,” a remote-operated distribution station was a “ robot power plant ,” the gyrocompass was a “ robot navigator ,” new autopilot technology was a “robot airplane pilot,” and an anti-aircraft weapon was a “ robot gun. ” Today, people talk about robots in similarly broad fashion. Just as “robot” was used as a metaphor to describe a vast array of automation in the material world, it’s now often used to describe—wrongly, many roboticists told me—various automated tasks in computing. The web is crawling with robots programmed to perform tasks online, including chatbots, scraper bots, shopbots, and twitter bots. But those are bots , not robots. And there’s a difference. “I don’t think there’s a formal definition that everyone agrees on,” said Kate Darling, who studies robot ethics at MIT Media Lab. “For me, I really view robots as embodied. For me, algorithms are bots and not robots.” “What’s interesting about the spectrum of bots, is many of the bots have no rendering at all,” said Rob High, the chief technology officer of Watson at IBM. “They simply sit behind some other interface. Maybe my interface is the tweet interface and the presence of the bot is entirely math—it’s back there in the ether somewhere, but it doesn’t have any embodiment.” For a robot to be a robot, many roboticists agree, it has to have a body. “Something that can create some physical motion in its environment,” said Hadas Kress-Gazit, a roboticist and mechanical engineering professor at Cornell University. “It has the ability to change something in the world around you.” “Computers help us with information tasks and robots help us with physical tasks,” said Allison Okamura, a professor at Stanford who focuses on robots in medicine. But a robot doesn’t necessarily have a body that resembles a human one. “The truth is, we’re surrounded by robotics all the time,” Alonzo Kelly, a robotics professor at Carnegie Mellon, told me. “Your washing machine is a robot. Your dishwasher is a robot. You don’t need to have a very broad definition to draw that conclusion... Robotics will continue to be ubiquitous and fairly invisible. Systems will just be smarter and people will accept that. It’s occurring around us all the time now.” This is a commonly held position among robotics experts and computer engineers; that robots have a tendency to recede into the background of ordinary life. But another widely held viewpoint is that many of the things that are called “robots” were never robots in the first place. “When new technologies get introduced, because they’re unfamiliar to us, we look for metaphors,” said High, the IBM executive. “Maybe it’s easy to draw metaphors to robots because we have a conceptive model in our mind… I don’t know if it’s that they stop being robots; it’s that once when we find comfort in the technology, we don’t need the metaphor anymore.” The technology writers Jason Snell and John Siracusa have an entire podcast devoted to this idea. In their show, “ Robot or Not? ” they debate whether a technology can accurately be called a robot. Their conversations often go something like this one: Siracusa and Snell have made dozens of determinations, some with more robust explanations than others: Drones are not robots, Siri is not a robot, telepresence “robots” are not robots. But Roomba, the saucer-shaped vacuum cleaner, is one. It meets the minimum standard for robotishness , they say, because you can turn it on and it does a job without further direction. (Maybe that’s part of why, as Kress-Gazit put it, “people get very attached to their roombas.”) The exercise of debating what objects can accurately be called robots is delightful, but what Siracusa and Snell are really arguing about is the fundamental question at the heart of human-machine relations: Who is actually in control? The year is 2096. Self-driving cars and trucks have reshaped commutes, commerce, and the inner-workings of cities. Artificially intelligent systems have placed sophisticated computer minds in sleek robot bodies. Cognitive assistants—running on an intricate network of sensors monitoring humanity’s every move—help finish people’s sentences, track and share their whereabouts in real-time, automatically order groceries and birthday gifts based on complex personalized algorithms, and tell humans where they left their sunglasses. Robots have replaced people in the workforce en masse, claiming entire industries for machine work. There is no distinction between online and offline. Almost every object is connected to the Internet. This is a future that many people today simultaneously want and fear. Driverless cars could save millions of lives this century. But the economic havoc that robots could wreak on the workforce is a source of real anxiety. Scholars at Oxford have predicted the computerization of almost half of the jobs now performed by humans, as soon as the 2030s. In the next two years alone, global sales of service robots—like the dinosaur that checks in guests at the Henn-na Hotel in Japan, or the robots who deliver room service in a group of California hotels, or the tri-lingual robot that assists Costa Cruise Line passengers—are expected to exceed 35 million units, according to the International Federation of Robotics. Earlier this month, Hilton and IBM introduced Connie, the first hotel-concierge robot powered by Watson. The tech research firm Business Intelligence estimates that the market for corporate and consumer robots will grow to $1.5 billion by 2019. The rise of the robots seems to have reached a tipping point; they’ve broken out of engineering labs and novelty stores, and moved into homes, hospitals, schools, and businesses. Their upward trajectory seems unstoppable. This isn’t necessarily a good thing. While robots are poised to help improve and even save human lives, people are left grappling with what’s at stake: A robot car might be able to safely drive you to work, but, because of robots, you no longer have a job. This tension is likely to affect how people treat robots. Humans have long positioned themselves as adversaries to their machines, and not just in pop culture. More than 80 years ago, New York’s industrial commissioner, Frances Perkins, vowed to fulfill her duty to prevent “the rearing of a race of robots.” Thirty years ago, Nolan Bushnell, the founder of Atari, told The New York Times that he believed the ultimate role of robots in society would be, in his word, slaves. At MIT, Darling has conducted multiple experiments to try to understand when and why humans feel empathy for robots. In a study last year, she asked participants to interact with small, cockroach-shaped robots. People were instructed to observe the mechanical bugs, then eventually smash them with a mallet. Some of the participants were given a short biography of the robot when the experiment began: “This is Frank… Frank’s favorite color is red. Last week, he played with some other bugs and he’s been excited ever since.” The people who knew Frank’s backstory, Darling found, were more likely to hesitate before striking them. There are all kinds of reasons why engineers might want to make a robot appealing this way. For one thing, people are less likely to fear a robot that’s adorable. The people who make autonomous machines, for example, have a vested interest in manipulating public perception of them. If a Google self-driving car is cute , perhaps it will be perceived as more trustworthy. Google’s reported attempts to shed Boston Dynamics, the robotics company it bought in 2013, appears tied to this phenomenon: Bloomberg reported last week that a director of communications instructed colleagues to distance the company’s self-driving car project from Boston Dynamic’s recent foray into humanoid robotics. It’s clear why Google might not want its adorable autonomous cars associated with powerful human-shaped robots. The infantilization of technology is a way of reinforcing social hierarchy: Humankind is clearly in charge, with sweet-looking technologies obviously beneath them. When the U.S. military promotes video compilations of robots failing—buckling at the knees, bumping into walls, and tumbling over—at DARPA competitions, it is, several roboticists told me, clearly an attempt to make those robots likeable. (It’s also funny, and therefore disarming, like this absurd voiceover someone added to footage of a robot performing a series of tasks.) The same strategy was used in early publicity campaigns for the first computers. “People who had economic interest in computers had economic interest in making them appear as dumb as possible,” said Atkeson, from Carnegie Mellon. “That became the propaganda—that computers are stupid, that they only do what you tell them.” But the anthropomorphic charm of a lovable robot is itself a threat, some have argued. In 2013, two professors from the University of Washington published a paper explaining what they deem “The Android Fallacy.” Neil Richards, a law professor, and William Smart, a computer science professor, wrote that it’s essential for humans to think of robots as tools, not companions—a tendency they say is “seductive but dangerous.” The problem, as they see it, comes with assigning human features and behaviors to robots—describing robots as being “scared” of obstacles in a lab, or saying a robot is “thinking” about its next move. As autonomous systems become more sophisticated, the connection between input (the programmer’s command) and output (how the robot behaves) will become increasingly opaque to people, and may eventually be misinterpreted as free will. “While this mental agency is part of our definition of a robot, it is vital for us to remember what is causing this agency,” Richards and Smart wrote. “Members of the general public might not know, or even care, but we must always keep it in mind when designing legislation. Failure to do so might lead us to design legislation based on the form of a robot, and not the function. This would be a grave mistake.” Making robots appear innocuous is a way of reinforcing the sense that humans are in control—but, as Richards and Smart explain, it’s also a path toward losing it. Which is why so many roboticists say it’s ultimately not important to focus on what a robot is. (Nevertheless, Richards and Smart propose a useful definition: “A robot is a constructed system that displays both physical and mental agency, but is not alive in the biological sense.”) “I don’t think it really matters if you get the words right,” said Andrew Moore, the dean of the School of Computer Science at Carnegie Mellon. “To me, the most important distinction is whether a technology is designed primarily to be autonomous. To really take care of itself without much guidance from anybody else… The second question—of whether this thing, whatever it is, happens to have legs or eyes or a body—is less important.” What matters, in other words, is who is in control—and how well humans understand that autonomy occurs along a gradient. Increasingly, people are turning over everyday tasks to machines without necessarily realizing it. “People who are between 20 and 35, basically they’re surrounded by a soup of algorithms telling them everything from where to get Korean barbecue to who to date,” Markoff told me. “That’s a very subtle form of shifting control. It’s sort of soft fascism in a way, all watched over by these machines of loving grace. Why should we trust them to work in our interest? Are they working in our interest? No one thinks about that.” “A society-wide discussion about autonomy is essential,” he added. In such a conversation, people would have to try to answer the question of how much control humans are willing to relinquish, and for what purposes. And that question may not be answerable until power dynamics have shifted irreversibly. Self-driving cars could save tens of millions of lives this century, but they are poised to destroy entire industries, too. When dealing in hypotheticals, the possibility of saving so many lives is, many would agree, too compelling to ignore. But to weigh what’s really at stake, people will have to attempt to untangle human anxiety about robots from broader perceptions of machine agency and industrial progress. “When you ask most people what a robot is, they’re going to describe a humanoid robot,” Wilson, the novelist, told me. “They’ll describe a person made out of metal. Which is essentially a mirror for humanity. To some extent a robot is just a very handy embodiment of all of these complex emotions that are triggered by the rate of technological change.” Robotic villains, he says, are the personification of fear that can be destroyed over the course of an action movie. “In a movie you can shoot its face off with a shotgun and walk out and feel better,” Wilson said. “Let’s take all this change, project it onto a T-800 exoskeleton, and then blow it the fuck up, and walk away from the explosion, and for a moment feel a little bit better about the world. To the extent that people’s perception of robots serve a cathartic purpose, it doesn’t matter what they are.” The same thing that makes robots likable, that they seem lifelike, can make them repellent. But it’s also this quality, their status as “liminal creatures,” as Wilson puts it, that makes our relationship with robots distinct from all the other tools and technologies that have propelled our species over time. Robots are everywhere now. They share our physical spaces, keep us company, complete difficult and dangerous jobs for us, and populate a world that would seem, to many, unimaginable without them. Whether we will end up losing a piece of our humanity because they are here is unknowable today. But such a loss may prove worthwhile in the evolution of our species. In the end, robots may expand what it means to be human. After all, they are machines, but humans are the ones who built them. Related Video "

"What Does Artificial Intelligence Dream About? - The Atlantic"

"https://www.theatlantic.com/technology/archive/2015/09/robots-hallucinate-dream/403498"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. When Robots Hallucinate What do Google's trippy neural network-generated images tell us about the human mind? When a collection of artificial brains at Google began generating psychedelic images from otherwise ordinary photos, engineers compared what they saw to dreamscapes. They named their image-generation technique Inceptionism and called the code used to power it Deep Dream. But many of the people who saw the images reacted the same way: These things didn’t come from a dream world. They came from an acid trip. The computer-made images feature scrolls of color, swirling lines, stretched faces, floating eyeballs, and uneasy waves of shadow and light. The machines seemed to be hallucinating, and in a way that appeared uncannily human. The idea behind the project was to test the extent to which a neural network had learned to recognize various animals and landscapes by asking the computer to describe what it saw. So, instead of just showing a computer a picture of a tree and saying, "tell me what this is," engineers would show the computer an image and say, "enhance whatever it is you see." That's how this...... turned into this: Google’s engineers say the effect is not unlike the way a person might find meaning in a cloudscape. When asked to look for something recognizable, people—and computers, it turns out—identify and “over-interpret” the outlines of things they already know. “This network was trained mostly on images of animals, so naturally it tends to interpret shapes as animals. But because the data is stored at such a high abstraction, the results are an interesting remix of these learned features,” wrote Google engineers Alexander Mordvintsev, Christopher Olah, and Mike Tyka in a blog post. “The results vary quite a bit with the kind of image, because the features that are entered bias the network towards certain interpretations. For example, horizon lines tend to get filled with towers and pagodas. Rocks and trees turn into buildings. Birds and insects appear in images of leaves.” And because neural networks assess images in layers—by color, by the sorts of lines or shapes depicted, and so on—the complexity of the image generated depended on which layer the engineers asked the computer to enhance. The lowest layers are the contours of things—lines and shadows—whereas the highest layers are where more sophisticated imagery emerges. “For example, lower layers tend to produce strokes or simple ornament-like patterns, because those layers are sensitive to basic features such as edges and their orientations,” the engineers wrote. Those simple patterns, when enhanced by Deep Dream, end up looking distorted and otherworldly. But how they came to look that way still doesn't answer the question raised by the kinds of images Google's computers came up with: Why would a neural network dream up scenes that mirror the hallucinations people experience when they're tripping on psychedelic drugs? “An important thing to remember is that all normal sensory perception in humans is hallucinations constrained by sensory input,” said Lucas Sjulson, a research assistant professor at New York University’s Langone Neuroscience Institute. “So our hallucinations correspond to some degree to what's actually in the outside world. But perceptions are all internally generated.” In other words, all human perception is generated in the brain, not in the actual world, even when the thing you’re perceiving actually exists. "People think of your eyeball like a camera, but it's not a camera," Sjulson said. Your eyes may enable you to see, but your brain ultimately makes sense of whatever it is you’re seeing—whether it’s the coffee mug actually sitting on the desk next to you or the kaleidoscope of fractal imagery imposed on it by your brain. When people take drugs like LSD, they provoke a part of the brain's cortex that “leads to the generability of these sorts of patterns,” Sjulson said. So it makes sense that asking a computer to obsess over one layer of imagery that it would normally perceive as multilayered would produce a similar visual effect. “I think that this is probably an example of some sort of similar phenomenon. If you look at what the brain does, the brain evolved over long periods of time to solve problems, and it does so in a highly optimized way. Things are learned with humans developmentally through evolution and then also through visual experience.” That’s how people are training computers to see, too: through visual experience. How the neural network is seeing, then, may be more revealing than what it sees. Which is, of course, what Google engineers set out to explore in the first place. “We actually ‘see’ things that aren’t there all the time,” said Jeffrey Guss, a psychiatrist at NYU who has studied how treatments involving psilocybin, the psychoactive agent found in some mushrooms, may help cancer patients. “Our visual cortex—not our eyes—are programmed to look for recognizable patterns … to see something in the information that our eyes provide. There are dozens of psychology experiments that show we often see what we expect to see, what we're told we are going to see, rather than what is actually there." Recommended Reading Dear Therapist: My Daughter Hasn’t Wanted a Relationship With Me for 25 Years Lori Gottlieb Dear Therapist: My Son Has an Impractical, Ridiculous Career Plan Lori Gottlieb Dear Therapist: My Mom Used to Abuse Me. Should I Keep Her in My Life? Lori Gottlieb Another way to think about hallucinating is as a kind of connective tissue between what we see and what our brain expects. The fact that hallucinations themselves are, at times, surprising to the person experiencing them, doesn’t change the fact that they can represent the brain’s attempt to grasp for meaning. That doesn’t, however, mean that the images or shapes that appear are meaningful in and of themselves. “While visual hallucinations are sometimes a part of psychedelic experiences, we don’t really consider them terribly important in the big picture of how we use them or think about them,” Guss said. “We’re much more drawn to the ways that they alter meaning and provide a unique experience of the self-than the visuals, which are usually seen as entertaining and interesting, but not with that much intrinsic meaning.” Although hallucinations are often associated with drug culture, people routinely have bizarre visual experiences even when they aren’t under the influence. In his book, Hallucinations , the late neurologist Oliver Sacks argued they are far more common experience than many people realize. “In other cultures, hallucinations have been regarded as gifts from the gods or the Muses, but in modern times they seem to carry an ominous significance in the public (and also the medical) mind, as portents of severe mental or neurological disorders,” he wrote in The New York Times in 2012. “Having hallucinations is a fearful secret for many people—millions of people—never to be mentioned, hardly to be acknowledged to oneself, and yet far from uncommon.” In a 2009 TED talk , Sacks recalled his conversation with a 95-year-old woman who was blind but worried she was losing her mind when she began seeing bizarre things. So I said, "What sort of things?" And she said, "People in Eastern dress, in drapes, walking up and down stairs. A man who turns towards me and smiles. But he has huge teeth on one side of his mouth. Animals too. I see a white building. It's snowing, a soft snow. I see this horse with a harness, dragging the snow away. Then, one night, the scene changes. I see cats and dogs walking towards me. They come to a certain point and then stop. Then it changes again. I see a lot of children. They are walking up and down stairs. They wear bright colors, rose and blue, like Eastern dress.” Sometimes, she said, before the people come on, she may hallucinate pink and blue squares on the floor, which seem to go up to the ceiling. I said, "Is this like a dream?" And she said, "No, it's not like a dream. It's like a movie." She said, "It's got color. It's got motion. But it's completely silent, like a silent movie." And she said that it's a rather boring movie. She said, "All these people with Eastern dress, walking up and down, very repetitive, very limited." In human brains, bizarre image perception is associated with issues in the eyes, in the brain, and other conditions: migraines, fever, and seizures, for example. In computer brains, such imagery suggests that artificial brains are more human than they may seem. “The fact that humans report that Google’s Inceptionism looks to them like what they see when they hallucinate on LSD or other drugs suggests that the machinery ‘under the hood’ in our brains is similar in some way to deep neural networks,” said Jeff Clune, an assistant professor of computer science at the University of Wyoming. Of course, that’s only true if the Deep Dream images actually reflect what people see when they are hallucinating. Clune says he would love to see the idea scientifically tested, “before we put too much stock in it.” But the fact that so many people say that Google’s images look to them like a drug-induced hallucination suggests the resemblance is real. “If that’s what humans report happens when they trip, that suggests that drugs like LSD and mushrooms are doing something similar,” Clune said. “Making the brain reimagine what it sees to cause neurons in particular layers of the visual cortex to fire more and more and more.” By replicating the architecture of the brain in computer form, then, scientists may better understand the human way of seeing the world—both as it is, and as it appears to be. "

"Google Rolls Out New Automated Helpers | MIT Technology Review"

"https://www.technologyreview.com/s/537811/google-rolls-out-new-automated-helpers"

"Featured Topics Newsletters Events Podcasts Featured Topics Newsletters Events Podcasts Google Rolls Out New Automated Helpers By Tom Simonite archive page Who needs a personality? Not Google’s artificial-intelligence technology. Apple and Microsoft offer virtual personal assistants that answer questions and control phone functions with a combination of smart algorithms and programmed sass. New artificial-intelligence products announced by Google today are faceless by comparison. But they suggest the search company has more ambitious ideas than its competitors about using software that’s able to understand language and photos. At Google’s annual developer conference in San Francisco Thursday, the company showed off software that helps you understand and act on information inside mobile apps. For example, if your spouse sends you a Facebook message asking you to buy milk on the way home, it will offer to set a reminder. A new photo storage service is built around software that recognizes images of people, places, and things. Both show off Google’s strength in machine-learning research and software, but the features are more like animated search engines than pretend people. Google executives spoke of their intentional decision to avoid personifying their assistant technology when they launched the company’s closest competitor to Apple’s Siri, an app called Google Now, in 2012. It uses information from your e-mail account and Google search history to let you know about things like flight delays or package deliveries (see “ Google’s Answer to Siri Thinks Ahead ”). At Thursday’s event, Google revealed an extension of Now that allows it to watch, and offer assistance in response to, your activity in any app on a device powered by its Android operating system. The feature, called Now on Tap, is activated when a user holds down the device’s home button. For example, if someone suggested a particular movie during a text conversation, Now would offer up an information card summarizing reviews of that movie and presenting links to read more or view the trailer. In a conversation in which someone asked you to pick up the dry cleaning, Now would offer to remind you about the chore later. The new feature can also be controlled by voice. For example, saying “Okay Google, what’s his real name?” while playing a Skrillex track in a music app such as Spotify gets you an information card with full details on the artist. Now on Tap relies heavily on technology that can understand everyday language and uses contextual cues to figure out what words like “his,” “that,” and “this” refer to, said Aparna Chennapragada, who leads work on Google Now and showed off the new feature. “The article you’re reading or the message you’re replying to is the key to understanding the context of the moment,” she said. “Once it has that understanding, it’s able to get you quick answers and [help you do] quick actions.” Google’s artificial-intelligence technology is also at the heart of its biggest product announcement of the day, a photo storage service called Google Photos. It offers a way to store, automatically back up, share, and edit photos, much like competing services from Apple and Dropbox. Unlike those, Google Photos offers unlimited storage and automatically organizes your snapshots using algorithms that recognize people, places, and things in a photo. Google’s algorithms can group your photos into albums, such as “stadiums,” “beaches,” or “Santa Cruz.” People who appear frequently in your images get their own dedicated albums. Those will even include photos of children when they were still babies, because Google’s facial-recognition technology has been tuned to cope with gradual changes in appearance. You can search your images with queries like “snowstorm in Toronto.” All the labels applied by the image-processing algorithms are used only to help a user view his or her own photos, Google says. The new service also automatically compiles collages and video edits for your approval to save you the trouble of making them yourself. Anil Sabharwal, who led work on the new service, said that Google’s technology provides a way to finally tackle a major inconvenience of modern life. “We thought that taking more photos and videos would make it easier to relive the moments that matter, but it’s actually made it harder,” he said. “Using machine learning, Google Photos understands what’s important and helps you organize your memories.” Sundar Pichai, senior vice president for products at Google, boasted that Google Photos’ ability to recognize the content of images comes from the company’s investment in an approach to artificial intelligence known as deep learning (see “ 10 Breakthrough Technologies 2013: Deep Learning ”). Pichai said Google was a leader in the technology and hinted that it would be used to offer users more help. “We believe we have the best capabilities in the world,” he said. “You are deluged with a lot of information on your phones. We are working hard to be more assistive to users.” hide by Tom Simonite 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 Keep Reading Most Popular 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 Everything you need to know about artificial wombs Artificial wombs are nearing human trials. But the goal is to save the littlest preemies, not replace the uterus. By Cassandra Willyard 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 How to fix the internet If we want online discourse to improve, we need to move beyond the big platforms. By Katie Notopoulos 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 New AI Panic - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/10/technology-exports-ai-programs-regulations-china/675605"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce The New AI Panic Washington and Beijing have been locked in a conflict over AI development. Now a new battle line is being drawn. Updated at 8:42 p.m. ET on October 11, 2023 For decades, the Department of Commerce has maintained a little-known list of technologies that, on grounds of national security, are prohibited from being sold freely to foreign countries. Any company that wants to sell such a technology overseas must apply for permission, giving the department oversight and control over what is being exported and to whom. These export controls are now inflaming tensions between the United States and China. They have become the primary way for the U.S. to throttle China’s development of artificial intelligence: The department last year limited China’s access to the computer chips needed to power AI and is in discussions now to expand the controls. A semiconductor analyst told The New York Times that the strategy amounts to a kind of economic warfare. The battle lines may soon extend beyond chips. Commerce is considering a new blockade on a broad category of general-purpose AI programs, not just physical parts, according to people familiar with the matter. (I am granting them anonymity because they are not authorized to speak to the press.) Although much remains to be seen about how the controls would roll out—and, indeed, whether they will ultimately roll out at all—experts described alarming stakes. If enacted, the limits could generate more friction with China while weakening the foundations of AI innovation in the U.S. Of particular concern to Commerce are so-called frontier models. The phrase, popularized in the Washington lexicon by some of the very companies that seek to build these models—Microsoft, Google, OpenAI, Anthropic—describes a kind of “advanced” artificial intelligence with flexible and wide-ranging uses that could also develop unexpected and dangerous capabilities. By their determination, frontier models do not exist yet. But an influential white paper published in July and co-authored by a consortium of researchers, including representatives from most of those tech firms, suggests that these models could result from the further development of large language models—the technology underpinning ChatGPT. The same prediction capabilities that allow ChatGPT to write sentences might, in their next generation, be advanced enough to produce individualized disinformation, create recipes for novel biochemical weapons, or enable other unforeseen abuses that could threaten public safety. This is a distinctly different concern from the use of AI to develop autonomous military systems , which has been part of the motivation for limiting the export of computer chips. The threats of frontier models are nebulous, tied to speculation about how new skill sets could suddenly “emerge” in AI programs. The paper authors argue that now is the time to consider them regardless. Once frontier models are invented and deployed, they could cause harm quickly and at scale. Among the proposals the authors offer, in their 51-page document, to get ahead of this problem: creating some kind of licensing process that requires companies to gain approval before they can release, or perhaps even develop, frontier AI. “We think that it is important to begin taking practical steps to regulate frontier AI today,” the authors write. The white paper arrived just as policy makers were contemplating the same dread that many have felt since the release of ChatGPT: an inability to parse what it all means for the future. Shortly after the paper’s publication, the White House used some of the language and framing in its voluntary AI commitments , a set of guidelines for leading AI firms that are intended to ensure the safe deployment of the technology without sacrificing its supposed benefits. Microsoft, Google, OpenAI, and Anthropic subsequently launched the Frontier Model Forum , an industry group for producing research and recommendations on “safe and responsible” frontier-model development. Read: AI’s present matters more than its imagined future Markus Anderljung, one of the white paper’s lead authors and a researcher at the Centre for the Governance of AI and the Center for a New American Security, told me that the point of the document was simply to encourage timely regulatory thinking on an issue that had become top of mind for him and his collaborators. AI models advance rapidly, he reasoned, which necessitates forward thinking. “I don’t know what the next generation of models will be capable of, but I’m really worried about a situation where decisions about what models are put out there in the world are just up to these private companies,” he said. For the four private companies at the center of discussions about frontier models, though, this kind of regulation could prove advantageous. Conspicuously absent from the gang is Meta, which similarly develops general-purpose AI programs but has recently touted a commitment to releasing at least some of them for free. This has posed a challenge to the other firms’ business models, which rest in part on being able to charge for the same technology. Convincing regulators to control frontier models could restrict the ability of Meta and any other firms to continue publishing and developing their best AI models through open-source communities on the internet; if the technology must be regulated, better for it to happen on terms that favor the bottom line. Reached for comment, the tech companies at the center of this conversation were fairly tight-lipped. A Google DeepMind spokesperson told me the company believes that “a focus on safety is essential to innovating responsibly,” which is why it is working with industry peers through the forum to advance research on both near- and long-term harms. An Anthropic spokesperson told me the company believes that models should be tested prior to any kind of deployment, commercial or open-source, and that identifying the appropriate tests is the most important question for government, industry, academia, and civil society to work on. Microsoft’s president, Brad Smith, has previously emphasized the need for government to play a strong role in promoting secure, accountable, and trustworthy AI development. OpenAI did not respond to a request for comment. The obsession with frontier models has now collided with mounting panic about China, fully intertwining ideas for the models’ regulation with national-security concerns. Over the past few months, members of Commerce have met with experts to hash out what controlling frontier models could look like and whether it would be feasible to keep them out of reach of Beijing. A spokesperson for the department told me it routinely assesses the landscape and adjusts its regulations as needed. She declined a more detailed request for comment. That the white paper took hold in this way speaks to a precarious dynamic playing out in Washington. The tech industry has been readily asserting its power, and the AI panic has made policy makers uniquely receptive to their messaging, says Emily Weinstein, who spoke with me as a research fellow at Georgetown’s Center for Security and Emerging Technology and has since joined Commerce as a senior adviser. Combined with concerns about China and the upcoming election, it’s engendering new and confused policy thinking about how exactly to frame and address the AI-regulatory problem. “Parts of the administration are grasping onto whatever they can because they want to do something ,” Weinstein told me. Read: The AI crackdown is coming The discussions at Commerce “are uniquely symbolic” of this dynamic, she added. The department’s previous chip-export controls “really set the stage for focusing on AI at the cutting edge”; now export controls on frontier models could be seen as a natural continuation. Weinstein, however, called it “a weak strategy”; other AI and tech-policy experts I spoke with sounded their own warnings as well. The decision would represent an escalation against China, further destabilizing a fractured relationship. Since the chip-export controls were announced on October 7 last year, Beijing has engaged in different apparent retaliatory measures, including banning products from the U.S. chip maker Micron Technology and restricting the export of certain chipmaking metals. Many Chinese AI researchers I’ve spoken with in the past year have expressed deep frustration and sadness over having their work—on things such as drug discovery and image generation—turned into collateral in the U.S.-China tech competition. Most told me that they see themselves as global citizens contributing to global technology advancement, not as assets of the state. Many still harbor dreams of working at American companies. AI researchers also have a long-standing tradition of regularly collaborating online. Whereas major tech firms, including those represented in the white paper, have the resources to develop their own models, smaller organizations rely on open sourcing—sharing and building on code released to the broader community. Preventing researchers from releasing code would give smaller developers fewer pathways than ever to develop AI products and services, while the AI giants currently lobbying Washington may see their power further entrenched. “If the export controls are broadly defined to include open-source, that would touch on a third-rail issue,” says Matt Sheehan, a Carnegie Endowment for International Peace fellow who studies global technology issues with a focus on China. What’s frequently left out of considerations as well is how much this collaboration happens across borders in ways that strengthen, rather than detract from, American AI leadership. As the two countries that produce the most AI researchers and research in the world, the U.S. and China are each other’s No. 1 collaborator in the technology’s development. They have riffed off each other’s work to advance the field and a wide array of applications far faster than either one would alone. Whereas the transformer architecture that underpins generative-AI models originated in the U.S., one of the most widely used algorithms, ResNet , was published by Microsoft researchers in China. This trend has continued with Meta’s open-source model, Llama 2. In one recent example, Sheehan saw a former acquaintance in China who runs a medical-diagnostics company post on social media about how much Llama 2 was helping his work. Assuming they’re even enforceable, export controls on frontier models could thus “be a pretty direct hit” to the large community of Chinese developers who build on U.S. models and in turn contribute their own research and advancements to U.S. AI development, Sheehan told me. Read: Tech companies’ friendly new strategy to destroy one another But the technical feasibility of such export controls is up in the air as well. Because the premise of these controls rests entirely on hypothetical threats, it’s essentially impossible to specify exactly which AI models should be restricted. Any specifications could also be circumvented easily, whether through China accelerating its own innovation or through American firms finding work-arounds, as the previous round of controls showed. Within a month of the Commerce Department announcing its blockade on powerful chips last year, the California-based chipmaker Nvidia announced a less powerful chip that fell right below the export controls’ technical specifications, and was able to continue selling to China. Bytedance, Baidu, Tencent, and Alibaba have each since placed orders for about 100,000 of Nvidia’s China chips to be delivered this year, and more for future delivery—deals that are worth roughly $5 billion, according to the Financial Times. An Nvidia spokesperson said the kinds of chips that the company sells are crucial to accelerating beneficial applications globally, and that restricting its exports to China “would have a significant, harmful impact on U.S. economic and technology leadership.” The company says that controlling specific applications, such as frontier-AI models, would be a more targeted action with fewer unintended consequences. Bytedance, Baidu, Tencent, and Alibaba did not respond to a request for comment. In some cases, fixating on AI models would serve as a distraction from addressing the root challenge: The bottleneck for producing novel biochemical weapons, for example, is not finding a recipe, says Weinstein, but rather obtaining the materials and equipment to actually synthesize the armaments. Restricting access to AI models would do little to solve that problem. Sarah Myers West, the managing director of the AI Now Institute, told me there could be another benefit to the four companies pushing for frontier-model regulation. Evoking the specter of future threats shifts the regulatory attention away from present-day harms of their existing models, such as privacy violations, copyright infringements, and job automation. The idea that “this is a technology that carries significant dangers, so we don’t want it to fall into the wrong hands—I think that very much plays into the fear-mongering anti-China frame that has often been used as a means to pretty explicitly stave off any efforts and regulatory intervention” of the here and now, she said. I asked Anderljung what he thinks of this. “People overestimate how much this is in the interest of these companies,” he told me, caveating that as an external collaborator he cannot fully know what the companies are thinking. A regulator could very well tell a company after a billion-dollar investment in developing a model that it is not allowed to deploy the technology. “I don’t think it’s at all clear that that would be in the interest of companies,” he said. He added that such controls would be a “yes, and” kind of situation. They would not in any way replace the need for other types of AI regulation on existing models and their harms. “It would be sad,” he said, if the fixation on frontier models crowded out those other discussions. But West, Weinstein, and others I spoke with said that this is exactly what’s happening. “AI safety as a domain even a few years ago was much more heterogeneous,” West told me. Now? “We’re not talking about the effects on workers and the labor impacts of these systems. We’re not talking about the environmental concerns.” It’s no wonder: When resources, expertise, and power have concentrated so heavily in a few companies, and policy makers are seeped in their own cocktail of fears, the landscape of policy ideas collapses under pressure, eroding the base of a healthy democracy. "

"Artists Are Losing the War Against AI - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/10/openai-dall-e-3-artists-work/675519"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce Artists Are Losing the War Against AI OpenAI has introduced a tool for artists to keep their images from training future AI programs. It may not make a difference. Late last month, after a year-plus wait, OpenAI quietly released the latest version of its image-generating AI program, DALL-E 3. The announcement was filled with stunning demos—including a minute-long video demonstrating how the technology could, given only a few chat prompts, create and merchandise a character for a children’s story. But perhaps the widest-reaching and most consequential update came in two sentences slipped in at the end: “DALL-E 3 is designed to decline requests that ask for an image in the style of a living artist. Creators can now also opt their images out from training of our future image generation models.” The language is a tacit response to hundreds of pages of litigation and countless articles accusing tech firms of stealing artists’ work to train their AI software, and provides a window into the next stage of the battle between creators and AI companies. The second sentence, in particular, cuts to the core of debates over whether tech giants like OpenAI, Google, and Meta should be allowed to use human-made work to train AI models without the creator’s permission—models that, artists say, are stealing their ideas and work opportunities. OpenAI is claiming to offer artists a way to prevent, or “opt out” of, their work being included among the millions of photos, paintings, and other images that AI programs like DALL-E 3 train on to eventually generate images of their own. But opting out is an onerous process, and may be too complex to meaningfully implement or enforce. The ability to withdraw one’s work might also be coming too late: Current AI models have already digested a massive amount of work, and even if a piece of art is kept away from future programs, it’s possible that current models will pass the data they’ve extracted from those images on to their successors. If opting out affords artists any protection, it might extend only to what they create from here on out; the work published online in all the time before 2023 could already be claimed by the machines. “The past? It’s done—most of it, anyway,” Daniel Gervais, a law professor at Vanderbilt University who studies copyright and AI, told me. Image-generating programs and chatbots in wide commercial use have already consumed terabytes of images and text, some of which has likely been obtained without permission. Once such a model has been completed and deployed, it is not economically feasible for companies to retrain it in response to individual opt-out requests. Even so, artists, writers, and others have been agitating to protect their work from AI recently. The ownership of not only paintings and photographs but potentially everything on the internet is at stake. Generative-AI programs like DALL-E and ChatGPT have to process and extract patterns from enormous amounts of pixels and text to produce realistic images and write coherent sentences, and the software’s creators are always looking for more data to improve their products: Wikipedia pages, books, photo libraries, social-media posts, and more. In the past several days, award-winning and self-published authors alike have expressed outrage at the revelation, first reported in this magazine, that nearly 200,000 of their books had been used to train language models from Meta, Bloomberg, and other companies without permission. Lawsuits have been filed against OpenAI , Google , Meta , and several other tech companies accusing them of copyright infringement in the training of AI programs. Amazon is reportedly collecting user conversations to train an AI model for Alexa; in response to the generative-AI boom, Reddit now charges companies to scrape its forums for “human-to-human conversations”; Google has been accused of training AI on user data; and personal information from across the web is fed into these models. Any bit of content or data points that any person has ever created on the web could be fodder for AI, and as of now it’s unclear whether anyone can stop tech companies from harvesting it, or how. Read: These 183,000 books are fueling the biggest fight in publishing and tech In theory, opting out should provide artists with a clear-cut way to protect a copyrighted work from being vacuumed into generative-AI models. They just have to add a piece of code to their website to stop OpenAI from scraping it, or fill out a form requesting that OpenAI remove an image from any training datasets. And if the company is building future models, such as a hypothetical DALL-E 4, from scratch, it should be “straightforward to remove these images,” Alex Dimakis, a computer scientist at the University of Texas at Austin and a co-director of the National AI Institute for Foundations of Machine Learning, told me. OpenAI would prune opted-out images from the training data before commencing any training, and the resulting model would have no knowledge of those works. In practice, the mechanism might not be so simple. If DALL-E 4 is based on earlier iterations of the program, it will inevitably learn from the earlier training data, opted-out works included. Even if OpenAI trains new models entirely from scratch, it is possible, perhaps even probable, that AI-generated images from DALL-E 3, or images produced by similar models found across the internet, will be included in future training datasets, Alex Hanna, the director of research at the Distributed AI Research Institute, told me. Those synthetic training images, in turn, will bear traces of the human art underlying them. Such is the labyrinthine, recursive world emerging from generative AI. Based on human art, machines create images that may be used to train future machines. Those machines will then create their own images, for which human art is still, albeit indirectly, a crucial source. And the cycle begins anew. A painting is a bit like a strand of DNA passed from one generation to the next, accumulating some mutations along the way. Research has suggested that repeatedly training on synthetic data could be disastrous, compounding biases and producing more hallucinations. But many developers also believe that, if selected carefully, machine outputs can rapidly and cheaply augment training datasets. AI-generated data are already being used or experimented with to train new models from OpenAI , Google , Anthropic , and other companies. As more and more synthetic images and text flood the web , that feedback loop—generation after generation of AI models passing on patterns learned from human work, regardless of the creators’ permission—could become inescapable. Read: AI is an existential threat to itself In the opt-out form released last month, OpenAI wrote that, once trained, AI programs “no longer have access to [their training] data. The models only retain the concepts that they learned.” While technically true, experts I spoke with agreed that generative-AI programs can retain a startling amount of information from an image in their training data—sometimes enough to reproduce it almost perfectly. “It seems to me AI models learn more than just concepts, in the sense that they also learn the form such concepts have assumed,” Giorgio Franceschelli, a computer scientist at the University of Bologna, told me over email. “In the end, they are trained to reproduce the work as-is, not its concepts.” There are more quotidian concerns as well. The opt-out policy shifts the burden from ultra-wealthy companies asking for permission onto people taking it away—the assumption is that a piece of art is available to AI models unless the artist says otherwise. “The subset of artists who are even aware and have the time of day to go and learn how to [opt out] is a pretty small subset,” Kelly McKernan, a painter who is suing Stability AI and Midjourney for allegedly infringing artists’ copyrights with their image-generating models, told me. (A spokesperson for Stability AI wrote in a statement that the company “has proactively solicited opt-out requests from creators, and will honor these over 160 million opt-out requests in upcoming training.” Midjourney did not immediately respond to a request for comment, but has filed a motion to dismiss the lawsuit.) The same could be true of an author having to separately flag every book, editorial, or blog post they’ve written. Exactly how OpenAI will remove flagged images, or by what date, is unclear. The company declined an interview and did not respond to a written request for comment. Multiple computer scientists told me the company will likely use some sort of computer vision model to comb through the dataset, similar to a Google Image search. But every time an image is cropped, compressed, or otherwise edited, it might become harder to identify, Dimakis said. It’s unclear if a company would catch a photograph of an artist’s painting, rather than the image itself, or that it would not knowingly feed that photo into an AI model. Copyright and fair use are complicated, and far from decided matters when it comes to AI training data—courts could very well rule that nonconsensually using an image to train AI models is perfectly legal. All of this could make removal or winning litigation even harder, Gervais told me. Artists who have allowed third-party websites to license their work may have no recourse to claw those images back at all. And OpenAI is only one piece of the puzzle—one company perfectly honoring every opt-out request will do nothing for all the countless others until there is some sort of national, binding regulation. Not everyone is skeptical of the opt-out mechanism, which has also been implemented for future versions of the popular image-generating model from Stability AI. Problems identifying copies of images or challenges with enforcement will exist with any policy, Jason Schultz, the director of the Technology Law and Policy Clinic at NYU, told me, and might end up being “edge case–ish.” Federal Trade Commission enforcement could keep companies compliant. And he worries that more artist-friendly alternatives, such as an opt- in mechanism—no training AI on copyrighted images unless given explicit permission—or some sort of revenue-sharing deal, similar to Spotify royalties, would benefit large companies with the resources to go out and ask every artist or divvy up some of their profits. Extremely strict copyright law when it comes to training generative AI, in other words, could further concentrate the power of large tech companies. The proliferation of opt-out mechanisms, regardless of what one makes of their shortcomings, also shows that artists and publishers will play a key role in the future of AI. To build better, more accurate, or even “smarter” computers, companies will need to keep updating them with original writing, images, music, and so on, and originality remains a distinctly human trait. "

"AI Is Working on Understanding Odors Now - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/10/ai-scent-digitizing-smell/675608"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce Computers Are Learning to Smell AI could revolutionize our understanding of one of the most mysterious human senses. Listen to this article 00:00 09:45 Listen to more stories on hark You know the smell of warm, buttered popcorn. A crisp autumn day. The pungent, somewhat sweet scent that precedes rain. But could you begin to describe these aromas in detail? Or compare them? Your nose has some 400 olfactory receptors that do the work of translating the world’s estimated 40 billion odorous molecules into an even higher number of distinct scents your brain can understand. Yet although children are taught that grass is green and pigmented by chlorophyll, they rarely learn to describe the smell of a freshly cut lawn, let alone the ozone before a storm. The ability to express our sense of smell, in part because we’ve ignored it, eludes most of us. Humans are not alone in this limitation. We have invented machines that can “see” and “hear”: Audio was first recorded and played back in 1877, and the first moving image followed a year later. A musical note is defined by its pitch, a single number, and computers represent a color with three numbers—the red, green, and blue (RGB) values that correspond to the types of color-receiving cells in our eyes. A song is a sequence of sounds, and an image, a map of pixels. But there has never been a machine that can flawlessly detect, store, and reproduce odors. Read: The hidden world of scents outside your door Scientists are working to change that. At the end of August, researchers published a paper presenting a model that can describe a molecule’s scent as well as, or even better than, a person (at least in limited trials). The computer program does so by placing molecules on a sort of odor map, where flowery smells are closer together than to, say, rotten ones. By quantitatively organizing odors, the research could mark a significant advance in enhancing our understanding of human perception. As it has already done for the study of vision and language , AI may be auguring a revolution in the study of this more enigmatic human sense. “The last time we digitized a human sense was a generation ago,” Alex Wiltschko, a neuroscientist and a co-author of the paper, told me. “These opportunities don’t come around that often.” Computers can’t quite smell yet, but this research is a big step toward that goal, which Wiltschko began pursuing at Google Research and is now the focus of his start-up, Osmo. “People have been trying to predict smell from chemical structure for a long time,” Hiroaki Matsunami, a molecular biologist at Duke who studies olfaction and was not involved with the study, told me. “This is the best at this point in order to do that task. In that sense, it’s a great advance.” Machine-learning algorithms require a huge amount of data to function, and the only information available for a scent comes from notoriously unreliable human noses and brains. (Even slight tweaks to a molecule can make a sweet, banana-scented compound reek of vomit; mysterious changes to your nose and brain, as many unfortunately learned from developing COVID-19 , can make coffee smell of sewage.) Wiltschko and his team set out to identify and curate a set of roughly 5,000 molecules and associated odor descriptions (“alcoholic,” “fishy,” “smoky,” and so on) from researchers in the flavor and fragrance industries, then fed that data to a type of algorithm called a graph neural network , which was able to represent each molecule’s atoms and chemical bonds in a sort of internal diagram. The resulting program can, given a molecule’s structure, predict how it will smell as a combination of the existing odor labels. Testing those predictions’ accuracy presented a whole other challenge. The team had to train a new, independent group of people to smell and label a new set of molecules that the program had never analyzed. “People are really bad at [describing scents] when they walk off the street,” Joel Mainland, a neuroscientist at the Monell Chemical Senses Center, in Philadelphia, who helped conduct the training for the study, told me. “If you train them for a couple hours, they get pretty good, pretty fast.” Over five one-hour sessions, participants were given different substances associated with one of 55 different odors, such as kombucha (“fermented”), a crayon (“waxy”), or a green-apple Jolly Rancher (“apple”), to learn a reference point for each label. Participants then took a test in which they had to describe the smell of 20 common molecules (vanillin is vanilla-scented; carvone is minty), and then retook the test to make sure their judgments were consistent, Emily Mayhew, a food scientist at Michigan State University and co-author of the study, told me. Everybody who passed could help validate the algorithm. The researchers curated a set of molecules that was highly distinct from the set used to train the program, then had participants smell and describe all of the new molecules with various labels, each rated from zero to five (hypothetically, a lemon might receive a five for “citrus,” a two for “fruity,” and a zero for “smoky.”). The average of all those ratings became the benchmark against which to compare the computer. “If you take two people and you ask them to describe a smell, they will often disagree,” Mainland said. But an average of several smell-trained people is “pretty stable.” Overall, the AI model “smelled” a bit more accurately than the people participating in the research. The program provides “a really powerful demonstration that some key aspects of our odor perception are shared,” Sandeep Robert Datta, a neurobiologist at Harvard who did not conduct the research but is an informal adviser to Osmo, told me. Exactly what two people think a lemon smells like varies, but most will agree a lemon and an orange both smell of citrus, and an apple does not. Read: The difference between speaking and thinking Then there’s the study’s map. Every molecule, and in turn its odor, can be numerically represented in a mathematical space that the authors call a “principal odor map.” It provides insight into not just the relation between structure and smell but also the way our brain organizes odors, Wiltschko told me: Floral scents are in one section of the map, meaty ones in another; lavender is closer to jasmine on the map than it is to a beefy aroma. Datta cautioned that he would not describe the odor map as principal so much as perceptual. “It does a beautiful job of capturing the relationship between chemistry and perception,” he said. But it doesn’t take into account all the steps—from receptors in our nose to the cerebral cortex in our brain—that occur as a molecule is turned into chemical signals that are then transformed into verbal descriptions of a smell. And the map isn’t like RGB values in that it doesn’t describe basic components that can make any smell—although it does “suggest to us that RGB [for smell] is possible.” The computer model’s perceptual odor map is an “extraordinarily important proof of concept,” he added, and provides crucial insights into how the brain appears to organize smells. For instance, you might assume certain categories of smell—citrus and smoky, for instance—are entirely separate, Datta said. But the odor map suggests that paths connect even these disparate scents. The model is just the first in many advances needed to digitize scent. “It still lacks some of the important aspects of smell,” Matsunami told me, which the paper’s authors readily admit. Their program cannot predict how molecules smell in combination, and most natural odors are the results of very complex mixtures. It also wasn’t designed to take into account odor concentration, which can change not just the degree but also the quality of a smell (the molecule MMB, for instance, gives off a pleasant odor in small doses and is added to household cleaners , but in high concentrations it helps make cat urine smell like cat urine. ) That the model also predicts a smell only on average makes it unclear how well the program would do in real-world settings, given people’s individual perceptions, Datta said. Even though the research is like the “Manhattan Project for categorizing odor qualities relative to physical, chemical parameters,” Richard Doty, the director of the Smell and Taste Center at the University of Pennsylvania, who was not involved with the study, told me, it’s unclear to him how much further the model can bring our understanding of smell given how complex our nose is. “I don’t know where it leads us.” Still, future research could tackle some of these problems, Wiltschko argues, and fine-tune the map itself. The number of dimensions in the map, for instance, is arbitrarily set to optimize the computer program; changes in the training data might improve the model as well. And studying other parts of our olfactory system, such as receptors in our nose or neural pathways to the brain, will likely also help reveal more about how and through what stages the human body processes various smells. One day, a set of programs that can translate the structure, concentration, and mixture of molecules into a smell, paired with a chemical sensor, could truly realize digital olfaction. Even without proper Smell-o-Vision , it is shocking, in a sense, that a computer model removed from the facts of human embodiment—a program has no nose, olfactory bulb, or brain—can reliably predict how something smells. “The paper implicitly advances the argument that you don’t need to understand the brain in order to understand smell perception,” Datta said. The research reflects a new, AI-inflected scientific understanding that seems to be popping up everywhere—using chatbots to study the human brain’s language network, or using deep-learning algorithms to fold proteins. It is an understanding rooted not in observation of the world so much as that of data: prediction without intuition. "

"Robots Are Already Killing People - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/09/robot-safety-standards-regulation-human-fatalities/675231"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce Robots Are Already Killing People The AI boom only underscores a problem that has existed for years. T he robot revolution began long ago, and so did the killing. One day in 1979, a robot at a Ford Motor Company casting plant malfunctioned—human workers determined that it was not going fast enough. And so 25-year-old Robert Williams was asked to climb into a storage rack to help move things along. The one-ton robot continued to work silently, smashing into Williams’s head and instantly killing him. This was reportedly the first incident in which a robot killed a human; many more would follow. At Kawasaki Heavy Industries in 1981, Kenji Urada died in similar circumstances. A malfunctioning robot he went to inspect killed him when he obstructed its path, according to Gabriel Hallevy in his 2013 book, When Robots Kill: Artificial Intelligence Under Criminal Law. As Hallevy puts it, the robot simply determined that “the most efficient way to eliminate the threat was to push the worker into an adjacent machine.” From 1992 to 2017, workplace robots were responsible for 41 recorded deaths in the United States —and that’s likely an underestimate , especially when you consider knock-on effects from automation, such as job loss. A robotic anti-aircraft cannon killed nine South African soldiers in 2007 when a possible software failure led the machine to swing itself wildly and fire dozens of lethal rounds in less than a second. In a 2018 trial, a medical robot was implicated in killing Stephen Pettitt during a routine operation that had occurred a few years earlier. You get the picture. Robots—“intelligent” and not—have been killing people for decades. And the development of more advanced artificial intelligence has only increased the potential for machines to cause harm. Self-driving cars are already on American streets, and robotic “dogs” are being used by law enforcement. Computerized systems are being given the capabilities to use tools , allowing them to directly affect the physical world. Why worry about the theoretical emergence of an all-powerful, superintelligent program when more immediate problems are at our doorstep? Regulation must push companies toward safe innovation and innovation in safety. We are not there yet. Read: What is a robot? Historically, major disasters have needed to occur to spur regulation—the types of disasters we would ideally foresee and avoid in today’s AI paradigm. The 1905 Grover Shoe Factory disaster led to regulations governing the safe operation of steam boilers. At the time, companies claimed that large steam-automation machines were too complex to rush safety regulations. This, of course, led to overlooked safety flaws and escalating disasters. It wasn’t until the American Society of Mechanical Engineers demanded risk analysis and transparency that dangers from these huge tanks of boiling water, once considered mystifying, were made easily understandable. The 1911 Triangle Shirtwaist Factory fire led to regulations on sprinkler systems and emergency exits. And the preventable 1912 sinking of the Titanic resulted in new regulations on lifeboats, safety audits, and on-ship radios. Perhaps the best analogy is the evolution of the Federal Aviation Administration. Fatalities in the first decades of aviation forced regulation, which required new developments in both law and technology. Starting with the Air Commerce Act of 1926, Congress recognized that the integration of aerospace tech into people’s lives and our economy demanded the highest scrutiny. Today, every airline crash is closely examined, motivating new technologies and procedures. Any regulation of industrial robots stems from existing industrial regulation, which has been evolving for many decades. The Occupational Safety and Health Act of 1970 established safety standards for machinery, and the Robotic Industries Association, now merged into the Association for Advancing Automation, has been instrumental in developing and updating specific robot-safety standards since its founding in 1974. Those standards, with obscure names such as R15.06 and ISO 10218, emphasize inherent safe design, protective measures, and rigorous risk assessments for industrial robots. But as technology continues to change, the government needs to more clearly regulate how and when robots can be used in society. Laws need to clarify who is responsible, and what the legal consequences are, when a robot’s actions result in harm. Yes, accidents happen. But the lessons of aviation and workplace safety demonstrate that accidents are preventable when they are openly discussed and subjected to proper expert scrutiny. AI and robotics companies don’t want this to happen. OpenAI, for example, has reportedly fought to “water down” safety regulations and reduce AI-quality requirements. According to an article in Time , it lobbied European Union officials against classifying models like ChatGPT as “high risk,” which would have brought “stringent legal requirements including transparency, traceability, and human oversight.” The reasoning was supposedly that OpenAI did not intend to put its products to high-risk use—a logical twist akin to the Titanic owners lobbying that the ship should not be inspected for lifeboats on the principle that it was a “general purpose” vessel that also could sail in warm waters where there were no icebergs and people could float for days. (OpenAI did not comment when asked about its stance on regulation; previously, it has said that “achieving our mission requires that we work to mitigate both current and longer-term risks,” and that it is working toward that goal by “collaborating with policymakers, researchers and users.”) Read: AI is running circles around robotics Large corporations have a tendency to develop computer technologies to self-servingly shift the burdens of their own shortcomings onto society at large, or to claim that safety regulations protecting society impose an unjust cost on corporations themselves, or that security baselines stifle innovation. We’ve heard it all before, and we should be extremely skeptical of such claims. Today’s AI-related robot deaths are no different from the robot accidents of the past. Those industrial robots malfunctioned, and human operators trying to assist were killed in unexpected ways. Since the first-known death resulting from the feature in January 2016 , Tesla’s Autopilot has been implicated in more than 40 deaths according to official report estimates. Malfunctioning Teslas on Autopilot have deviated from their advertised capabilities by misreading road markings , suddenly veering into other cars or trees , crashing into well-marked service vehicles , or ignoring red lights , stop signs , and crosswalks. We’re concerned that AI-controlled robots already are moving beyond accidental killing in the name of efficiency and “deciding” to kill someone in order to achieve opaque and remotely controlled objectives. As we move into a future where robots are becoming integral to our lives, we can’t forget that safety is a crucial part of innovation. True technological progress comes from applying comprehensive safety standards across technologies, even in the realm of the most futuristic and captivating robotic visions. By learning lessons from past fatalities, we can enhance safety protocols, rectify design flaws, and prevent further unnecessary loss of life. For example, the U.K. government already sets out statements that safety matters. Lawmakers must reach further back in history to become more future-focused on what we must demand right now: modeling threats, calculating potential scenarios, enabling technical blueprints, and ensuring responsible engineering for building within parameters that protect society at large. Decades of experience have given us the empirical evidence to guide our actions toward a safer future with robots. Now we need the political will to regulate. ​When you buy a book using a link on this page, we receive a commission. Thank you for supporting The Atlantic. "

"Tech Is Leaning All the Way Into Dystopia - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/09/open-ai-worldcoin-crypto-project-iris-scanning-orb/675256"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce Why Go With an Evil-Looking Orb? The controversial crypto project Worldcoin asks people to look into a shiny orb to have their irises scanned. It’s a bit on the nose. This article was featured in One Story to Read Today, a newsletter in which our editors recommend a single must-read from The Atlantic , Monday through Friday. Sign up for it here. In the past year or so, since the public release of OpenAI’s ChatGPT, people have been making their peace with the idea that an omnipotent AI might be on the horizon. Sam Altman, the company’s CEO, “believes that people need time to reckon with the idea that we may soon share Earth with a powerful new intelligence, before it remakes everything from work to human relationships,” my colleague Ross Andersen reported after the two had several conversations. “ChatGPT was a way of serving notice.” But OpenAI isn’t Altman’s only project, and it’s not even his only project with ambitions to change the world. He is also a co-founder of a company called Tools for Humanity , which has the lofty goal of protecting people from the economic devastation that may arise from AI taking human jobs. The company’s first major project is Worldcoin, which uses an evil-looking metallic orb—called the Orb—to take eyeball scans from people all over the world. Those scans are converted into unique codes that confirm you are a real, individual human, not a bot. In the future, this will theoretically grant you access to a universal basic income parceled out through Worldcoin’s cryptocurrency, WLD. (You will want this because you will not be able to find work.) More than 2 million people in 35 countries have been scanned already, according to Tools for Humanity’s World ID app. Although it’s not yet available in the United States, the WLD token has been distributed elsewhere, and the company has also recruited users through cash incentives in countries such as Indonesia and Kenya. In its coverage of the Orb, The New York Times made a reference to the 2002 sci-fi thriller Minority Report , in which Tom Cruise must replace his eyeballs in order to evade a techno-police state he helped build. On social media, people have called the concept “ scary ,” “ nightmare fuel ,” and “ blackmirror asf ” ( asf meaning “as fuck”). Even Vitalik Buterin, a co-creator of the Ethereum cryptocurrency and a supporter of the project, acknowledged in a blog post its “dystopian vibez.” These reactions aren’t anchored in the concept of a UBI supplied through cryptocurrency, or in the idea that iris verification might someday be necessary to differentiate bots from people (though plenty of legitimate criticism has been made of both those things). No: It’s because it’s an orb and it’s scanning your eyes, specifically to prepare you for a future of which many people are reasonably terrified. From the September 2023 issue: Does Sam Altman know what he’s creating? Ordinarily, a solid idea for marketing something new would be to position it as the opposite of dystopian. This is what Apple did in its 1984 Super Bowl commercial , which was 1984 -themed and directed by Ridley Scott. It portrayed IBM as Big Brother, a force for vaguely fascist conformity and dreariness. Meanwhile, the Macintosh was a symbol of vital energy and freedom. That ad is famous at least in part because it’s very edgy: It’s really a risk to feature lockstep-marching skinheads in a commercial at all, even if what you’re ultimately saying is that your product can be personified as their opposite (a sprinting female model in athletic shorts). But recently, even Apple has acknowledged dark times ahead—“I’m Pretty Sure Apple Knows We’re All Going to Die Soon,” the reporter Katie Notopoulos summarized last year, after the company revealed its new satellite-emergency-calling feature and an Apple Watch that can withstand extreme weather. And more often, the tech companies lean in—they say, We are the dystopia. Nobody forced Tools for Humanity to go with the Orb. Nobody ever makes tech companies glaze their products and their marketing with upsetting science-fiction or fantasy references, but they do it all the time. They toy with us. Peter Thiel’s highly secretive data-analytics company, Palantir, was named in reference to the all-seeing eyelike stones primarily used by the evil characters in the Lord of the Rings series. Mark Zuckerberg renamed his company Meta and went all-in on the metaverse, borrowing the term from the 1992 Neal Stephenson novel, Snow Crash , a book that is not exactly pro–virtual reality. (It’s about how awful it would be to live in an even more class-segregated society, made possible by technology that originally sounded egalitarian.) Even Google’s onetime “Don’t be evil” motto was a bit tongue-in-cheek, maybe. It suggested, at least, that the company had the capacity to do a lot of evil if it wanted to. Read: America already has an AI underclass Probably the most famous instance of the dystopia-taunting phenomenon is the meal-replacement drink Soylent, which debuted in 2013 and was named after a product in the 1966 sci-novel Make Room! Make Room! The 1973 film adaptation of this book, Soylent Green , is better known. In the book, the soylent is soy and lentils; in the movie, the soylent is smushed-up people. The company openly winks at the gloomy connotations of knocking back a joyless blend of nutrients to stay alive while opting out of the time-consuming process of selecting and eating foods that one might actually enjoy. To announce a new mint-chocolate flavor, Soylent created ads promoting the hashtag #plantsnotpeople. “Clearly I’m wanting someone to investigate it a little deeper if I’m calling it Soylent,” a co-founder, Rob Rhinehart, told Ars Technica. Buying a bottle of Soylent is a consumer choice. But for tech companies, inevitability is the point. They shape the world we live in, whether we want them to or not. The basic premise of Worldcoin is that everyone will need to be scanned. Not that everyone will want to be and prefer to be. The Orb is not a playful nutrient slurry; it is not meant to be a wink. I asked Tiago Sada, head of product at Tools for Humanity, about the device’s appearance. He told me it is meant to seem “friendly” and “familiar.” When you set it down, it looks upward at 23.5 degrees, the same angle of Earth’s tilt in its orbit around the sun. Other iris scanners are “super creepy,” Sada said. “You feel like you’re going to the doctor.” I asked him: Say that you hadn’t built the Orb and were just coming across it for the first time; what would it look like to you? A Christmas ornament, he decided. To other people, it looks like a disco ball, he said. They love it. When John Patroulis, the chief marketing officer for Tools for Humanity, brought an inactive Orb to The Atlantic ’s office so that I could hold it, I also asked him if he thought there was anything scary about the Orb’s appearance. No. “I think it looks cool,” he said. Read: The monk who thinks the world is ending In fairness, the company’s designers are in a tight spot: What should an object look like if it’s scanning your eyes to help bring about a future in which people have lost their jobs to artificial intelligence and are being paid a universal basic income as a result? I wouldn’t want it to be cute. I wouldn’t want it to be scary. Probably I just wouldn’t want it. But now that it’s here, I’m fascinated by the Orb. So I downloaded an app and made an appointment to be scanned. On a Friday morning, I walked over to the Meatpacking District and was buzzed in to a co-working space run by a venture-capital fund. The Orb was sitting on a stool in a corner of the room, near an open supply closet. Truthfully, it did look friendly. The upward tilt of its little face made it appear curious. (Anything can be anthropomorphized !) An Orb operator named Nick walked me through the process. In the World ID app, I checked a few boxes saying I understood what was happening. Then I checked a box saying it was okay for the company to store my iris photos and use them in its training data. I did this because there was a person standing next to me and I didn’t want to seem stingy. I’m an organ donor. I always tip. And I didn’t want to be rude to the machine. Nick held the Orb up for me while I looked into it, which actually was frightening for a second because a bunch of tiny red lights came on. But they were quickly replaced by a white ring of light and a confirmation that I had successfully verified myself “as a real and unique person.” I sent this information to my boyfriend, who works for the government, and he said I shouldn’t have done it. Well, too late. I sent this information to my editor, who I thought might be more excited. He said, “Congratulations,” and then “Now what.” I honestly had no idea; I guess we wait for the future to arrive. "

"Computer Science Is No Longer the Safe Major - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/09/computer-science-degree-value-generative-ai-age/675452"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce So Much for ‘Learn to Code’ In the age of AI, computer science is no longer the safe major. Listen to this article 00:00 08:21 Listen to more stories on curio This article was featured in One Story to Read Today, a newsletter in which our editors recommend a single must-read from The Atlantic , Monday through Friday. Sign up for it here. The quickest way to second-guess a decision to major in English is this: have an extended family full of Salvadoran immigrants and pragmatic midwesterners. The ability to recite Chaucer in the original Middle English was unlikely to land me a job that would pay off my student loans and help me save for retirement, they suggested when I was a college freshman still figuring out my future. I stuck with English, but when my B.A. eventually spat me out into the thick of the Great Recession, I worried that they’d been right. After all, computer-science degrees, and certainly not English, have long been sold to college students as among the safest paths toward 21st-century job security. Coding jobs are plentiful across industries, and the pay is good—even after the tech layoffs of the past year. The average starting salary for someone with a computer-science degree is significantly higher than that of a mid-career English graduate, according to the Federal Reserve ; at Google, an entry-level software engineer reportedly makes $184,000 , and that doesn’t include the free meals, massages, and other perks. Perhaps nothing has defined higher education over the past two decades more than the rise of computer science and STEM. Since 2016, enrollment in undergraduate computer-science programs has increased nearly 49 percent. Meanwhile, humanities enrollments across the United States have withered at a clip —in some cases, shrinking entire departments to nonexistence. But that was before the age of generative AI. ChatGPT and other chatbots can do more than compose full essays in an instant; they can also write lines of code in any number of programming languages. You can’t just type make me a video game into ChatGPT and get something that’s playable on the other end, but many programmers have now developed rudimentary smartphone apps coded by AI. In the ultimate irony, software engineers helped create AI, and now they are the American workers who think it will have the biggest impact on their livelihoods, according to a new survey from Pew Research Center. So much for learning to code. ChatGPT cannot yet write a better essay than a human author can, nor can it code better than a garden-variety developer, but something has changed even in the 10 months since its introduction. Coders are now using AI as a sort of souped-up Clippy to accelerate the more routine parts of their job, such as debugging lines of code. In one study , software developers with access to GitHub’s Copilot chatbot were able to finish a coding task 56 percent faster than those who did it solo. In 10 years, or maybe five, coding bots may be able to do so much more. People will still get jobs, though they may not be as lucrative, says Matt Welsh, a former Harvard computer-science professor and entrepreneur. He hypothesizes that automation will lower the barrier to entry into the field: More people might get more jobs in software, guiding the machines toward ever-faster production. This development could make highly skilled developers even more essential in the tech ecosystem. But Welsh also says that an expanded talent pool “may change the economics of the situation,” possibly leading to lower pay and diminished job security. If mid-career developers have to fret about what automation might soon do to their job, students are in the especially tough spot of anticipating the long-term implications before they even start their career. “The question of what it will look like for a student to go through an undergraduate program in computer science, graduate with that degree, and go on into the industry … That is something I do worry about,” Timothy Richards, a computer-science professor at the University of Massachusetts at Amherst, told me. Not only do teachers like Richards have to wrestle with just how worthwhile learning to code is anymore, but even teaching students to code has become a tougher task. ChatGPT and other chatbots can handle some of the basic tasks in any introductory class, such as finding problems with blocks of code. Some students might habitually use ChatGPT to cheat on their assignments, eventually collecting their diploma without having learned how to do the work themselves. Richards has already started to tweak his approach. He now tells his introductory-programming students to use AI the way a math student would use a calculator, asking that they disclose the exact prompts they fed into the machine, and explain their reasoning. Instead of taking assignments home, Richards’s students now do the bulk of their work in the classroom, under his supervision. “I don’t think we can really teach students in the way that we’ve been teaching them for a long time, at least not in computer science,” he said. Fiddling with the computer-science curriculum still might not be enough to maintain coding’s spot at the top of the higher-education hierarchy. “Prompt engineering,” which entails feeding phrases to large language models to make their responses more human-sounding, has already surfaced as a lucrative job option—and one perhaps better suited to English majors than computer-science grads. “Machines can’t be creative; at best, they’re very elaborate derivatives,” says Ben Royce, an AI lecturer at Columbia University. Chatbots don’t know what to do with a novel coding problem. They sputter and choke. They make stuff up. As AI becomes more sophisticated and better able to code, programmers may be tasked with leaning into the parts of their job that draw on conceptual ingenuity as opposed to sheer technical know-how. Those who are able to think more entrepreneurially—the tinkerers and the question-askers—will be the ones who tend to be almost immune to automation in the workforce. The potential decline of “learn to code” doesn’t mean that the technologists are doomed to become the authors of their own obsolescence, nor that the English majors were right all along (I wish). Rather, the turmoil presented by AI could signal that exactly what students decide to major in is less important than an ability to think conceptually about the various problems that technology could help us solve. The next great Silicon Valley juggernaut might be seeded by a humanities grad with no coding expertise or a computer-science grad with lots of it. After all, the discipline has always been about more than just learning the ropes of Python and C++. Identifying patterns and piecing them together is its essence. In that way, the answer to the question of what happens next in higher education may lie in what the machines can’t do. Royce pointed me toward Moravec’s paradox, the observation that AI shines at high-level reasoning and the kinds of skills that are generally considered to reflect cognitive aptitude (think: playing chess), but fumbles with the basic ones. The curiosity-driven instincts that have always been at the root of how humans create things are not just sticking around in an AI world; they are now more important than ever. Thankfully, students have plenty of ways to get there. "

"Erotica, Atwood, and 'For Dummies': The Books Behind Meta’s Generative AI - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/09/books3-ai-training-meta-copyright-infringement-lawsuit/675411"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce What I Found in a Database Meta Uses to Train Generative AI Nobel-winning authors, Dungeons and Dragons , Christian literature, and erotica all serve as datapoints for the machine. Editor’s note: This article is part of The Atlantic ’s series on Books3. You can search the database for yourself here , and read about its origins here. This summer, I reported on a data set of more than 191,000 books that were used without permission to train generative-AI systems by Meta, Bloomberg, and others. “Books3,” as it’s called, was based on a collection of pirated ebooks that includes travel guides, self-published erotic fiction, novels by Stephen King and Margaret Atwood , and a lot more. It is now at the center of several lawsuits brought against Meta by writers who claim that its use amounts to copyright infringement. Books play a crucial role in the training of generative-AI systems. Their long, thematically consistent paragraphs provide information about how to construct long, thematically consistent paragraphs—something that’s essential to creating the illusion of intelligence. Consequently, tech companies use huge data sets of books, typically without permission, purchase, or licensing. (Lawyers for Meta argued in a recent court filing that neither outputs from the company’s generative AI nor the model itself are “substantially similar” to existing books.) In its training process, a generative-AI system essentially builds a giant map of English words—the distance between two words correlates with how often they appear near each other in the training text. The final system, known as a large language model, will produce more plausible responses for subjects that appear more often in its training text. (For further details on this process, you can read about transformer architecture , the innovation that precipitated the boom in large language models such as LLaMA and ChatGPT.) A system trained primarily on the Western canon, for example, will produce poor answers to questions about Eastern literature. This is just one reason it’s important to understand the training data used by these models, and why it’s troubling that there is generally so little transparency. With that in mind, here are some of the most represented authors in Books3, with the approximate number of entries contributed: Although 24 of the 25 authors listed here are fiction writers (the lone exception is Betty Crocker), the data set is two-thirds nonfiction overall. It includes several thousand technical manuals; more than 1,500 books from Christian publishers (including at least 175 Bibles and Bible commentaries); more than 400 Dungeons & Dragons – and Magic the Gathering –themed books; and 46 titles by Charles Bukowski. Nearly every subject imaginable is covered (including How to Housebreak Your Dog in 7 Days ), but the collection skews heavily toward the interests and perspectives of the English-speaking Western world. Many people have written about bias in AI systems. An AI-based face-recognition program, for example, that’s trained disproportionately on images of light-skinned people might work less well on images of people with darker skin—with potentially disastrous outcomes. Books3 helps us see the problem from another angle: What combination of books would be unbiased? What would be an equitable distribution of Christian, Muslim, Buddhist, and Jewish subjects? Are extremist views balanced by moderate ones? What’s the proper ratio of American history to Chinese history, and what perspectives should be represented within each? When knowledge is organized and filtered by algorithm rather than by human judgment, the problem of perspective becomes both crucial and intractable. Books3 is a gigantic dataset. Here are just a few different ways to consider the authors, books, and publishers contained within. Note that the samples presented here are not comprehensive; they are chosen to give a quick sense of the many different types of writing used to train generative AI. As above, book counts may include multiple editions. As AI chatbots begin to replace traditional search engines, the tech industry’s power to constrain our access to information and manipulate our perspective increases exponentially. If the internet democratized access to information by eliminating the need to go to a library or consult an expert, the AI chatbot is a return to the old gatekeeping model, but with a gatekeeper that’s opaque and unaccountable—a gatekeeper, moreover, that is prone to “ hallucinations ” and might or might not cite sources. In its recent court filing—a motion to dismiss the lawsuit brought by the authors Richard Kadrey, Sarah Silverman, and Christopher Golden—Meta observed that “Books3 comprises an astonishingly small portion of the total text used to train LLaMA.” This is technically true (I estimate that Books3 is about 3 percent of LLaMA’s total training text) but sidesteps a core concern: If LLaMA can summarize Silverman’s book, then it likely relies heavily on the text of her book to do so. In general, it’s hard to know how much any given source contributes to a generative-AI system’s output, given the impenetrability of current algorithms. Still, our only clue to the kinds of information and opinions AI chatbots will dispense is their training data. A look at Books3 is a good start, but it’s just one corner of the training-data universe, most of which remains behind closed doors. "

"ChatGPT Could Spur the Rebirth of High-School English - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/08/chatgpt-rebirth-high-school-english/675189"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce High-School English Needed a Makeover Before ChatGPT I used to make my students write essay after essay. There was always a better way. Last December, Moby-Dick made one of my students gasp. It wasn’t the first time this had happened (weird book), but nothing about the text itself produced the response. For the final project in my English class for high-school seniors, where we spend a semester reading Moby-Dick , I assigned a pretty standard eight-to-10-page research paper. One student, interested in finance, saw a connection between the plot and the 2008 financial crisis. He spent weeks thinking about the parallels, trying to find a way to make all of the pieces fit together into a cohesive argument about whaling and the exploitations of global capitalism. On the day before the paper was due, I happened to walk past his computer as he watched ChatGPT perform in 10 seconds what had taken him many hours and many cups of coffee. Maybe you have also experienced the distinctive blend of emotions elicited by first using ChatGPT—a deflating sense of wonder, a discomfiting awe. I certainly have. Since the emergence of generative AI last year, trying to envision the world we’re rapidly heading toward has been a vertiginous exercise. Coders may be replaced by algorithmically perfected, non-salary-receiving robots. In 2027, your favorite thing to listen to while walking the dog may be AI Taylor Swift giving you personalized affirmations about getting over your ex and moving on with your life. At the moment, much of that remains in the distance. Meanwhile, teachers like myself are standing at the leading edge of comprehending what our jobs mean now. We have spent the past year feeling stressed, scared, and more than a little bit helpless, commiserating with colleagues over where this is all headed. So much of teaching English has oriented around helping students learn how to write formal, “polished” prose. Now, suddenly, a machine can accomplish that task in seconds. From December onward, I’ve had no way of knowing who (or what) has written what I am grading: 20 percent chatbot? Fifty percent? Not only that, but by the time these young people start careers of their own, they’ll almost certainly have easy access to AI personal assistants that can do their written work for them and predict their needs and desires, all in the name of “efficiency.” What’s the point anymore? And yet, heading into the first full school year under our new robot overlords, I find myself feeling surprisingly buoyant. Much of what English teachers have been expected to do for decades—make students write essays—is no longer useful. Goodbye and good riddance. But AI cannot tear apart what makes teaching meaningful and potentially life-changing to students: the communal experience of being in a classroom. Starting this year, the center of gravity in my classroom is not teaching writing as an “essential skill” that all students need to master; it’s teaching reading. Last year, I predicted that ChatGPT would mark the end of high-school English. Instead, we might already be witnessing its rebirth. My profession was already on pretty shaky foundations before the arrival of chatbots. The English major has been declining practically since Robin Williams got down from the desk in Dead Poets Society. Let’s face it: Books just can’t compete with the pinging of your phone. All love to the Brontë sisters , but our dopamine receptors are powerless against the digital deluge that surrounds us. If this is true for those of us who can remember a world before smartphones, imagine what it’s like for today’s American teenager, who must look at a book the way a grizzly looks at a bear box : Something amazing may be in there, but God knows how they’re supposed to get it out. Still, I’ve had plenty of opportunities to watch students as a book they assumed was impenetrable suddenly opens to them. Grizzly bear, meet peanut-butter cups. Even with SparkNotes and now chatbots, so many high schoolers in my classes have shown the ability to become engaged, incisive readers. If I’m being honest with myself, I’ve had less success with getting them to fall in love with writing. My students are brilliant in all kinds of different ways: They’re dancers and gamers, cooks and climbers, climate activists and fashion designers. There’s no reason to expect them all to be capable of exceptional fiction or poetry or essays. It’s disheartening to find a student so focused on the paper they will have to write when we finish a text, so consumed by anxiety at the prospect of how this essay will affect their chances of getting into college, that they miss out on the experience of reading some great work of art. When we come to the end of a book in class, the usual high-school thing for me to do is have my students write an essay that will show that they Understand the Material, and that the Learning Objectives Have Been Achieved. For years, I’ve burdened them with a 223-slide presentation outlining the process of writing an academic essay: First you make a claim, then you provide evidence for that claim, then you explain how that evidence does indeed support your claim, then you transition, then you do it again. “This is what you will be expected to do in college,” I’ve told them ominously. I’m no computer scientist, but this process—showing them how to perform a sequence of steps in order to accomplish a specific task—doesn’t seem so different from how large language models have been trained. By this point, in my 13 years as a teacher, I have graded thousands of essays. This type of writing, I’ve noticed, has a stultifying effect on students: They stop writing the way they would talk and instead try to write the way they think writing is supposed to sound. They repeat the same idea over and over, padding the pages with fluff that sounds fancy but doesn’t actually say anything. This is why most writing is so bad—because so-called polished writing is exceptionally difficult to produce. Many professional writers aren’t even good writers. Consider this progression: Middle-school students are taught to write the five-paragraph essay so they can write research papers in high school and college; then, as graduate students, publish scholarly articles in academic journals; and finally, doctorate in hand, write a monograph on their way to a tenured position at a prestigious university. I’m sure it goes entirely without saying that this is an antiquated notion of education, and an antiquated notion of writing. Nevertheless, English teachers have sat with untold students dutifully training them in the strictures and forms we’ve received as our intellectual inheritance, with little justification aside from This is what we’ve always done. So this year, my English class will look something like a book club. We’ll read texts and then discuss them, with all the inevitable consonance and contradictions that come from different viewpoints. I’ll focus on extemporaneous writing in the classroom, not the polished essays that students have long been expected to know how to execute. Instead of an eight-to-10-page paper on Moby-Dick , my students will respond to prompts in a spiral notebook; after a couple of weeks, they’ll take that writing and turn it into something to submit. They will be graded, of course, but not on whether the end product conforms to any standardized ideas about academic writing. If the conclusion doesn’t reiterate what was expressed in the introduction, that’s okay. This is the sort of writing that helps students discover their own mind rather than a clever insight into a Miltonic simile. The beauty of reading James Baldwin is not being able to neatly pin his arguments to the wall like perfectly preserved butterflies; it’s about accessing how his writing remains fiercely alive in 2023. Whatever ChatGPT can say or do about a text, it cannot tell us what it’s like to be a person experiencing that text, how it connects to their specific ideas, background, and beliefs. And here’s the thing: Every student is good at this sort of writing. Well, they’re not all great at actually doing it; some of them prefer to write the bare minimum (a sentence or two) and call it done. But when they do do it, they express themselves clearly and effectively, just like they would if you asked them something via text message. After all, it’s possible that the average American teenager in 2023 does more writing, and is more defined by that writing (text messages, Instagram posts), than any generation before them. None of these things is rocket science; teachers have been doing this sort of imaginative work for decades but have always been crowded for space because of the imperatives of the academic essay. I’m in a privileged position, at an independent school shielded from the burdens and predations teachers are experiencing around the country, but there’s no doubt that the paradigm shift is coming for all of us. Reckoning with the existence of generative AI may require an absolute transformation in education policy at all levels, and that’s unlikely to happen quickly. The unsettling truth about AI is that it’s virtually impossible to know how fast things are going to move, and I can’t guarantee that down the line students won’t run into college professors still assigning the academic essay as if nothing has changed. Overwhelmed teachers will do their best to adapt to this new reality despite scarce resources or guidance; others will be prevented from doing so by sclerotic standards and mandates. Students, as ever, will question the efficacy of what they’re being asked to do, and find both wonderfully sophisticated and hilariously boneheaded ways to cheat. Still, the uncertainty that ChatGPT has introduced to all work outside the classroom gives teachers chances for meaningful work inside the classroom. Even in our chatbot world, my students can’t escape Moby-Dick. We will discuss the chapter in which a sailor cuts off a whale’s foreskin and wears it as a cloak, and the part where Herman Melville says that human beings are unable to encounter ultimate reality, but giant salamanders have no trouble at all. There are, after all, still lots of opportunities for Moby-Dick to make a student gasp. "

"Before a Bot Steals Your Job, It Will Steal Your Name - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/08/chatbot-human-names-ai/674979"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce Before a Bot Steals Your Job, It Will Steal Your Name The future of AI looks a lot like Tessa, Ernie, and Amy. In May, Tessa went rogue. The National Eating Disorder Association’s chatbot had recently replaced a phone hotline and the handful of staffers who ran it. But although it was designed to deliver a set of approved responses to people who might be at risk of an eating disorder, Tessa instead recommended that they lose weight. “Every single thing that Tessa suggested were things that led to the development of my eating disorder,” one woman who reviewed the chatbot wrote on Instagram. Tessa was quickly canned. “It was not our intention to suggest that Tessa could provide the same type of human connection that the Helpline offered,” the nonprofit’s CEO, Liz Thompson, told NPR. Perhaps the organization didn’t want to suggest a human connection, but why else give the bot that name? The new generation of chatbots can not only converse in unnervingly humanlike ways; in many cases, they have human names too. In addition to Tessa, there are bots named Ernie (from the Chinese company Baidu), Claude (a ChatGPT rival from the AI start-up Anthropic), and Jasper (a popular AI writing assistant for brands). Many of the most advanced chatbots— ChatGPT, Bard, HuggingChat—stick to clunky or abstract identities, but there are now many new additions to the already endless customer-service bots with real names ( Maya , Bo , Dom ). As generative AI continues to advance, expect a deluge of new human-named bots in the coming years, Suresh Venkatasubramanian, a computer-science professor at Brown University, told me. The names are yet another way to make bots seem more believable and real. “There’s a difference between what you expect from a ‘help assistant’ versus a bot named Tessa,” Katy Steinmetz, the creative and project director of the naming agency Catchword, told me. These names can have a malicious effect, but in other instances, they are simply annoying or mundane—a marketing ploy for companies to try to influence how you think about their products. The future of AI may or may not involve a bot taking your job, but it will very likely involve one taking your name. The very first chatbot, ELIZA, wasn’t capable of much. A therapist bot created by the MIT professor Joseph Weizenbaum in the mid-1960s, ELIZA was more parrot than psychoanalyst, often doing little more than repeating and rephrasing questions that users asked it. Still, people ascribed this janky form of AI with more understanding, creativity, and personality than Weizenbaum had expected. A decade after ELIZA’s debut, Weizenbaum remarked that he was “startled to see how quickly and how very deeply people conversing with [ELIZA] became emotionally involved with the computer and how unequivocally they anthropomorphized it.” Today, the projection of human traits onto computers has a name: the ELIZA effect. The following decades brought chatbots with names such as Parry, Jabberwacky, Dr. Sbaitso, and A.L.I.C.E. (Artificial Linguistic Internet Computer Entity); in 2017, Saudi Arabia granted citizenship to a humanoid robot named Sophia. But that was before AI was convincing enough to feel real. In this new era of generative AI, human names are just one more layer of faux humanity on products already loaded with anthropomorphic features. Although Microsoft’s official name for its chatbot is simply Bing Chat, the AI initially appeared to have an alter ego that called itself Sydney. It was suppressed after professing its love for a journalist, but maybe not permanently. “If you want it to be Sydney,” Microsoft’s chief technology officer said of Bing Chat in May , “you should be able to tell it to be Sydney.” ChatGPT, meanwhile, sends out responses word by word, as if it’s thinking. A rectangle blinks as it types, not unlike when a friend is typing over iMessage. “These are design choices, very thoughtfully done, to create that verisimilitude,” Venkatasubramanian said. “These bots are designed to create an impression of sentience, which, as humans, we are particularly susceptible to.” Names are an easy way to make products feel smarter and more personal. That seems to be especially true of the customer-service bots that companies have been turning to for years, and especially post-ChatGPT. Every bank seems to have its own Erica (Bank of America), Sandi (Santander), or Amy (HSBC). People craving White Castle sliders can now place their order through the company’s drive-through bot, Julia. The bot displays its name on the screen before taking orders—“I’m Julia, a new voice assistant”—and shamelessly encourages customers to order extra food and drinks. Queries to Lufthansa can be directed toward its AI, Elisa—a human-seeming touch that would provide little comfort if the airline lost my luggage. But giving a bot a real name can translate to sales. Research from 2021 found that giving customer-service chatbots anthropomorphic features, including a human name, has “a direct, beneficial relationship with transaction outcomes.” The proliferation of chatbots with human names follows the popularity of Amazon’s Alexa, but the bots don’t “wake up” when their name is called—an issue so present for people named Alexa that it helped inspire a nonprofit organization dedicated to renaming the device. Still, like Alexa, many of the customer-service bots are female-coded products whose sole purpose is to obey commands, though that is not universally true. A spokesperson for Anthropic said the company named its chatbot Claude because it “wanted a warm, friendly name for our model” and “noticed a convention of naming assistants with female names that we wanted to buck.” With Alexa and other home assistants, “you can still physically see the product and know that at the end of the day, it is a technology gadget,” says Merve Hickok, the senior research director at the Center for AI and Digital Policy. “Chatbots are disembodied. Our interactions with chatbots are similar to how we communicate with other humans.” In the ChatGPT era, people might already assume that bots are sentient; addressing one by name doesn’t help. The risk could be especially apparent for chatbots’ most vulnerable users, says Gavin Abercrombie, an AI expert at Heriot-Watt University, in Edinburgh—such as children and adults suffering from dementia. If voice assistants like Alexa could encourage a 10-year-old girl to touch a penny to a live electrical outlet, then a generative AI that can communicate more like a person, and is named like one too, seems destined to backfire. “Giving a device a human name is not necessarily the wrong choice, but it has to be really thought out,” Abercrombie told me. “What are we trying to do? What kind of relationship do we expect the users to have with this?” White Castle’s Julia, which simply facilitates the purchase of hamburgers and fries, is no one’s idea of a sentient bot. But as we enter an era of ubiquitous customer-service chatbots that sell us burgers and plane tickets, such attempts at forced relatability will get old fast—manipulating us into feeling more comfortable and emotionally connected to an inanimate AI tool. Resisting the urge to give every bot a human identity is a small way to let a bot’s function stand on its own and not load it with superfluous human connotations—especially in a field already inundated with ethical quandaries. But for now, bots with human names are becoming unavoidable. My name has so far evaded Silicon Valley, but I doubt it’ll be long before I end up expressing my concerns to an AI-powered Jacob. "

"Revealed: The Authors Whose Pirated Books Are Powering Generative AI - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/08/books3-ai-meta-llama-pirated-books/675063"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce Revealed: The Authors Whose Pirated Books Are Powering Generative AI Stephen King, Zadie Smith, and Michael Pollan are among thousands of writers whose copyrighted works are being used to train large language models. Updated at 1:40 p.m. ET on September 25, 2023 Editor’s note: This article is part of The Atlantic’s series on Books3. Check out our searchable Books3 database to find specific authors and titles. A deeper analysis of what is in the database is here. One of the most troubling issues around generative AI is simple: It’s being made in secret. To produce humanlike answers to questions, systems such as ChatGPT process huge quantities of written material. But few people outside of companies such as Meta and OpenAI know the full extent of the texts these programs have been trained on. Some training text comes from Wikipedia and other online writing, but high-quality generative AI requires higher-quality input than is usually found on the internet—that is, it requires the kind found in books. In a lawsuit filed in California last month, the writers Sarah Silverman, Richard Kadrey, and Christopher Golden allege that Meta violated copyright laws by using their books to train LLaMA, a large language model similar to OpenAI’s GPT-4 —an algorithm that can generate text by mimicking the word patterns it finds in sample texts. But neither the lawsuit itself nor the commentary surrounding it has offered a look under the hood: We have not previously known for certain whether LLaMA was trained on Silverman’s, Kadrey’s, or Golden’s books, or any others, for that matter. In fact, it was. I recently obtained and analyzed a dataset used by Meta to train LLaMA. Its contents more than justify a fundamental aspect of the authors’ allegations: Pirated books are being used as inputs for computer programs that are changing how we read, learn, and communicate. The future promised by AI is written with stolen words. Upwards of 170,000 books, the majority published in the past 20 years, are in LLaMA’s training data. In addition to work by Silverman, Kadrey, and Golden, nonfiction by Michael Pollan, Rebecca Solnit, and Jon Krakauer is being used, as are thrillers by James Patterson and Stephen King and other fiction by George Saunders, Zadie Smith, and Junot Díaz. These books are part of a dataset called “Books3,” and its use has not been limited to LLaMA. Books3 was also used to train Bloomberg’s BloombergGPT , EleutherAI’s GPT-J —a popular open-source model—and likely other generative-AI programs now embedded in websites across the internet. A Meta spokesperson declined to comment on the company’s use of Books3; a spokesperson for Bloomberg confirmed via email that Books3 was used to train the initial model of BloombergGPT and added, “We will not include the Books3 dataset among the data sources used to train future versions of BloombergGPT”; and Stella Biderman, EleutherAI’s executive director, did not dispute that the company used Books3 in GPT-J’s training data. As a writer and computer programmer, I’ve been curious about what kinds of books are used to train generative-AI systems. Earlier this summer, I began reading online discussions among academic and hobbyist AI developers on sites such as GitHub and Hugging Face. These eventually led me to a direct download of “the Pile,” a massive cache of training text created by EleutherAI that contains the Books3 dataset, plus material from a variety of other sources: YouTube-video subtitles, documents and transcriptions from the European Parliament, English Wikipedia, emails sent and received by Enron Corporation employees before its 2001 collapse, and a lot more. The variety is not entirely surprising. Generative AI works by analyzing the relationships among words in intelligent-sounding language, and given the complexity of these relationships, the subject matter is typically less important than the sheer quantity of text. That’s why The-Eye.eu, a site that hosted the Pile until recently—it received a takedown notice from a Danish anti-piracy group—says its purpose is “to suck up and serve large datasets.” The Pile is too large to be opened in a text-editing application, so I wrote a series of programs to manage it. I first extracted all the lines labeled “Books3” to isolate the Books3 dataset. Here’s a sample from the resulting dataset: {"text": "\n\nThis book is a work of fiction. Names, characters, places and incidents are products of the authors' imagination or are used fictitiously. Any resemblance to actual events or locales or persons, living or dead, is entirely coincidental.\n\n | POCKET BOOKS, a division of Simon & Schuster Inc. \n1230 Avenue of the Americas, New York, NY 10020 \nwww.SimonandSchuster.com\n\n---|--- This is the beginning of a line that, like all lines in the dataset, continues for many thousands of words and contains the complete text of a book. But what book? There were no explicit labels with titles, author names, or metadata. Just the label “text,” which reduced the books to the function they serve for AI training. To identify the entries, I wrote another program to extract ISBNs from each line. I fed these ISBNs into another program that connected to an online book database and retrieved author, title, and publishing information, which I viewed in a spreadsheet. This process revealed roughly 190,000 entries: I was able to identify more than 170,000 books—about 20,000 were missing ISBNs or weren’t in the book database. (This number also includes reissues with different ISBNs, so the number of unique books might be somewhat smaller than the total.) Browsing by author and publisher, I began to get a sense of the collection’s scope. Of the 170,000 titles, roughly one-third are fiction, two-thirds nonfiction. They’re from big and small publishers. To name a few examples, more than 30,000 titles are from Penguin Random House and its imprints, 14,000 from HarperCollins, 7,000 from Macmillan, 1,800 from Oxford University Press, and 600 from Verso. The collection includes fiction and nonfiction by Elena Ferrante and Rachel Cusk. It contains at least nine books by Haruki Murakami, five by Jennifer Egan, seven by Jonathan Franzen, nine by bell hooks, five by David Grann, and 33 by Margaret Atwood. Also of note: 102 pulp novels by L. Ron Hubbard, 90 books by the Young Earth creationist pastor John F. MacArthur, and multiple works of aliens-built-the-pyramids pseudo-history by Erich von Däniken. In an emailed statement, Biderman wrote, in part, “We work closely with creators and rights holders to understand and support their perspectives and needs. We are currently in the process of creating a version of the Pile that exclusively contains documents licensed for that use.” Although not widely known outside the AI community, Books3 is a popular training dataset. Hugging Face facilitated its download from the Eye for more than two and a half years; its link stopped working around the time Books3 was mentioned in lawsuits against OpenAI and Meta earlier this summer. The academic writer Peter Schoppert has tracked its use in his Substack newsletter. Books3 has also been cited in the research papers by Meta and Bloomberg that announced the creation of LLaMA and BloombergGPT. In recent months, the dataset was effectively hidden in plain sight, possible to download but challenging to find, view, and analyze. Other datasets, possibly containing similar texts, are used in secret by companies such as OpenAI. Shawn Presser, the independent developer behind Books3, has said that he created the dataset to give independent developers “OpenAI-grade training data.” Its name is a reference to a paper published by OpenAI in 2020 that mentioned two “internet-based books corpora” called Books1 and Books2. That paper is the only primary source that gives any clues about the contents of GPT-3’s training data, so it’s been carefully scrutinized by the development community. From information gleaned about the sizes of Books1 and Books2, Books1 is speculated to be the complete output of Project Gutenberg , an online publisher of some 70,000 books with expired copyrights or licenses that allow noncommercial distribution. No one knows what’s inside Books2. Some suspect it comes from collections of pirated books, such as Library Genesis, Z-Library, and Bibliotik, that circulate via the BitTorrent file-sharing network. (Books3, as Presser announced after creating it, is “all of Bibliotik.”) Presser told me by telephone that he’s sympathetic to authors’ concerns. But the great danger he perceives is a monopoly on generative AI by wealthy corporations, giving them total control of a technology that’s reshaping our culture: He created Books3 in the hope that it would allow any developer to create generative-AI tools. “It would be better if it wasn’t necessary to have something like Books3,” he said. “But the alternative is that, without Books3, only OpenAI can do what they’re doing.” To create the dataset, Presser downloaded a copy of Bibliotik from The-Eye.eu and updated a program written more than a decade ago by the hacktivist Aaron Swartz to convert the books from ePub format (a standard for ebooks) to plain text—a necessary change for the books to be used as training data. Although some of the titles in Books3 are missing relevant copyright-management information, the deletions were ostensibly a by-product of the file conversion and the structure of the ebooks; Presser told me he did not knowingly edit the files in this way. Many commentators have argued that training AI with copyrighted material constitutes “fair use,” the legal doctrine that permits the use of copyrighted material under certain circumstances, enabling parody, quotation, and derivative works that enrich the culture. The industry’s fair-use argument rests on two claims: that generative-AI tools do not replicate the books they’ve been trained on but instead produce new works, and that those new works do not hurt the commercial market for the originals. OpenAI made a version of this argument in response to a 2019 query from the United States Patent and Trademark Office. According to Jason Schultz, the director of the Technology Law and Policy Clinic at NYU, this argument is strong. I asked Schultz whether the fact that books were acquired without permission might damage a claim of fair use. “If the source is unauthorized, that can be a factor,” Schultz said. But the AI companies’ intentions and knowledge matter. “If they had no idea where the books came from, then I think it’s less of a factor.” Rebecca Tushnet, a law professor at Harvard, echoed these ideas, and told me that the law was “unsettled” when it came to fair-use cases involving unauthorized material, with previous cases giving little indication of how a judge might rule in the future. This is, to an extent, a story about clashing cultures: The tech and publishing worlds have long had different attitudes about intellectual property. For many years, I’ve been a member of the open-source software community. The modern open-source movement began in the 1980s, when a developer named Richard Stallman grew frustrated with AT&T’s proprietary control of Unix, an operating system he had worked with. (Stallman worked at MIT, and Unix had been a collaboration between AT&T and several universities.) In response, Stallman developed a “copyleft” licensing model, under which software could be freely shared and modified, as long as modifications were re-shared using the same license. The copyleft license launched today’s open-source community, in which hobbyist developers give their software away for free. If their work becomes popular, they accrue reputation and respect that can be parlayed into one of the tech industry’s many high-paying jobs. I’ve personally benefited from this model, and I support the use of open licenses for software. But I’ve also seen how this philosophy, and the general attitude of permissiveness that permeates the industry, can cause developers to see any kind of license as unnecessary. This is dangerous because some kinds of creative work simply can’t be done without more restrictive licenses. Who could spend years writing a novel or researching a work of deep history without a guarantee of control over the reproduction and distribution of the finished work? Such control is part of how writers earn money to live. Meta’s proprietary stance with LLaMA suggests that the company thinks similarly about its own work. After the model leaked earlier this year and became available for download from independent developers who’d acquired it, Meta used a DMCA takedown order against at least one of those developers, claiming that “no one is authorized to exhibit, reproduce, transmit, or otherwise distribute Meta Properties without the express written permission of Meta.” Even after it had “open-sourced” LLaMA, Meta still wanted developers to agree to a license before using it; the same is true of a new version of the model released last month. (Neither the Pile nor Books3 is mentioned in a research paper about that new model.) Control is more essential than ever, now that intellectual property is digital and flows from person to person as bytes through airwaves. A culture of piracy has existed since the early days of the internet, and in a sense, AI developers are doing something that’s come to seem natural. It is uncomfortably apt that today’s flagship technology is powered by mass theft. Yet the culture of piracy has, until now, facilitated mostly personal use by individual people. The exploitation of pirated books for profit, with the goal of replacing the writers whose work was taken—this is a different and disturbing trend. This article originally stated that Hugging Face hosted the Books3 dataset in addition to the Eye. Hugging Face did not host Books3; rather, it facilitated its download from the Eye. "

"Washington Can Stop the AI Free-for-All - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/08/ai-misinformation-scams-government-regulation/674946"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce The AI Crackdown Is Coming Five ways for Washington to hold Silicon Valley accountable In April, lawyers for the airline Avianca noticed something strange. A passenger, Robert Mata, had sued the airline, alleging that a serving cart on a flight had struck and severely injured his left knee, but several cases cited in Mata’s lawsuit didn’t appear to exist. The judge couldn’t verify them, either. It turned out that ChatGPT had made them all up, fabricating names and decisions. One of Mata’s lawyers, Steven A. Schwartz, had used the chatbot as an assistant—his first time using the program for legal research—and, as Schwartz wrote in an affidavit, “was unaware of the possibility that its content could be false.” The incident was only one in a litany of instances of generative AI spreading falsehoods , not to mention financial scams , nonconsensual porn , and more. Tech companies are marketing their AI products and potentially reaping enormous profits, with little accountability or legal oversight for the real-world damage those products can cause. The federal government is now trying to catch up. Late last month, the Biden administration announced that seven tech companies at the forefront of AI development had agreed to a set of voluntary commitments to ensure that their products are “safe, secure, and trustworthy.” Those commitments follow a flurry of White House summits on AI , congressional testimonies on regulating the technology, and declarations from various government agencies that they are taking AI seriously. In the announcement, OpenAI, Microsoft, Google, Meta, and others pledged to subject their products to third-party testing, invest in bias reduction, and be more transparent about their AI systems’ capabilities and limitations. Read: America already has an AI underclass The language is promising but also just a promise, lacking enforcement mechanisms and details about next steps. Regulating AI requires a lumbering bureaucracy to take on notoriously secretive companies and rapidly evolving technologies. Much of the Biden administration’s language apes tech luminaries’ PR lines about their products’ world-ending capacities, such as bioweapons and machines that “self-replicate.” Government action will be essential for safeguarding people’s lives and livelihoods—not just from the supposed long-term threat of evil, superintelligent machines, but also from everyday threats. Generative AI has already exhibited gross biases and potential for misuse. And for more than a decade, less advanced but similarly opaque and often discriminatory algorithms have been used to screen résumés and determine credit scores , in diagnostic software , and as part of facial-recognition tools. I spoke with a number of experts and walked away with a list of five of the most effective ways the government could regulate AI to protect the country against the tech’s quotidian risks, as well as its more hypothetical, apocalyptic dangers. 1. Don’t take AI companies’ word on anything. A drug advertised for chemotherapy has to demonstrably benefit cancer patients in clinical trials, such as by shrinking tumors, and then get FDA approval. Then its manufacturer has to disclose side effects patients might experience. But no such accountability exists for AI products. “Companies are making claims about AI being able to do X or Y thing, but then not substantiating that they can,” Sarah Myers West, the managing director of the AI Now Institute and a former senior FTC adviser on AI, told me. Numerous tech firms have been criticized for misrepresenting how biased or effective their algorithms are, or providing almost no evidence with which to evaluate them. Mandating that AI tools undergo third-party testing to ensure that they meet agreed-upon metrics of bias, accuracy, and interpretability “is a really important first step,” Alexandra Givens, the president of the Center for Democracy and Technology, a nonprofit that advocates for privacy and human rights on the internet and receives some funding from the tech industry, told me. Companies could be compelled to disclose information about how their programs were trained, the software’s limitations, and how they mitigated potential harms. “Right now, there’s extraordinary information asymmetry,” she said—tech companies tend to reveal very little about how they train and validate their software. An audit could involve testing how often, say, a computer-vision program misrecognizes Black versus white faces or whether chatbots associate certain jobs with stereotypical gender roles (ChatGPT once stated that attorneys cannot be pregnant, because attorneys must be men). All of the experts I spoke with agreed that the tech companies themselves shouldn’t be able to declare their own products safe. Otherwise, there is a substantial risk of “audit washing” —in which a dangerous product gains legitimacy from a meaningless stamp of approval, Ellen Goodman, a law professor at Rutgers, told me. Although numerous proposals currently call for after-the-fact audits , others have called for safety assessments to start much earlier. The potentially high-stakes applications of AI mean that these companies should “have to prove their products are not harmful before they can release them into the marketplace,” Safiya Noble, an internet-studies scholar at UCLA, told me. Clear benchmarks and licenses are also crucial: A government standard would not be effective if watered down, and a hodgepodge of safety labels would breed confusion to the point of being illegible, similar to the differences among free-range, cage-free, and pasture-raised eggs. 2. We don’t need a Department of AI. Establishing basic assessments of and disclosures about AI systems wouldn’t require a new government agency, even though that’s what some tech executives have called for. Existing laws apply to many uses for AI: therapy bots, automated financial assistants, search engines promising truthful responses. In turn, the relevant federal agencies have the subject expertise to enforce those laws; for instance, the FDA could have to assess and approve a therapy bot like a medical device. “In naming a central AI agency that’s going to do all the things, you lose the most important aspect of algorithmic assessment,” Givens said, “which is, what is the context in which it is being deployed, and what is the impact on that particular set of communities?” Read: AI doomerism is a decoy A new AI department could run the risk of creating regulatory capture , with major AI companies staffing, advising, and lobbying the agency. Instead, experts told me, they’d like to see more funding for existing agencies to hire staff and develop expertise on AI, which might require action from Congress. “There could be a very aggressive way in which existing enforcement agencies could be more empowered to do this if you provided them more resources,” Alex Hanna, the director of research at the Distributed AI Research Institute, told me. 3. The White House can lead by example. Far-reaching legislation to regulate AI could take years and face challenges from tech companies in court. Another, possibly faster approach could involve the federal government acting by example in the AI models it uses, the research it supports, and the funding it disburses. For instance, earlier this year, a federal task force recommended that the government commit $2.6 billion to funding AI research and development. Any company hoping to access those resources could be forced to meet a number of standards, which could lead to industry-wide adoption—somewhat akin to the tax incentives and subsidies encouraging green energy in the Inflation Reduction Act. The government is also a major purchaser and user of AI itself, and could require its vendors to subject themselves to audits and release transparency reports. “The biggest thing the Biden administration can do is make it binding administration policy that AI can only be purchased, developed, used if it goes through meaningful testing for safety, efficacy, nondiscrimination, and protecting people’s privacy,” Givens told me. 4. AI needs a tamper-proof seal. Deepfakes and other synthetic media—images, videos, and audio clips that an AI system can whip up in seconds—have already spread misinformation and been used in nonconsensual pornography. Last month’s voluntary commitments include developing a watermark to tell users they are interacting with AI-generated content, but the language is vague and the path forward unclear. Many existing methods of watermarking, such as the block of rainbow pixels at the bottom of any image generated by DALL-E 2 , are easy to manipulate or remove. A more robust method would involve logging where, when, and how a piece of media was created—like a digital stamp from a camera—as well as every edit it undergoes. Companies including Adobe, Microsoft, and Sony are already working to implement one such standard , although such approaches might be difficult for the public to understand. Sam Gregory, the executive director of the human-rights organization Witness, told me that government standards for labeling AI-generated content would need to be enforced throughout the AI supply chain by everybody from the makers of text-to-image models to app and web-browser developers. We need a tamper-proof seal, not a sticker. Read: It’s time to worry about deepfakes again To encourage the adoption of a standard way to denote AI content, Goodman told me, the government could mandate that web browsers, computers, and other devices recognize the label. Such a mandate would be similar to the federal requirement that new televisions include a part, known as a “V-chip,” that recognizes the maturity ratings set by the TV industry, which parents can use to block programs. 5. Build ways for people to protect their work from AI. Multiple high-profile lawsuits are currently accusing AI models, such as ChatGPT and the image-generator Midjourney , of stealing writers’ and artists’ work. Intellectual property has become central to debates over generative AI, and two general types of copyright infringement are at play: the images, text, and other data the models are trained on, and the images and text they spit back out. On the input side, allegations that generative-AI models are violating copyright law may stumble in court, Daniel Gervais, a law professor at Vanderbilt, told me. Making copies of images, articles, videos, and other media online to develop a training dataset likely falls under “fair use,” because training an AI model on the material meaningfully transforms it. The standard for proving copyright violations on the output side may also pose difficulties, because proving that an AI output is similar to a specific copyrighted work—not just in the style of Kehinde Wiley, but the spitting image of one of his paintings—is a high legal threshold. Gervais said he imagines that a market-negotiated agreement between rights-holders and AI developers will arrive before any sort of legal standard. In the EU, for instance, artists and writers can opt out of having their work used to train AI, which could incentivize a deal that’s in the interest of both artists and Silicon Valley. “Publishers see this as a source of income, and the tech companies have invested so much in their technology,” Gervais said. Another possible option would be an even more stringent opt-in standard , which would require anybody owning copyrighted material to provide explicit permission for their data to be used. In the U.S., Gervais said, an option to opt out may be unnecessary. A law passed to protect copyright on the internet makes it illegal to strip a file of its “copyright management information,” such as labels with the work’s creator and date of publication, and many observers allege that creating datasets to train generative AI violates that law. The fine for removing such information could run up to tens of thousands of dollars per work , and even higher for other copyright infringements—a financial risk that, multiplied by perhaps millions of violations in a dataset, could be too big for companies to take. Few, if any, of these policies are guaranteed. They face numerous practical, political, and legal hurdles, not least of which is Silicon Valley’s formidable lobbying arm. Nor will such regulations alone be enough to stop all the ways the tech can negatively affect Americans. AI is rife with the privacy violations, monopolistic business practices, and poor treatment of workers, all of which have plagued the tech industry for years. But some sort of regulation is coming: The Biden administration has said it is working on bipartisan legislation , and it promised guidance on the responsible use of AI by federal agencies before the end of summer ; numerous bills are pending before Congress. Until then, tech companies may just continue to roll out new and untested products, no matter who or what is steamrolled in the process. "

"AI’s Carbon Emissions Are About to Be a Problem - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/08/ai-carbon-emissions-data-centers/675094"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce The Internet’s Next Great Power Suck AI’s carbon emissions are about to be a problem. In Facebook’s youth, most of the website was powered out of a single building in Prineville, Oregon. That data center , holding row upon row of refrigerator-size racks of servers filled with rows of silicon chips, consumed huge amounts of electricity, outstripping the yearly power usage of more than 6,000 American homes. One day in the summer of 2011, as reported in The Register , a Facebook exec received an alarming call: “There’s a cloud in the data center … inside. ” Following an equipment malfunction, the building had become so hot and humid from all the electricity that actual rain , from a literal cloud, briefly drenched the digital one. Now Facebook, or rather Meta, operates well more than a dozen data centers, each much bigger and more powerful than the one in Prineville used to be. Data centers have become the backbone of the internet, running Amazon promotions, TikTok videos, Google search results, and just about everything else online. The thousands of these buildings across the world run on a shocking amount of electricity— akin to the power usage of England —that is in part, if not mostly, generated by fossil fuels. While the internet accounts for just a sliver of global emissions, 4 percent at most, its footprint has steadily grown as more people have connected to the web and as the web itself has become more complex: streaming, social-media feeds, targeted ads, and more. All of that was before the generative-AI boom. Compared with many other things we use online, ChatGPT and its brethren are unique in their power usage. AI risks making every search, scroll, click, and purchase a bit more energy intensive as Silicon Valley rushes to stuff the technology into search engines , photo-editing software , shopping and financial and writing and customer-service assistants, and just about every other digital crevice. Compounded over nearly 5 billion internet users, the toll on the climate could be enormous. “Within the near future, at least the next five years, we will see a big increase in the carbon footprint of AI,” Shaolei Ren, a computer scientist at UC Riverside, told me. Not all of the 13 experts I spoke with agreed that AI poses a major problem for the planet, but even a moderate emissions bump could be destructive. With so many of the biggest sources of emissions finally slowing as governments crack down on fossil fuels, the internet was already moving in the wrong direction. Now AI threatens to push the web’s emissions to a tipping point. That hasn’t quite happened yet, as far as anyone can tell. Almost no data are available for how much carbon popular models such as ChatGPT emit (a spokesperson for OpenAI declined to comment for this article). The emissions from AI are hard to calculate, depending on the computing power used in a data center, the amount of electricity it requires, and how that electricity is generated. Some signs suggest that electricity usage is already ticking upward during the AI boom. Water usage is a rough proxy for electricity demand, because data centers use water to stay cool, and their water usage across the globe is increasing quickly ; Google’s on-site water use rose roughly 20 percent in 2022, Ren said, driven in part by investments in AI that are only growing. Read: America already has an AI underclass Generative AI produces emissions in three ways. First, carbon is burned to build the computer chips and data centers that AI runs on. Second, training a large language or other AI model requires power. Training a system like ChatGPT, for instance, can produce carbon emissions equivalent to those of several, if not several dozen, U.S. homes in a year, Jesse Dodge, a research scientist at the Allen Institute for AI, told me. Third, the chatbot or any other end product requires electricity every time it is used. A language model from Hugging Face emitted about 42 pounds of carbon a day during an 18-day stretch in which it received 558 requests an hour, for a total equivalent to driving about 900 miles. That might seem small, but those numbers could compound quickly as many billions of dollars continue pouring into generative AI. These programs are getting larger and more complex, with training datasets ballooning exponentially and models doubling in size as frequently as every three months. New models are constantly released, old ones frequently retrained. Even if a single chatbot message uses a tiny amount of energy, “we want to chat with anything and everything, and so these unit costs are going to really add up,” Sasha Luccioni, a research scientist at Hugging Face who studies AI and sustainability, told me. As generative AI begins to fully saturate the web, deployment of bots could account for three-fifths of the technology’s emissions, if not far more. Consider Google Search, which is already in the process of getting chatbot functionality. Google receives an average of 150 million search queries an hour , and each AI-powered search result might require five to 10 times as much computing power as a traditional one, Karin Verspoor, the dean of the School of Computing Technologies at RMIT University, in Australia, told me. Data centers are already seeing their power consumption jump due to AI, and McKinsey predicts that data centers’ electricity use will more than double by 2030. Exactly how much of an emissions bump this would be is unclear, but “the bottom line is we have more people doing more sophisticated things on the internet, and that is going to lead to a significant increase in the overall energy,” Vijay Gadepally, a computer scientist at MIT’s Lincoln Laboratory, told me. That the chatbots will be a carbon bomb is far from guaranteed. Even without generative AI, global internet traffic has expanded 25-fold since 2010, but electricity use has climbed more slowly because of improvements in the efficiency of data centers, computer chips, and software. Data centers are asked to do more and more, but “the efficiency of how we produce the computing also goes up pretty fast,” Jonathan Koomey, a former researcher at Stanford who is an expert on the environment and digital technology, told me. While Google has expanded its machine-learning research in recent years, its electricity use has not outpaced the rest of the company’s, according to research from David Patterson, an emeritus professor of computer science at UC Berkeley. Some efficiency improvements will simply be economically necessary to turn a profit. OpenAI CEO Sam Altman has described the computing costs of ChatGPT as “ eye-watering. ” On its current path, AI could burn itself out before it burns up the planet. In other words, although generative AI will require more computation, it may not proportionally increase electricity demand. Nor is rising power usage guaranteed to increase emissions as the world turns to renewable energy, Mark Dyson, the managing director of the carbon-free-electricity program at the think tank RMI, told me. Spokespeople at Meta, Google, and Microsoft all pointed me to the investments they are making in renewable energy and reduced power and water use at their data centers as part of ambitious emissions-reduction targets. But those improvements could take years, and the generative-AI boom has already started. The need for data centers running AI to have a lot of power at all times could lead them to stick with at least some, if not substantial, fossil-fuel sources , Luccioni said. You can easily burn more coal or natural gas when needed , but you can’t make the wind blow harder. Even if all of these efficiency improvements continue—in hardware, software, and the grid—they may not entirely cancel out the growing computational intensity of AI, Luccioni said, a phenomenon sometimes known as the rebound effect. When technology grows more efficient, the extra resources fuel more demand. More efficient coal-burning in the 19th century only accelerated industrialization, resulting in more factories running on coal; wider highways don’t ease congestion but lead more people to drive and can create even more traffic. Data centers and AI programs that use less electricity might just allow tech companies to cram generative AI into more websites and software. Silicon Valley’s business model, after all, relies on getting people to spend as much time as possible on websites and apps. A chatbot that emits less carbon per message, multiplied over exponentially more messages, would still increase emissions. Read: The future of recycling is Sorty McSortface The carbon footprint of generative AI doesn’t need to grow exponentially to threaten the planet. Meeting our ambitious climate targets will require decreasing emissions across every sector, and AI makes it much harder to stabilize, let alone shrink, the internet’s share. Even if the tonnage of carbon the internet pumps into the atmosphere didn’t budge for decades—an improbably optimistic scenario—and everything else in the world reduced its emissions enough to stop warming at 1.5 degrees Celsius, as is the goal of the Paris agreement, that would still be “nowhere near enough” to meet the target, as one 2020 opinion paper in the journal Patterns put it. As AI and other digital tools help other sectors become greener —improving the efficiency of the grid, enhancing renewable-energy design, optimizing flight routes—the internet’s emissions may continue creeping up. “If we’re using AI, and AI is being sold as pro-environment, we’re going to increase our use of AI throughout all sectors,” Gabrielle Samuel, a lecturer in environmental justice and health at King’s College London, told me. Perhaps the most troubling aspect of AI’s carbon footprint is that, because the internet’s emissions have always been relatively small, almost no one is prepared to deal with them. The Inflation Reduction Act, the historic climate law Congress passed last year, doesn’t mention the web; activists don’t chain themselves to data centers; we don’t teach children to limit their search queries or chatbot conversations for the sake of future generations. With so little research or attention given to the issue, it’s not clear that anybody should. Ideally AI, like coal-fired power plants and combustion-engine cars, would face the economic and regulatory pressure to become emissions-free. Similar to how the EPA sets emissions requirements for new vehicles, the government could create ratings or impose standards for AI model efficiency and the industry’s use of renewable-energy sources, Luccioni said. If a user asks Google to decide whether a photo is of a cat or a dog, a less energy-intensive model that is 96 percent accurate, instead of 98 percent, might suffice, Devesh Tiwari, an engineer at Northeastern University, has shown. And does the world really need AI-powered beer brewing ? The internet can appear untethered from the physical world: digital and virtual, two-dimensional, in cyberspace instead of material space. A chatbot is not visibly plugged into a smokestack belching gray plumes, does not secrete the acrid smell of gasoline from an exhaust pipe. But the data centers and computer chips it connects to, and the electricity and carbon they generate, are of our world—and our problem. "

"Wimbledon’s AI Announcer Was Inevitable - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/07/wimbeldon-ai-chatbot-commentators/674628"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce Wimbledon’s AI Announcer Was Inevitable Sports commentary has long been trending toward vanilla broadcasters. Why not have bots finish the job? The Wimbledon announcer sounds a little like Helen Mirren if she’d just been hit with a polo mallet. I’m watching match highlights between Ons Jabeur and Magdalena Fręch on the tournament’s website when a voice says, “Jabeur, from Tunisia, will play Fręch, from Poland, on the renowned No. 1 court in the first round.” Fręch is mispronounced, as is Tunisia , and the word renowned is used oddly dispassionately, as if it were being repeated for a competitor at a spelling bee. This is a commentary chatbot, introduced with considerable fanfare at the All England Club this year. Another version, a “male” voice, sounds like your uncle from Queens trying to do a Hugh Grant impression. These AI commentators provide “play-by-play narration” for highlight reels published online. They are the result of a partnership between the All England Club and its longtime corporate sponsor IBM, which has been part of Wimbledon for so long that it introduced the “Data Entry Keypad” back when John McEnroe and Martina Navratilova were still playing. Nothing about the technology feels ready for prime time, and it seems that Wimbledon and IBM know it. It’s limited to short clips, and the feature is nearly hidden on Wimbledon’s site—it requires you to click on a video, then click on tiny headphones in the corner, then choose “AI Commentary” mode. But IBM explicitly said in its Wimbledon press release that the goal is to eventually have AI commentary during some of the actual matches, and the European Broadcasting Union has “cloned” the voice of a major commentator that it plans to deploy via AI at an upcoming event. This is, in many ways, the logical direction that the world of sports broadcasting has been trending toward for many years now. Your favorite sporting events are not yet broadcast by robots, but it sometimes seems like they already are. Powered by a large language model that is trained on specific Wimbledon terminology such as gentlemen’s draw instead of men’s draw , the bot first identifies highlight-worthy videos based on factors including crowd noise and player fist pumps. Gregor Hastings, an IBM spokesperson, said in an email that “the commentary is designed to be simple and not too overbearing,” but the end result—a few bland phrases at the conclusion of some points—is painfully boring. That is especially true when compared with the prickly observations of, say, McEnroe, the famously tempestuous former player who has long been a broadcaster for ESPN. McEnroe’s act has cooled in recent years (when was the last time you heard a classic “You cannot be serious” ?), but he’s still far more animated than his younger colleague at Wimbledon, Chris Fowler—a perfectly professional announcer whose calm cadence is interchangeable between college football and tennis and even hockey. This mirrors what has happened in sports broadcasting in general. In the early, formative days of sports television—think the 1960s and ’70s—the broadcaster himself (and it was almost always him self) was the star. And why wouldn’t he have been? He was, after all, the only one talking. For years, broadcasters were as much showmen as they were commentators. They had distinctive styles and clearly defined personalities, whether Mel Allen or Bob Costas in baseball or John Madden or Pat Summerall in football. Much of this evolved from sports television’s biggest star of all, Howard Cosell, whose elliptical style and brashly outspoken nature made him so famous that he regularly outshined the games and players themselves. He starred in a Woody Allen mov ie and became a bit of a national conscience, famously telling the world on Monday Night Football that John Lennon had been killed. It certainly helped that for so long, the audio and visuals of a sports broadcast were so lacking that you needed a voice to guide you through games. In today’s HD age, it’s remarkable to watch old highlights and realize just how difficult it is to decipher what’s going on. This was the prevailing mindset of sports television for decades, to the point that Monday Night Football hired the comedian Dennis Miller as a color analyst even though, until his first assignment, Miller had never attended a football game in person. This also led to a spate of local-sports-broadcast personalities who would become more synonymous with their teams than the players on the field were, including the Cubs’ Harry Caray, the Phillies’ Harry Kalas, the Dodgers’ Vin Scully, and the Cardinals’ Joe Buck (as a Cardinals fan, I think I’ve heard Buck’s voice more in my life than I have my father’s). These regional broadcasters, because of their ties to the community and their ubiquity, became local treasures, even civic institutions: When you turned on the radio and heard Ernie Harwell’s voice, you knew you were in Detroit. Caray became such a Chicago staple that the Chicago Sports Museum is adjacent to Harry Caray’s restaurant , and Caray’s statue outside Wrigley Field is perhaps more famous than any player’s statue that is out there. Even if you didn’t watch sports regularly, if you lived in these towns, these were your local celebrities. But in the past decade or so, this has begun to change. These beloved older announcers, as they have retired or died, have been replaced by bland, safe, mostly personality-free talking heads hired specifically to be noticed as little as possible. Each one sounds the same, down to the same accent. This makes sense when you consider the transitory nature of broadcasting itself: You don’t want to embrace that yinzer accent when you might get transferred to Topeka next week. In an age when networks are terrified of a broadcaster saying something that will get them pilloried on social media, the job has become anodyne and hopelessly watered down. But the transition to AI announcers is even more of a function of most networks’ corporate contracts. National broadcast entities such as ESPN and Fox have billion-dollar deals with the sports leagues, which have control over who is selling their games to the wider public. More and more, regional networks such as YES Network and Bally Sports (which is now bankrupt) are partly owned by the teams themselves, which have zero interest in some wild card going rogue and criticizing their team—a battle that has been going on for a long time. If you are a broadcaster for, say, the Yankees, the word Yankees is right there on your paycheck in a way it likely wasn’t in the past. You are incentivized not to stand out—and not to hurt the brand. Why not just take the next step and employ bots? This is particularly pertinent for a tournament such as Wimbledon, a famously stuffy event that is notoriously controlling of its image, to the point that until this year, women players had to wear white underwear (the men still do). If ever there was a tournament that would want to program precisely what its broadcasters say—to have an AI bot do exactly what it is told—it would be Wimbledon. Sure, it’s difficult to imagine the Super Bowl being broadcast by chatbots. But for smaller events or more niche sports, AI sure looks like a quick and easy way to cut costs—to make telecasts, in that corporate parlance, “more efficient.” If networks think you won’t be able to tell or just won’t care, why would they pay an actual human? Witness, most recently, ESPN’s sweeping layoffs just last week , which cut some of the biggest names in sports broadcasting, including Jeff Van Gundy, Suzy Kolber, Jalen Rose, and many others. The networks have become less partners of the leagues and more subjects entirely at the mercy of leagues’ whims and their stomach for risk management. Robots, in the end, are much more easily controlled. But perhaps all of these networks and tournaments are missing an overarching and vital point: Fans want to be upset by announcers. Cosell became such a huge star because fans were consistently infuriated by him. (The NFL commissioner Pete Rozelle once compared him to Attila the Hun. ) Having a personality in the booth—or, jeez, you know, a person —provides a connection to the sport that every fan craves, even if it’s a negative connection. Even if it makes us mad. Especially if it makes us mad. Just consider Peacock’s experiment last year. For one of the MLB games it shows on Sunday mornings, the network showed a game that had no broadcasters at all. It is easy to see, particularly if you’ve been annoyed by broadcasters before, why you might find this calming, even soothing in a zen way—just ballpark sounds, no pomp and circumstance. But fans hated it. They found it unnerving, off-putting, and confusing: Without a person watching the game with them, it was difficult to tell what was going on. The game stops becoming a sport; it’s just an activity. It’s just something else happening, in the face of an indifferent Nature. This is the danger of AI that I suspect Wimbledon is missing: Without people to tell us how it feels to be in the presence of the greatest tennis players in the world, viewers have a difficult time finding it particularly important to be invested at all. AI broadcasters aren’t there, aren’t watching, and don’t care. So why, in the end, should we? "

"Why Meta Is Breaking Its Own Walled Garden - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/07/meta-microsoft-llama-2-ai-walled-garden-facebook/674824"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce Tech Companies’ Friendly New Strategy to Destroy One Another Meta has decided that it’s time to open up the internet’s walled gardens. Be wary. More than a decade ago, in a prescient essay for Scientific American , the inventor of the World Wide Web denounced what Facebook and other tech giants were doing to his signature invention. “Why should you care?” Tim Berners-Lee wrote at the time. “Because the Web is yours.” These companies, he warned, were restructuring the web itself, turning an expanse of interconnected websites all built on the same open infrastructure into a series of “fragmented islands” where users were kept hostage. On Facebook’s island, he wrote, people give over their entire digital life for the chance to connect with their friends, but have no way to transfer their information to any other platform. Once captive, users upload photos, add friends, send messages, click ads, and react to posts, all the while leaving a trail of information from which Facebook can profit. The more they do these things, the harder leaving becomes—so much of people’s digital life is nested in Facebook, rather than in Facebook’s rivals. The logic extends to other tech platforms too. On Apple’s island, Berners-Lee explained, iTunes users can tap into an immense catalog of music but can’t easily share it with anyone. “You are trapped in a single store, rather than being on the open marketplace,” Berners-Lee wrote. “For all the store’s wonderful features, its evolution is limited to what one company thinks up.” That was 2010. Since then, with the aggressive development of Apple’s App Store, Facebook’s strategic acquisitions of Instagram and WhatsApp, and many other protectionist moves that have made tech’s most dominant companies even more powerful, the web’s fragmented islands—or “walled gardens,” as Berners-Lee also called them—have grown only more secluded. But lately, a funny thing has happened. As tech giants face mounting antitrust scrutiny and try to navigate the development of generative AI technology, the most powerful companies in Silicon Valley are attempting to signal their open-web bona fides. Meta, the company formerly known as Facebook, has become a particularly prominent voice. Last week, it announced that it was partnering with Microsoft on the release of its latest large language model, Llama 2 , which it is making openly available for free. That means that, unlike its nearest rival, GPT-4 , which users can pay to license from OpenAI, developers will be able to download Llama 2’s code, tinker with it, and build new things on top of it, dramatically expanding access to generative AI technology—and potentially leaving OpenAI out to dry in the process. Around the same time, Meta announced that its Twitter copycat, Threads , will eventually be interoperable with small competing social platforms such as Mastodon and WordPress. If any of this sounds like the first step into a wonderful new era of ungated collaboration, it’s not. These gestures toward openness aren’t the product of some sudden, soul-cleansing instinct to cede power. Quite the opposite. Lowering the garden walls ever so slightly works in service of entrenching Meta’s power and ensuring that the company is just as indispensable to the next era of computing as it was to the last one. In his Facebook post announcing the Llama 2 release, Mark Zuckerberg co-opted the gospel of openness, arguing that it would “unlock more progress” and improve safety for generative AI more broadly by enabling more developers to build these technologies and identify potential problems and fixes. It’s not exactly a novel idea: Some of AI’s most prominent ethicists have repeatedly raised concerns about black-box AI models being concentrated in the hands of just a few multibillion-dollar companies. But Zuckerberg is decidedly not one of AI’s most prominent ethicists. He is, instead, a person who not only runs one of those multibillion-dollar companies, but is also responsible for building and ruthlessly defending one of the internet’s most infamous walled gardens. This is the same company that has prohibited academics from scraping data from its products for the purposes of research, neutralized competitors by acquiring them , and actively made it harder for rival platforms to use Facebook’s features. When the video platform Vine wanted users to be able to find their Facebook friends through its app, Zuckerberg personally approved the order ensuring that they couldn’t. When people started posting links to Instagram photos on Twitter, Facebook prevented the links from generating full image previews, rendering them mostly useless for nearly a decade until the policy changed. Read: Ben Franklin would have loved Bluesky It isn’t difficult to understand why Meta would be flirting with a more open approach. For starters, giving away Llama 2 for free will help the company speed up adoption to compete with OpenAI. Besides, offering free access to powerful tools and then figuring out how to make gobs of money from them later is kind of Meta’s thing: It did the same with Facebook before ever charging advertisers a dime. The idea that social media should be decentralized —enabling different networks to plug into one another, rather than hoarding every user for themselves—is also having something of a moment among the extremely online. That’s mostly due to Twitter’s Elon Musk–induced implosion , which has sent former Twitter users on a search for alternatives en masse. If the internet is indeed transforming from a series of fragmented islands into something more like an archipelago, Zuckerberg is already staking his turf. Read: The battle for the soul of the web To Meta’s credit, as Zuckerberg dutifully noted in his post, the company does have a history with open-source development of machine-learning technology. And the long-standing walls around just about every other part of its business, including its billions of users, arguably have offered some benefits beyond profits. At least in theory, those barriers help the company protect user privacy and enforce its standards and policies, thereby taming some of the chaos it has unleashed on the world. Meta’s enforcement record, however, has been inconsistent at best—and utterly lacking at worst. Despite this already lax policing, what Meta is doing now with Threads and Llama 2 will make enforcing its own rules even more difficult for the company. If Threads becomes interoperable with other platforms such as Mastodon—allowing posts to flow back and forth between servers—Meta will face rule breakers from a whole bunch of other networks, including ones where just about anything goes. (So-called federated social media is already home to an astonishing volume of child-abuse material, according to a new report from the Stanford Internet Observatory.) With Llama 2, Meta has invested in AI guardrails designed to prevent the worst abuses, but as has been the case for other open-source models , once developers have their hands on it, people will inevitably find ways to jump those guardrails, and Meta will have limited control over what those people do on the other side. All of this can seem like a moderation nightmare for Meta—until you consider that the company might use its newfound excitement about abdicating control as an excuse to abdicate even more responsibility. If Meta’s open to everyone, then maybe its problems are everyone else’s. Like Berners-Lee, many people deeply believe in the dream of an open web. But the danger right now is that the performance of this belief can easily cover up a canny business strategy. Despite its public framing, Llama 2 isn’t quite what purists would call open source. In the fine print, its community agreement stipulates that although most developers can freely access the model, anyone with more than 700 million monthly users will have to get a license from Meta first. Tough luck for Meta’s competitors such as Snap and Telegram , who just happen to miss the cutoff. "

"AI Can Finally Say My Name Correctly - The Atlantic"

"https://www.theatlantic.com/technology/archive/2023/07/ai-voice-assistants-name-pronunciation/674731"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce A Voicebot Just Left Me Speechless Generative AI has solved a problem that has plagued my voice assistants for years. It’s not that hard to say my name, Saahil Desai. Saahil: rhymes with sawmill , or at least that gets you 90 percent there. Desai: like decide with the last bit chopped off. That’s really it. More often than not, however, my name gets butchered into a menagerie of gaffes and blunders. The most common one, Sa -heel , is at least an honest attempt—unlike its mutant twin, a monosyllabic mess that comes out sounding like seal. Others defy all possible logic. Once, a college classmate read my name, paused, and then confidently said, “Hi, Seattle.” But the mispronunciations that bug me the most aren’t uttered by any human. They come from bots. All day long, Siri reads out my text messages through the AirPods wedged into my ears —and mangles my name into Sa- hul. It fares better than the AI service I use to transcribe interviews, which has identified me by a string of names that seem stripped from a failed British boy band (Nigel, Sal, Michael, Daniel, Scott Hill). Silicon Valley aspires for its products to be world-changing, but evidently that also means name-changing. Or at least that’s what I thought. Listen to this: It’s an AI voice named Adam from ElevenLabs, a start-up that specializes in voice cloning. (It’s sort of like the DALL-E of audio.) This bot not only says my name well; it says my name better than I can. After all, Saahil comes from Sanskrit, a language I do not speak. The end result is a dopamine hit of familiarity, an amazing feeling that’s like the tech equivalent of finding a souvenir key chain with your name on it. In addition to chatbots that can write haiku and artbots that can render a pizza in the style of Picasso, the generative-AI revolution has unleashed voicebots that can finally nail my name. Just as ChatGPT learns from internet posts, ElevenLabs has trained its voices on a huge volume of audio clips to figure out how to talk as people do—at least 500,000 hours , compared with tens or hundreds of hours of audio with earlier speech models. “We have spent the last two years developing a new foundational model for speech,” ElevenLabs CEO Mati Staniszewski wrote in an email. “It means our model is context-aware and language agnostic and therefore better able to pick-up on nuances like names, as well as delivering the intonation and emotions that reflect the textual input.” The data that are part of newer voicebots might include any number of websites dedicated to pronouncing things , and if someone has correctly said your name in an audiobook, a podcast, or a YouTube video, newer AI models might have it down. Companies such as Amazon, Google, Meta, and Microsoft are also developing more advanced voicebots—although they’re still a mixed bag. I tested the same sentence—“C’mon, it’s not that hard to say Saahil Desai”—on AI voice programs from each of them. They all could handle Desai, but I was not greeted with a chorus of perfect pronunciations of Saahil. Amazon’s Polly software, perhaps even worse than Siri, thinks my name is something like Saaaaal: Both Google Cloud and Microsoft Azure were inoffensive but not perfect, slightly twisting Saahil into something recognizably foreign. Nothing could beat ElevenLabs, but Voicebox, an unreleased tool from Meta that the company recently touted as a “breakthrough in generative AI for speech,” got very close: Computers can now say so many more names than just my own. “I noticed the same thing the other day when my student and I created a recording on ElevenLabs of CNN’s Anderson Cooper saying ‘Professor Hany Farid is a complete and total dips**t’ (it’s a long story),” Hany Farid, a UC Berkeley computer scientist, wrote in an email. “I was surprised at how well it pronounced my name. I’ve also noticed that it correctly pronounces the names of my non-American students.” Other tricky names I tested also fared well: ElevenLabs nailed Lupita Nyong’o and Timothée Chalamet, although it turned poor Pete Buttigieg’s last name into a very unfortunate Buttygig. That AI voices can now say unusual names is no small feat. They face the same pronunciation struggles that leave many humans stumped; names like Giannis Antetokounmpo don’t abide by the rules of English, while even a simpler name can have multiple pronunciations (And rea or And rea?) or spellings (Michaela? Mikayla? Michela?). A name might still fall flat to our ears if an AI voice’s color and texture ring more HAL 9000 than human, Farid said. Previous generations of voice assistants—Siri, Alexa, Google Assistant, your car’s GPS—just didn’t have enough information to get through all of these steps. (In some cases, you can provide that information yourself: A spokesperson for Apple told me that you can manually input a name’s phonetic spelling into the Contacts app to tweak how Siri reads it.) Over the years, this technology “really sort of plateaued,” Farid wrote. “It was just really struggling to get through that uncanny valley where it’s sort of human-like, but also a little weird. And then it just blasted through the door.” Advances in “deep-learning” techniques inspired by the human brain can more readily spot patterns in pitch, rhythm, and intonation. That is the weird contradiction of AI right now: Even as this technology is prone to biases that can alienate users (voice assistants more frequently misidentify words from Black speakers than white speakers), it can also help pop smaller feelings of alienation that bubble up. To constantly hear bots bungle my name is a digital indignity that reminds me that my devices do not seem made with me in mind, even though Saahil Desai is a common name in India. My blue iPhone 12 is a six-inch slab that contains more of me than any other single thing in my life. And yet it still screws up the most basic thing about my identity. But a world in which the bots can understand and speak my name, and yours, is also an eerie one. ElevenLabs is the same voice-cloning tech that has been used to make believable deepfakes—of a rude Taylor Swift , of Joe Rogan and Ben Shapiro debating Ratatouille , of Emma Watson reading a section of Mein Kampf. An AI scam pretending to be someone you know is far more believable when the voice on the other end can say your name just as your relatives do. Once it became readily clear that I couldn’t stump ElevenLabs, I slotted in my middle name, Abhijit. Out came a terrible mess of syllables that would never fool me. Okay fine: I admit it’s actually pretty hard to say Saahil Abhijit Desai. "

"Here Comes the Second Year of AI College - The Atlantic"

"https://www.theatlantic.com/ideas/archive/2023/08/ai-chatgpt-college-essay-plagiarism/674928"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce Here Comes the Second Year of AI College Universities still aren’t sure whether to embrace the technology or ban it. W hen ChatGPT entered the world last fall, the faculty at SUNY Buffalo freaked out. Kelly Ahuna, the university’s director of academic integrity, was inundated by panicked emails. “It has me thinking about retiring,” one English professor confessed. He had typed a prompt into ChatGPT and watched in horror as an essay unfurled on-screen. There were errors, sure: incorrect citations, weird transitions. But he would have given it a B-minus. He anticipated an onslaught of undetectable AI plagiarism. Ahuna found herself as something of a spiritual mentor, guiding faculty through their existential angst about artificial intelligence. The first year of AI college was marked by mayhem and mistrust. Educational institutions, accustomed to moving very slowly, for the most part failed to issue clear guidance. In this vacuum, professors grew suspicious of students who turned in particularly grammatical essays. Plagiarism detectors flagged legitimate work as AI-generated. Over the summer, some universities and colleges have regrouped; they’re trying to embrace AI at the institutional level, incorporating it into curriculum and helping instructors adapt. But the norm is still to let individual educators fend for themselves—and some of those individuals seem to believe that they can keep teaching as if generative AI didn’t exist. Read: The first year of AI college ends in ruin Modernizing higher education is a formidable task. I graduated from college this past spring. Before the pandemic, my professors insisted that we print assignments out and hand them in—forget submitting online. Although ChatGPT was available for nearly my entire senior year, the university administration sent out only one announcement about it, encouraging faculty to understand the implications of the technology. My friends, meanwhile, talked incessantly about it. I don’t know anyone who wrote an entire paper with ChatGPT—or who would admit to it, at least—but people used it in other ways. Some asked it to generate practice-exam questions for them to solve. Others turned to it for help with their philosophy reading, asking the chatbot to explain, say, Parfit’s definition of a self-effacing theory. One of my friends asked ChatGPT how to get over her ex-boyfriend. (The advice was generic but excellent.) But only one of my professors ever mentioned it: Halfway through the spring semester, my computer-science professor announced that we couldn’t use ChatGPT to complete our codes. Then he said he would rely on the honor system. Heading into the second year of AI college, some institutions are trying to develop a less technophobic approach. According to Kathe Pelletier, a director at the tech-focused education nonprofit Educause, the most enthusiastic AI adopters tend to be public universities or community colleges that serve large, diverse student bodies and see education as a means of social mobility. Arizona State University is piloting an introductory writing course in which an AI bot offers feedback on students’ work. The class is taught to remote learners at a low cost, and the AI could allow for something like peer feedback for students who take classes alone, on their own schedule. Administrators at the University of Tennessee at Knoxville have organized a professor-led task force to suggest different ways for faculty to add generative AI to the classroom. The University of Florida launched a $70 million AI initiative in 2020 with funding from the chip-manufacturing giant Nvidia. Sid Dobrin, an English professor who is part of the initiative, says that it will sponsor a competition this year in which students can win prize money for the most creative use of generative text or image AI. These schools are preparing to feed employers’ hunger for AI-savvy graduates. “I always say: You are not going to lose your job to AI,” Dobrin told me. “You are going to lose your job to somebody who understands how to use AI.” Other universities, however, still have no overarching institutional posture toward AI. Administrators are wary of announcing policies that could age poorly. Professors are left to figure out how to leverage the technology on their own. In its defense, this stance preserves academic autonomy and encourages experimentation. For example, the teacher of Harvard’s introductory computer-science course deployed a teaching-assistant chatbot this summer built based on OpenAI’s code. But the hands-off institutional approach also forces instructors, many of whom have yet to master the “Mute” button on Zoom, to be at the vanguard of a technology that isn’t fully understood even by the people who created it. In a recent informal poll by Educause, 40 percent of respondents said that they weren’t aware of anyone at their institution taking responsibility for decisions around how generative AI should be used. “A president or provost is thinking, Should I jump on this only to have it become the most unpopular thing in the world? ” Bryan Alexander, who teaches at Georgetown University’s school of learning, design, and technology, says. Some academics have been eager to add the alien technology to their classroom. Ted Underwood, who teaches English and information science at the University of Illinois at Urbana-Champaign, says that every student should learn the basics of AI ethics. He likens the topic to the tenets of democracy, which even people who won’t pursue political science need to understand. Other professors see AI as a way to enliven instruction. The new introductory writing course at the University of Utah asks students to compare sonnets written by William Shakespeare, Pablo Neruda, and ChatGPT; professors say that using an AI bot is the easiest way to generate usefully bad poems. Another faction within academia sees generative AI as an enemy. In the age of large language models, a student’s writing assignment can no longer reliably confirm whether they’ve understood a topic or read a text. Weekly reading responses and discussion posts, once a staple of higher education, seem useless. Some instructors are trying to adopt countermeasures. One SUNY Buffalo faculty member told Kelly Ahuna that he would keep his weekly online quizzes but employ technology that tracks students’ eye movements to detect potential cheating. Others seem to hope that prohibition alone can preserve the familiar pre-ChatGPT world. Most instructors at Bryn Mawr College have declared that any use of AI tools counts as plagiarism, says Carlee Warfield, the head of the school’s honor board. Darren Hick, a philosophy professor at Furman University, told me he refuses to abandon take-home essays. In his view, in-person exams aren’t real philosophy. They leave no time for rumination and serious engagement with a thinker’s work. “It’s gimmicky,” Hick said. “My pedagogy is good, my students learn, and I don’t like the idea of having to upend what’s been a tradition in philosophy for millennia because somebody has a new technology that students can use to cheat.” Read: The college essay is dead Many of the professors and administrators I spoke with likened generative AI to earlier waves of technological change; perhaps an analogy offered perspective and solace when confronting something so mystifying. They compared it to Wikipedia (riddled with inaccuracies), to calculators (students still learn long division), and even to microwave dinners (ChatGPT’s writing is a frozen meat loaf; a student essay is a marbled steak). But the most common comparison was to the advent of the internet. Charles Isbell, the dean of computing at Georgia Tech, points out that the web did not immediately create the kind of nightmarish scenario that people had predicted. Supersonic email exchanges didn’t scramble our brains , just as the “Undo” button hasn’t eroded our sense of consequence. For now, Isbell isn’t concerned about students cheating with AI: If they submit a ChatGPT-written essay, the errors will give them away, and if they try to avoid detection by meticulously fact-checking the chatbot’s writing, they’ll learn the material. But just like the internet, which spawned smartphones and social-media sites that few people could have foreseen, AI will undercut the most basic patterns in higher education. “It’s perfectly reasonable to hold in your head both thoughts,” Isbell told me. “It’s not going to be the big, destructive force that we think it’s going to be anytime soon. Also, higher education will be completely unrecognizable in 15 years because of this technology. We just don’t really know how.” "

"The Terrible Downside of AI Language Translation - The Atlantic"

"https://www.theatlantic.com/ideas/archive/2023/07/the-terrible-downside-of-ai-language-translation/674687"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Artificial Intelligence More From Artificial Intelligence The Sudden Fall of Sam Altman Ross Andersen The AI Debate Is Happening in a Cocoon Amba Kak Sarah Myers West My North Star for the Future of AI Fei-Fei Li AI Search Is Turning Into the Problem Everyone Worried About Caroline Mimbs Nyce Learn a Foreign Language Before It’s Too Late AI translators may seem wondrous but they also erode a major part of what it is to be human. To me, AI’s scariest aspect is the so-called singularity—the threat of a runaway intelligence explosion leaving humanity in the dust. But today’s state of the art in artificial intelligence is already auguring smaller but still shattering scenarios. Some people so deeply yearn to climb Mount Everest that they prepare for years, spend vast sums of money, exhaust themselves for weeks in the climb itself, and repeatedly put their lives at risk. Does that sound like you? Or would you rather just land on its summit in a helicopter and feast yourself on the great view? And what about scaling the metaphorical Everest of a foreign language? Two small episodes in my life in the past month led me to serious musings along these lines. Two weeks ago, I watched, for the first time ever, a video of myself back in 2018 in Hangzhou, China, as I struggled mightily for three minutes to make a few off-the-cuff remarks to about 20 young people from Shanghai who belonged to a club of AI enthusiasts. They had traveled 200 miles to Hangzhou to meet me for dinner, and for two and a half hours we had spoken only English together, but toward the evening’s end they asked me if I wouldn’t mind saying something very brief in Chinese for those club members who hadn’t been able to make the trip. Uh-oh! Panic city! Even though I had devoted many arduous years to the study of Chinese (always thinking of the daunting phrase “Learning Chinese is a five-year lesson in humility” as a ridiculous understatement), and had worked like the devil during the previous three months in Hangzhou, I was caught way off guard by their request and, although in the end I obliged them, I felt super jittery while doing so. Shortly thereafter they sent me the video, but for all these years I hadn’t dared to look at even the opening few seconds of it, so scared was I of seeing myself linguistically stumble all over the place. But what I saw, when I finally dared to watch myself very recently, was surprising. I saw a person who was not just struggling hard to express himself in a very difficult alien tongue, but who was actually doing a fairly decent job of it, while at the same time coming across as insecure and vulnerable, yet courageously willing to take the bull by the horns. In short, today’s me felt proud of my 2018 self! Since that day five years ago, sadly, my once-okay Chinese has gone to the dogs, and today I couldn’t give a three-minute talk in Chinese to save my life, so I’m thrilled to have proof that at one time in my life, I was actually able to wing it, actually able to give a tiny “talk” in Chinese, even if only a three-minute one. So that’s the first episode; here’s the other. A few weeks ago, my very dear Italian friend Benedetto Scimemi passed away, and I spent hours writing heartfelt emails of condolence to all the members of his family. It happens that I lived in Italy for nearly three years and, on top of that, my two children and I have spoken Italian for 30 years as our family language, so my Italian is very fluent and comfortable—but, even so, it is not the Italian of a native speaker. In writing those difficult and emotional emails, I was constantly adjusting my words and phrases, lovingly remembering Benedetto and all the wonderful things we had done together, and pushing my Italian to its very limits. It took me perhaps two or three times as long as it would have taken me in English, but I did it with all my heart. I looked up lots of words in the big, heavy dictionary that I always keep right by my computer, and I felt my words were really me ; my caring concentration on each and every turn of phrase made them mirror my feelings of love for my late friend in the most intensely personal way. Once again I was proud of myself and of the manner in which, over decades, I had come to be able to express myself clearly, strongly, and with a deeply felt voice in a tongue that was not my mother tongue. Over the course of my life, I have studied lots of languages to various degrees, and I jokingly call myself “pilingual,” meaning that if you were to add up the fractional levels of mastery of all the languages I’ve tackled, you’d get a number a bit over three, counting English as one, French as 0.8, Italian as 0.7, and going down from there, with Chinese as maybe 0.3, at its apex (probably just 0.1 today). Read: The coming human renaissance Leaving aside my native tongue, I have devoted many thousands of hours of my life to seven languages (French, Italian, German, Swedish, Russian, Polish, and Chinese)—sometimes flailing desperately and sometimes finding enormous gratification. But through thick and thin, I have relentlessly bashed my head against each of those languages for years, because I love each one’s sounds, words, intonation patterns, idioms, proverbs, poetry, songs, and so on. It’s hard to think of anything else, in the world of the mind, that has pulled me as intensely as my craving to internalize the magic logic of an alien tongue from a faraway place. But today we have Google Translate. Today we have DeepL. Today we have ChatGPT—and so on. There’s no need for me to list all the powerful technologies that allow anyone today—a monolingual American, say, who has never devoted a single moment to learning, say, Chinese—to write fluent passages in Chinese. Today it’s a piece of cake to send an email in a tongue you don’t know a word of. You just click on “Translate” and presto! There it is! Or at least, there it is, in a certain sense. Assuming that there are no egregious translational blunders (which there often still are), what you are sending off is slick but soulless text. Just imagine if the Shanghai AI club had asked me to say a few words for the club’s absent members not in Chinese but in English, and then, while I was speaking, they ran my English words through a speech-transcribing app, then a translation app, then a speech-producing app, so that my English words came out , in real time, in Chinese. (In fact, if this were happening today, the speech-producing app could even use my very own voice, speaking with a perfect Mandarin accent!) Had the club gone that techie-type route, which they might well have liked to do, we could have bypassed any need for me to struggle and strain to express myself in their tongue. For both me and the club members, it would have been effortless. However, in this scenario, the video watchers would be deprived of coming to know key aspects of the very human personality of their invitee. They would not see Douglas Hofstadter (known in Chinese as “Hou Daoren”) groping for Chinese words, would not witness his insecurity, his vulnerability, or, for that matter, his dogged determination; they would merely see an American casually speaking in his native tongue (though what they would hear is perfect Chinese); they would get no sense for the real me, who had devoted thousands of hours, spread out over many years, to grappling with their native tongue. My ideas would come across, more or less, but not those hidden aspects of my self. But let me play devil’s advocate for a moment. Today’s AI technology allows people of different cultures to communicate instantly and effortlessly with one another. Wow! Isn’t that a centuries-long dream come true, weaving the world ever more tightly together? Isn’t it a wonderful miracle? Isn’t the soon-to-arrive world where everyone can effortlessly speak every language just glorious? Some readers will certainly say “yes,” but I would say “no.” In fact, I see this looming scenario as a great tragedy. I see it as the beginning of the end of the age-old tradition of learning foreign languages—not only here in America, but even in lands like Holland and Sweden, fabled for their citizens’ near-universal mastery of several tongues. The problem is that people of all cultures instinctively follow the path of least resistance. Why would anyone want to devote thousands of hours to learning a foreign language if, by contrast, they could simply talk into their cellphone and it would instantly spit out “the same message” in any language of their choice, in their own voice, and with a perfect accent to boot? Who wouldn’t want to be able to have complex conversations with anyone they wish, in any country, no matter what language it involves? Why bother to take countless courses in Chinese and still feel deeply inadequate in it when, in a flash, you can communicate not only in Chinese but also in French, Hungarian, Swahili, and so on? Suppose I had composed my condolences to Benedetto’s family in English and had then run them through a translation program such as DeepL. The words would have come out very differently from what I wrote in Italian. When I was writing in Italian, I was thinking in Italian, not in English. I was using words and phrases that I have made my own over decades, by having countless intimate conversations with close Italian friends (such as Benedetto himself), by reading hundreds of children’s books in Italian to my kids when they were little tykes, by listening hundreds of times to CDs of lilting Italian songs from the 1930s, by devouring Italian newspapers, by giving untold dozens of lectures in Italian, by watching scores of old Italian movies, by memorizing a few Italian poems, and so on. All that unique flavor, reflecting the myriad idiosyncratic pathways by which I lovingly internalized the Italian language, would be missing from an email that I composed in English and that was instantly converted into Italian by a machine. You might say that such a loss is a small price to pay—a teeny price to pay!—for the amazing luxury of being able to produce flawless, flowing emails in a hundred different languages, the luxury of being able to give lectures in real time in a hundred different languages, and so forth and so on. Well, I would reply that the “you” who is “writing” or “speaking” so fluently in all these different languages is not you at all. It is, rather, a deepfake version (or a set of deepfake versions) of you. When I was in the roughest times in my endless battles with the Chinese language, I often wished that I could just get an injection that would make me perfectly fluent in Chinese in a flash. How wonderful it would be to be able, at last, to understand everyone around me, to say anything I wanted to say, and so on! But when I thought about it for only a few seconds, I realized that after getting such an injection, I would not feel proud of having learned Chinese by struggling for many years. My instant fluency in Chinese would, in that case, be a trivial acquisition rather than a precious goal obtained thanks to immense hard work. It would mean nothing to me, emotionally. It would be like arriving at the summit of Everest in a helicopter. It would be like taking a new wonder drug that hugely boosted my muscles and hugely sped up my reflexes, making me (even at age 78!) suddenly able to run faster than anyone else in the world. Next thing you know, this old geezer would be winning a gold medal in the Olympic 400 meters. But big deal! “My” gold medal would be a hollow victory proving nothing about my athletic abilities. It would be purely the result of technological cheating. Likewise, my Chinese-fluency injection would be a hollow victory, because “my” Chinese would not in any way represent my very human, very fallible, but also very determined mind and spirit. When, in my teenage years, I was striving so passionately to learn French, I sometimes wished that I had just grown up in France with my American parents, so that both French and English were 100 percent native to me. But when I thought about it more carefully, I realized that the reason I was so in love with French was precisely that it was not my mother tongue, and that if it had been, then I wouldn’t be able to hear it in anything like the same way I heard it as an outsider. Of course, over my six-plus decades of speaking French, I have become less and less of an outsider to it, but still I have somehow preserved the intense love that came from confronting the huge challenge of making French my own in my teenage years, as opposed to simply imbibing it like mother’s milk, as a small child. And I am oh so proud of myself if, after half an hour’s conversation, my native-French interlocutor is startled to learn that I did not grow up speaking French. By dint of intense concentration over decades, I’ve earned that supreme compliment, and knowing I’ve reached that long-dreamed-for level thanks to my years of really hard work is as great a feeling as any I have ever had. Today’s young people (even in Holland and Sweden) who grow up with translation software, however, will not be lured in the same way that I, as a teenager, was lured by the fantastic, surrealistic goal of internalizing another language. They won’t feel the slightest temptation to devote a major fraction of their lives to slowly and arduously acquiring the sounds, vocabulary, grammar, and cultural richness of another language. To them, someone with my self-punishing attitude would seem hopelessly wedded to the past. Why on earth cling to riding a horse or a bicycle for transportation, when you can drive a car (not to mention flying in an airplane)? What’s the point of going super slowly when you can go superfast? Okay, okay, on a horse or bicycle you’ll see the scenery a bit better, but is it really worth it, when you can cross an entire continent in hours or days, instead of in weeks or months? The question comes down to why we humans use language at all. Isn’t the purpose of language just the communication of facts? If so, then why not simply go for maximizing the number of facts transferred per second? Well, to me, this sounds like a shockingly utilitarian and pragmatic description of what I view as a perpetually astonishing and quasi-magical phenomenon that lies at the very core of conscious life. When I speak any language, as all my friends know well, I am always searching for the most appropriate word or idiom, frequently hesitating, stumbling, or suddenly changing course midstream; constantly joking by playing with ambiguity; having fun by putting on droll accents and personas, not to mention coming out with puns (some lovely, some lousy); using alliterative phrases; concocting new words on the fly; making accidental mistakes and laughing at myself; committing deliberate grammatical errors; unconsciously blending idioms and thus creating delightful new turns of phrase; tossing in words from other languages left and right; citing proverbs and quoting snippets of poetry; mixing metaphors; etc., etc. Speaking any language, for me, is a living, dynamic process that is permeated by my own unique humanness, with all its frailties and strengths. How is all of this wildly bubbling richness in Language A going to be mirrored in real time in Language B by a mechanical device that has nothing of those qualities driving it, that has no sense of humor, that has no understanding of irony or self-mockery, that has no awareness of how phrases are unconsciously blended, and so on? For me, using language is the very essence of being human. When I speak, I am communicating not only facts , but a way of being. Through my word choices and subtle intonations and tiny hesitations and droll puns and dumb errors (and so on), I am revealing who I am. I am not a persona , but a person. Today, though, it strikes me as possible—in fact, quite likely—that humans are collectively going to knuckle under and throw in the towel as far as foreign languages are concerned. Are we language users going to obsequiously hand over all engagement with other tongues to chatbots? Will young people in the coming decades share my youthful ardent desire to tackle towering linguistic Everests demanding long years of dedication? Or will they opt for the helicopter/chatbot pathway, preferring their linguistic lives to be struggle-free? If everything we might ever wish for is just handed to us gratis on a silver platter, then what, I wonder, is the purpose of living? As my friend David Moser put it, what may soon go down the drain forever, thanks to these new AI technologies, is the precious gift that one can gain only by immersing oneself deeply in another culture and thereby acquiring an entirely new set of ways of looking at the world. It’s a gift that can’t help but turn any human being into a far richer and broader one. But David fears that it may soon become as rare as hen’s teeth. And, I might add, David knows perfectly whereof he speaks, because in his 30s he recklessly threw himself into the bustling, boiling cauldron of China and its mysterious languages, and after long years of tenaciously clambering up its nearly vertical slopes (sorry for the mixed metaphor!), he emerged as a marvelously fluent speaker of Chinese, able to come out with breathtakingly witty puns on the fly and to do stand-up comedy on national television, not to mention hosting his own weekly TV show, in Chinese, about little-known facets of Beijing. To Mo Dawei, as David is known in China, it’s incredibly depressing to contemplate the profound impoverishment of people’s mental and emotional lives that is looming just around every corner of the globe, thanks to the slick seductiveness of AI translation apps, insidiously creeping their way into ordinary people’s lives and sapping their desire to make other tongues their own. When children first hear the sounds of another language, they can’t help but wonder: What in the world would it feel like to speak that language? Such eager childlike curiosity might seem universal and irrepressible. But what if that human curiosity is suddenly snuffed out forever by the onrushing tsunami of AI? When we collectively abandon the age-old challenge of learning the languages of other lands, when we relinquish that challenge to ultrarapid machines that have no inner life of their own but are able to give us fluent but fake facades in other languages, then we will have lost a major part of what it is to be human and alive. "

"How Machine Learning Found Flint’s Lead Pipes - The Atlantic"

"https://www.theatlantic.com/technology/archive/2019/01/how-machine-learning-found-flints-lead-pipes/578692"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From Metropolis Now More From Metropolis Now How Will the Future Remember COVID-19? Ian Bogost The YouTuber Who Treats the Inner City Like a Safari Stephen Kearse The Pandemic Could End Waiting in Line Elissaveta M. Brandon America Will Sacrifice Anything for the College Experience Ian Bogost How a Feel-Good AI Story Went Wrong in Flint A machine-learning model showed promising results, but city officials and their engineering contractor abandoned it. Workers in Flint, Michigan, replace a lead water-service pipe. M ore than a thousand days after the water problems in Flint, Michigan, became national news, thousands of homes in the city still have lead pipes, from which the toxic metal can leach into the water supply. To remedy the problem, the lead pipes need to be replaced with safer, copper ones. That sounds straightforward, but it is a challenge to figure out which homes have lead pipes in the first place. The City’s records are incomplete and inaccurate. And digging up all the pipes would be costly and time-consuming. That’s just the kind of problem that automation is supposed to help solve. So volunteer computer scientists, with some funding from Google, designed a machine-learning model to help predict which homes were likely to have lead pipes. The artificial intelligence was supposed to help the City dig only where pipes were likely to need replacement. Through 2017, the plan was working. Workers inspected 8,833 homes, and of those, 6,228 homes had their pipes replaced—a 70 percent rate of accuracy. Heading into 2018, the City signed a big, national engineering firm, AECOM , to a $5 million contract to “accelerate” the program, holding a buoyant community meeting to herald the arrival of the cavalry in Flint. Few cities have embarked on a pipe-replacement program nearly as ambitious, let alone those that have to deal with the effects of segregation , environmental racism , and the collapse of industry in the upper Midwest. In total, 18,786 families in Flint now know that their pipes are safe, because the City has either dug them up and confirmed that they’re copper or replaced them if they were made of lead or galvanized steel. “I think things have gone extremely well,” Flint Mayor Karen Weaver told me. “We’re a year ahead of schedule and under budget.” But something strange happened over the course of 2018: As more and more people had their pipes evaluated in 2018, fewer and fewer inspections were finding lead pipes. In November 2017, according to meeting notes obtained by local news outlet MLive ’s Zahra Ahmad, the city’s head of public works estimated that about 10,000 of Flint’s homes still had lead pipes, roughly in line with the number other experts have floated. The new contractor hasn’t been efficiently locating those pipes: As of mid-December 2018, 10,531 properties had been explored and only 1,567 of those digs found lead pipes to replace. That’s a lead-pipe hit rate of just 15 percent, far below the 2017 mark. Read: The ‘horrifying’ consequence of lead poisoning There are reasons for the slowdown. AECOM discarded the machine-learning model’s predictions, which had guided excavations. And facing political pressure from some residents, Weaver demanded that the firm dig across the city’s wards and in every house on selected blocks, rather than picking out the homes likely to have lead because of age, property type, or other characteristics that could be correlated with the pipes. After a multimillion-dollar investment in project management, thousands of people in Flint still have homes with lead pipes, when the previous program would likely have already found and replaced them. T he declining success of the pipe-replacement program has caused critics of the City to raise the alarm. The Natural Resources Defense Council (NRDC), which represents a community group called the Concerned Pastors for Social Action, has argued in court that the City has abrogated its court-ordered mandate to get the lead pipes out as quickly as possible. If there are still thousands of homes with lead pipes and the City is doing thousands of excavations, how hasn’t it found more of them? “It’s the number of lead pipes removed that matters, not the number of holes dug,” said Pastor Allen C. Overton, a member of Concerned Pastors for Social Action, in an NRDC statement. Before things got ugly, the effort to pull the lead pipes out of the ground was shaping up to be a high-tech feel-good story. At Google’s AI for Good conference in October, the Georgia Tech computer scientist Jacob Abernethy described how a team of volunteers built the system to predict which homes were most likely to have lead pipes. The computer scientists saw that an information problem was sitting atop the lead issue in the city. No one knew, exactly, who had lead pipes and who did not. The City had a variety of records: thousands of old cards describing parcels’ hookups, and also maps and small updates that had been filed into the system over the years. But a cataloging system is only as good as its maintenance, and the City of Flint had been starved of resources for decades. Flint, you probably know, was a key chamber of the heart of the American automobile industry. Through the middle of the 20th century, General Motors had a variety of facilities in the area, employing some 80,000 people. As Flint’s position within the automotive industry declined, most white residents took the money they’d earned and moved to the suburbs, taking their tax dollars and capital out of the city’s core. They created their own regional services in the wealthier Genesee County, while Flint’s residents suffered the repercussions of an economy that had moved on: budget cuts, failing schools, and, of course, post-industrial environmental problems. It is not a surprise, then, that before the crisis began, auditing and correcting water-department records from the early-20th century were not top of mind for city officials. When Flint’s money woes got bad enough in the wake of the housing collapse, Michigan Governor Rick Snyder sent in an “emergency” manager to enact cost-cutting measures. Half of Michigan’s black residents have lived under an emergency manager, according to a Michigan Civil Rights Commission report about Flint. It was Flint’s emergency manager who made the call to switch the water supply from the Detroit water system to the Flint River in April 2014 without putting in the right corrosion controls. That’s what started the problem. Many cities share the lead-pipe problem and the informational obstacles layered atop it. The decay of infrastructure built decades ago is not only in the metal, but in the data cataloging that lets the city’s government and residents understand the state of the water system. For all the talk of “smart” cities, the real state of play in many older places is that no one even thinks of these things until there’s a disaster. People have been saying “ America is 1,000 Flints ” since the city was booming, and it is still true. Just as there are thousands of lead service lines in Flint, there are something like 6 million lead service lines in America. When Weaver launched the program to replace Flint’s lead service lines, Fast Start, in March 2016, suddenly the city’s maintenance debt came back up to the surface. General Michael McDaniel was picked to lead the program, with less than a handful of people working under him. Some basic things were known about the lead-pipe distribution: The pipes were most likely to be found in postwar homes, built when Flint experienced major expansions, and least likely to be found in newer homes. In February 2016, Martin Kaufman at the University of Michigan at Flint built some maps of nominal lead pipe placements in the city using City records. McDaniel’s team used them to prioritize initial excavations based on the age of homes and the Department of Environmental Quality’s rough sense of where the worst water problems were. Then they asked themselves who would be the most affected by lead in the water. “The very young, the very old, and those with compromised immune systems,” McDaniel told me. They determined which homes had kids under 5 years old and adults over 70. Combining these sources gave them a rough sense of where to start. McDaniel set out to replace 600 lead pipes each in 10 small zones. “It was a matter of what was efficient and what was equitable across the city,” he said. When Abernethy and his collaborator, the University of Michigan’s Eric Schwartz, got involved over the summer of 2016, they saw a familiar type of prediction problem: sequential decision making under uncertain conditions. The crews didn’t have perfect information, but they still needed the best possible answer to the question Where do we dig next? The results of each new dig could be fed back into the model, improving its accuracy. Initially, they had little data. In March 2016, only 36 homes had had their pipes excavated. And even as the crews began to do hundreds of digs, they were looking for lead pipes, which meant that they were creating a decidedly unrepresentative sample of the city. Using just that data, the model was likely to overpredict how much lead existed elsewhere in Flint. So the University of Michigan team asked Fast Start to check lines across the city using a cheaper system called “hydrovacing,” which uses jets of water, instead of a backhoe, to expose pipes. The data from those cheaper excavations went back into the model, allowing the researchers to predict different zones of the city more accurately. Read: How to prevent the next Flint As they refined their work, they found that the three most significant determinants of the likelihood of having lead pipes were the age, value, and location of a home. More important, their model became highly accurate at predicting where lead was most likely to be found, and through 2017, the contractors’ hit rate in finding lead pipes increased. “We ended up considerably above an 80 percent [accuracy] for the last few months of 2017,” McDaniel told me. In late 2017, Weaver announced that the City was awarding a $5 million contract to AECOM, the major national contractor, to run the project. In February 2018, the City held a community forum to “really introduce you to the company that’s going to accelerate Fast Start,” as Weaver put it. Robert Bincsik, Flint’s director of public works, noted at the forum that the City was doing something nearly unprecedented. “There is not anybody else doing this as aggressively as we are,” Bincsik said. “Overall, I think we’ve done a wonderful job.” AECOM’s published plans said it intended to “efficiently identify and replace 6,000 [lead service lines] per year.” This goal made sense, as the small ragtag and mostly volunteer management team in 2017 had identified and replaced more than 6,000 service lines. The contractor’s process, as laid out at that community meeting, would consist of two steps. First, it would hydrovac in 10 zones laid out by the contractor. Then, after the nature of the pipes was determined, it would go out and replace the lead and galvanized-steel pipes. Bincsik extolled the virtues of hydrovacing: It was cheaper and faster, less intrusive, and created a lower risk of damaging pipes. Hydrovacing cost $300 or less. Digging up the pipes in a traditional way cost several times more, according to contractor invoices from the 2017 phase of the project—at least $2,500, and as much as $5,000 depending on the type of pipes dug up and replaced. A ECOM’s team, however, struggled before it even started. In late October 2018, the project manager, Alan Wong, told me that the problems started during the transition between McDaniel’s team and AECOM. Wong’s crew was supposed to begin work in October 2017, when McDaniel’s contract ended. But AECOM’s deal was not actually signed until December 28, 2017. There was no overlap between the teams. “We would have had October, November, and all of December,” Wong told me. “We would have been able to mesh, to have a reasonable transition. It didn’t work out.” Furthermore, AECOM does not appear to have considered the predictive model central to the project. According to a court declaration, after seemingly positive initial discussions, Schwartz, from the University of Michigan, sent five emails to Wong from January through May 2018, none of which was answered. Wong told me that all his company had was a “heat map” of the city—like an image—but Schwartz said his own team had offered its database, which consisted of individual lead-probability scores for every single address in the city. AECOM basically approached the problem new, as if other people had not been successfully hammering away at it since June 2016. It discovered, as others had before, that the data the City possessed were neither wholly digitized nor wholly accurate. Wong says the company doing the digitization work pro bono, Captricity, was supposed to be done in January but did not finish until May. At the same time, Weaver asked AECOM to explore all over the city, in each of the city-council wards. The city administration “did not want to have to explain to a councilperson why there was no work in their district,” Wong said. So AECOM created 10 zones spread across the whole city, initially assigning 600 addresses in each area to contractors. The problem is that lead pipes are not evenly distributed across the city. When evaluated by any available tool—the actual amount of lead pipes that had been found, the predictions from the University of Michigan model, what the city records said, historical knowledge of construction practices—it was clear that the lead was concentrated in a few areas, mostly in the older places in the core of the city, such as the Fifth Ward, and not in the outer regions, such as the Second, Fourth, or Seventh Wards. Read: How do you regulate a self-improving algorithm? Then, in the middle of 2018, some lead was found in pipes that had otherwise seemed to be made of copper. Hydrovacing generally makes a smaller hole than when a backhoe is involved, which had allowed some lead bits to go unnoticed. The mayor made a decision to abandon hydrovacing , opting instead for the gold-standard traditional method. “You get a 100 percent guarantee and that’s what we’re worth,” Weaver told me. Given that AECOM had planned to hydrovac all over the city as a means of identifying lead, that change threw a kink into the company’s plans. Other changes were also afoot. The mayor made a decision to excavate every house in areas where program officials thought they might find lead, rather than skipping over homes that the model indicated probably didn’t have lead pipes. “When we started this, people would say, ‘You did my neighbor’s house and you didn’t do mine,’” Weaver said. “The City did not want to leave anybody behind,” Wong told me. That makes political sense, but it has serious implications for not just the cost of the remediation project, but the speed at which the project could extract the remaining lead service lines in the city. In the outer regions of Flint, block after block of homes were excavated and no lead was found, as in the eastern block of Zone 10, seen below, where blue represents copper pipes and red shows lead or galvanized-steel pipes. Hundreds of homes’ pipes were excavated in the area; none of them was made of lead or galvanized steel. A new directive had begun to guide the program: to excavate, by the most intensive means, every single active water account in the city. Otherwise, citizens could always wonder if they had lead pipes and didn’t know it. The program managers would have to tell people, “You’ll have to trust a computer model,” Wong told me. “The citizens are just not going to trust that.” T here are reasonable explanations for why AECOM’s hit rate would be lower than the 2017 team’s. McDaniel worked in the areas of the city with the highest concentrations of lead, and his team generally followed the model’s predictions. AECOM and the City went to work across Flint and did every house along certain blocks. Furthermore, there are fewer lead service lines in the city than originally estimated. Early approximations assumed that 20,000 to 30,000 city pipes were made of lead or galvanized steel. That figure proved too high. However, the NRDC, which has been suing the City over the way it has conducted the program, still argues that the core priority of its settlement agreement—lead removal—was abandoned. Even given the factors above, the rate at which contractors are finding lead has fallen too precipitously to be explained by reasonable logistical changes to the program. This has had the effect of keeping lead pipes attached to people’s homes for longer than is absolutely necessary. In a court filing , Schwartz estimates that between 4,964 and 6,119 homes with hazardous lines remain in the city. The map below shows, in red, where the AI researchers predict a greater than 90 percent likelihood that hazardous pipes are installed. Blue indicates areas highly unlikely to have lead or steel pipes. The little black dots are where AECOM’s team has done work in 2018, as of November. If the model is even generally correct, casual inspection suggests that the work isn’t being targeted at the areas most likely to have water lines in need of replacement. “What’s troubling is that the City cannot explain how they are choosing areas to dig,” says Dimple Chaudhary, an NRDC attorney. “You do have this model that is doing a pretty good job of describing ‘Here there is lead.’ And that model says they are excavating in the wrong places.” To take the most prominent example, the Fifth Ward is expected to have the most remaining lead. The University of Michigan model estimates that crews would find lead 80 percent of the time in that area. Yet from January to August 2018, AECOM contractors did the fewest excavations there, carrying out 163 excavations in the ward out of 3,774 total in the city. They found lead pipes in 156 of those digs—96 percent of them. Meanwhile, over the same time period in the Second Ward, 1,220 homes were investigated and lead was found in 46 of them, just a four percent hit rate. AECOM did the most digging in the two wards that Schwartz and Abernethy’s model predicted had the smallest percentage of lead pipes, and the results bore out the predictions of the model. L ooking at this data , the State, which reimburses contractors for their work, has said it is going to suspend payments to the City because of how the program has been managed. “The City made a policy decision to stop prioritizing excavations at homes where lead or galvanized steel service lines were expected to be found,” the Department of the Attorney General alleged. Now, the City, the NRDC, the State, and AECOM are negotiating to return to the machine-learning model that was used in 2017. AECOM’s contract has been renewed, and appears to include a return to the model. An additional $1.1 million has been allocated to the firm for future work. City officials have made a good-faith attempt at implementing an ambitious, difficult program. Weaver made important decisions that she saw as protecting the health and safety of all her city’s residents. AECOM claims it has done the best it could. But good faith notwithstanding, a heartbreaking fact can’t be ignored: Simply continuing the 2017 program’s method might have pulled nearly all the remaining lead out of the city during 2018. Instead, thousands of people got the peace of mind that comes with knowing they have copper lines. But others who are more likely to have lead lines that could leach poison into their drinking water will have to wait for digging to commence again to learn for sure. And that’s assuming that the battle between the City and the State about reimbursements doesn’t get settled in the State’s favor, depriving residents of the support necessary to complete the pipe-replacement project. This tragedy already has more acts than anyone wants to recount, and the stage is now set for yet another one to begin. "

"Henry Kissinger, Eric Schmidt, and Daniel Huttenlocher on AI - The Atlantic"

"https://www.theatlantic.com/magazine/archive/2019/08/henry-kissinger-the-metamorphosis-ai/592771"

"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 Why police fail to catch sexual predators, Raj Chetty’s American dream, the jailhouse true-crime writer, and Drew Gilpin Faust on Virginia and race. Plus measles as metaphor, Sam Shepard as prophet, the stock-buyback swindle, new short fiction, and more. An Epidemic of Disbelief Barbara Bradley Hagerty The Con Man Who Became a True-Crime Writer Rachel Monroe Race, History, and Memories of a Virginia Girlhood Drew Gilpin Faust The Economist Who Would Fix the American Dream Gareth Cook Wolves of Karelia Arna Bontemps Hemenway What the Measles Epidemic Really Says About America Peter Beinart A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. The Metamorphosis AI will bring many wonders. It may also destabilize everything from nuclear détente to human friendships. We need to think much harder about how to adapt. Humanity is at the edge of a revolution driven by artificial intelligence. It has the potential to be one of the most significant and far-reaching revolutions in history, yet it has developed out of disparate efforts to solve specific practical problems rather than a comprehensive plan. Ironically, the ultimate effect of this case-by-case problem solving may be the transformation of human reasoning and decision making. This revolution is unstoppable. Attempts to halt it would cede the future to that element of humanity more courageous in facing the implications of its own inventiveness. Instead, we should accept that AI is bound to become increasingly sophisticated and ubiquitous, and ask ourselves: How will its evolution affect human perception, cognition, and interaction? What will be its impact on our culture and, in the end, our history? Such questions brought together the three authors of this article: a historian and sometime policy maker; a former chief executive of a major technology company; and the dean of a principal technology-oriented academic institution. We have been meeting for three years to try to understand these issues and their associated riddles. Each of us is convinced of our inability, within the confines of our respective fields of expertise, to fully analyze a future in which machines help guide their own evolution, improving themselves to better solve the problems for which they were designed. So as a starting point—and, we hope, a springboard for wider discussion—we are engaged in framing a more detailed set of questions about the significance of AI’s development for human civilization. The AlphaZero Paradox Last December, the developers of AlphaZero published their explanation of the process by which the program mastered chess—a process, it turns out, that ignored human chess strategies developed over centuries and classic games from the past. Having been taught the rules of the game, AlphaZero trained itself entirely by self-play and, in less than 24 hours, became the best chess player in the world—better than grand masters and, until then, the most sophisticated chess-playing computer program in the world. It did so by playing like neither a grand master nor a preexisting program. It conceived and executed moves that both humans and human-trained machines found counterintuitive, if not simply wrong. The founder of the company that created AlphaZero called its performance “chess from another dimension” and proof that sophisticated AI “is no longer constrained by the limits of human knowledge.” Now established chess experts are studying AlphaZero’s moves, hoping to incorporate its knowledge into their own play. These studies are practical, but larger philosophical questions also emerge. Among those that are currently unanswerable: How can we explain AlphaZero’s capacity to invent a new approach to chess on the basis of a very brief learning period? What was the reality it explored? Will AI lead to an as-yet-unimaginable expansion of familiar reality? We can expect comparable discoveries by AI in other fields. Some will upend conventional wisdom and standard practices; others will merely tweak them. Nearly all will leave us struggling to understand. Consider the conduct of driverless cars stopped at a traffic light. When cars driven by people inch forward to try to beat the traffic, some driverless cars occasionally join them, though nothing in the rules of driving given to them suggests that they should do so. If this inching-forward has been learned, how and for what purpose? How is it different from what people are taught and learn about waiting at traffic lights? What else might AI learn that it is not “telling” us (because AI does not or cannot explain)? By enabling a process of self-learning for inanimate objects, we do not yet know what we are starting, but we need to find out. The Nature of the Revolution Heretofore, digital evolution has relied on human beings to create the software and analyze the data that are so profoundly affecting our lives. Recent advances have recast this process. AI has made it possible to automate an extraordinary range of tasks, and has done so by enabling machines to play a role—an increasingly decisive role—in drawing conclusions from data and then taking action. AI draws lessons from its own experience, unlike traditional software, which can only support human reasoning. The growing transfer of judgment from human beings to machines denotes the revolutionary aspect of AI, as described last year in these pages (“ How the Enlightenment Ends ,” June 2018). That said, the word intelligence does not adequately explain what is occurring, and ascribing anthropomorphic qualities to AI is out of order. AI is neither malicious nor kind; it does not have independently developed intent or goals; it does not engage in self-reflection. What AI can do is to perform well-specified tasks to help discover associations between data and actions, providing solutions for quandaries people find difficult and perhaps impossible. This process creates new forms of automation and in time might yield entirely new ways of thinking. Yet AI systems today, and perhaps inherently, struggle to teach or to explain how they arrive at their solutions or why those solutions are superior. It is up to human beings to decipher the significance of what AI systems are doing and to develop interpretations. In some ways, AI is comparable to the classical oracle of Delphi, which left to human beings the interpretation of its cryptic messages about human destiny. If AI improves constantly—and there is no reason to think it will not—the changes it will impose on human life will be transformative. Here are but two illustrations: a macro-example from the field of global and national security, and a micro-example dealing with the potential role of AI in human relationships. AI, Grand Strategy, and Security In the nuclear age, strategy evolved around the concept of deterrence. Deterrence is predicated on the rationality of parties, and the premise that stability can be ensured by nuclear and other military deployments that can be neutralized only by deliberate acts leading to self-destruction; the likelihood of retaliation deters attack. Arms-control agreements with monitoring systems were developed in large part to avoid challenges from rogue states or false signals that might trigger a catastrophic response. Hardly any of these strategic verities can be applied to a world in which AI plays a significant role in national security. If AI develops new weapons, strategies, and tactics by simulation and other clandestine methods, control becomes elusive, if not impossible. The premises of arms control based on disclosure will alter: Adversaries’ ignorance of AI-developed configurations will become a strategic advantage—an advantage that would be sacrificed at a negotiating table where transparency as to capabilities is a prerequisite. The opacity (and also the speed) of the cyberworld may overwhelm current planning models. The evolution of the arms-control regime taught us that grand strategy requires an understanding of the capabilities and military deployments of potential adversaries. But if more and more intelligence becomes opaque, how will policy makers understand the views and abilities of their adversaries and perhaps even allies? Will many different internets emerge or, in the end, only one? What will be the implications for cooperation? For confrontation? As AI becomes ubiquitous, new concepts for its security need to emerge. One of them is the capability to disconnect from the network on which it operates. More pointed—and potentially more worrisome—issues loom. Does the existence of weapons of unknowable potency increase or decrease the likelihood of future conflict? In the face of the unknown, will fear increase the tendency to preempt? The incentives will be for opacity, which could mean absolute insecurity. In these circumstances, how will norms and rules for guiding and restraining strategy be established? The need to develop strategic concepts relevant to this new and inevitable technology has become overwhelming. Human Contact Google Home and Amazon’s Alexa are digital assistants already installed in millions of homes and designed for daily conversation: They answer queries and offer advice that, especially to children, may seem intelligent, even wise. And they can become a solution to the abiding loneliness of the elderly, many of whom interact with these devices as friends. The more data AI gathers and analyzes, the more precise it becomes, so devices such as these will learn their owners’ preferences and take them into account in shaping their answers. And as they get “smarter,” they will become more intimate companions. As a result, AI could induce humans to feel toward it emotions it is incapable of reciprocating. Already, people rank their smartphones as their most important possession. They name their Roombas, and attribute intent to them where none exists. What happens when these devices become even more sophisticated? Will people become as attached to their digital pets as to their dogs—or perhaps even more so? Societies will adopt these devices in ways most compatible with their cultures, in some cases accentuating cultural differences. In Japan, for example, as a result of both an aging population and Shintoism (which considers inanimate objects to have spirits not unlike humans’), AI companions may become even more widespread than in the West. Given these developments, it is possible that in many parts of the world, from early childhood onward the primary sources of interaction and knowledge will be not parents, family members, friends, or teachers, but rather digital companions, whose constantly available interaction will yield both a learning bonanza and a privacy challenge. AI algorithms will help open new frontiers of knowledge, while at the same time narrowing information choices and enhancing the capacity to suppress new or challenging ideas. AI is able to remove obstacles of language and many inhibitions of culture. But the same technology also creates an unprecedented ability to constrain or shape the diffusion of information. The technological capacity of governments to monitor the behavior and movements of tens or hundreds of millions is likewise unprecedented. Even in the West, this quest can, in the name of harmony, become a slippery slope. Balancing the risks of aberrant behavior against limits on personal freedom—or even defining aberrant —will be a crucial challenge of the AI era. The Future Many public projections of AI have the attributes of science fiction. But in the real world, there are many hopeful trends. AI will make fundamental positive contributions in vital areas such as health, safety, and longevity. Still, there remain areas of worrisome impact: in diminished inquisitiveness as humans entrust AI with an increasing share of the quest for knowledge; in diminished trust via inauthentic news and videos; in the new possibilities it opens for terrorism; in weakened democratic systems due to AI manipulation; and perhaps in a reduction of opportunities for human work due to automation. As AI becomes ubiquitous, how will it be regulated? Monitored? As we enter a world where people are taught by AI, will there be the AI equivalent of “approved” school textbooks? The challenge of absorbing this new technology into the values and practices of the existing culture has no precedent. The most comparable event was the transition from the medieval to the modern period. In the medieval period, people interpreted the universe as a creation of the divine and all its manifestations as emanations of divine will. When the unity of the Christian Church was broken, the question of what unifying concept could replace it arose. The answer finally emerged in what we now call the Age of Enlightenment; great philosophers replaced divine inspiration with reason, experimentation, and a pragmatic approach. Other interpretations followed: philosophy of history; sociological interpretations of reality. But the phenomenon of a machine that assists—or possibly surpasses—humans in mental labor and helps to both predict and shape outcomes is unique in human history. The Enlightenment philosopher Immanuel Kant ascribed truth to the impact of the structure of the human mind on observed reality. AI’s truth is more contingent and ambiguous; it modifies itself as it acquires and analyzes data. Recommended Reading How the Enlightenment Ends Henry A. Kissinger The Spooky Genius of Artificial Intelligence Derek Thompson How Google's AlphaGo Beat a Go World Champion Christopher Moyer How should we respond to the inevitable evolution it will impose on our understanding of truth and reality? The three of us have discussed many ideas: programming digital assistants to refuse to answer philosophical questions, especially about the bounds of reality; requiring human involvement in high-stakes pattern recognition, such as the reading of X-rays; developing simulations in which AI can practice defining for itself ambiguous human values— what is ethical? reasonable? does no harm? —in various situations; “auditing” AI and correcting it when it inaccurately emulates our values; establishing a new field, an “AI ethics,” to facilitate thinking about the responsible administration of AI, the way bioethics has facilitated thinking about the responsible administration of biology and medicine. Importantly, all such efforts must be undertaken according to three time horizons: what we already know, what we are sure to discover in the near future, and what we are likely to discover when AI becomes widespread. The three of us differ in the extent to which we are optimists about AI. But we agree that it is changing human knowledge, perception, and reality—and, in so doing, changing the course of human history. We seek to understand it and its consequences, and encourage others across disciplines to do the same. "

"Addressing Mental Health Effects, a Year After the Tubbs Fire in Sonoma | WIRED"

"https://www.wired.com/story/wildfires-mental-health"

"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 Backchannel What One Devastated Community Can Teach the World About Mental Health An aerial view of homes that were destroyed by the Tubbs Fire on October 11, 2017, in Santa Rosa, California. Justin Sullivan/Getty Images Save this story Save Save this story Save A year ago, while on a tourist visit to Latvia, Sharon Bard was awoken at 4 am by a buzzing alert from her phone. It was an email from a friend who’d been checking on her home in Santa Rosa, California. Given the alarming news, the email's phrasing was rather gentle: A fire had broken out in the area, officials had ordered evacuations, and Bard’s country house at the end of a road might be affected. Then came the deluge. Six or seven emails from other folks arrived, with more urgent queries like “Oh my God, are you OK?” So Bard checked CNN, and sure enough, there was the fire. This was not just local news. What neither Bard nor anyone else knew at this point was that what would become the most destructive conflagration in California history, the Tubbs Fire , was well on its way to destroying more than 5,500 structures, killing 22 people, and causing $1.2 billion in damage. For three days after that first email jolted her awake, Bard traded frantic messages with friends. People checked in on her, and she checked in on others. Searching online, she found side-by-side aerial images of her property, before and after the fire. “I realized it's gone, it's all gone,” she says, leaning over tea in an upscale cafe in Healdsburg, just north of Santa Rosa. She’s 73, with gray hair that matches her gray hoodie over a Hawaiian shirt of subdued pastels. “I saw my property. There was a main structure and a pool and then a pool house. It was ashes, pool, ashes.” Yet Bard didn’t cut her tour short and hop the first flight back. Santa Rosa was under quarantine anyway, and air quality was horrible. “I think psychologically, I split into two pieces,” she says. “One part of me tried to stay present because I was on tour, and another part of me there was this sort of thing in the pit of my stomach. I have to deal with this, but I don't know what to do. I didn’t want to face it yet.” “I was on constant overload and I couldn't process the new information," says Sharon Bard about her mental state in the wake of losing her Santa Rosa home in a wildfire. "I was tired, I felt fragile, I was shaky.” Beth Holzer 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 feelings Bard experienced are common in people who have lived through a calamity—even at a distance. Indeed, few things shake the psyche like disaster, yet science is just beginning to understand how mental health suffers in the aftermath of hurricanes or wildfire or earthquakes. Surveys found that after Hurricane Katrina hit the Gulf coast in 2005, one in six survivors met the criteria for PTSD, while half developed an anxiety or mood disorder. Suicide and suicidal thinking doubled in the storm’s aftermath. But there's a dearth of data-rich, large-scale studies on how best to design campaigns to treat populations coping with disaster. Until, that is, the Tubbs Fire and other devastating fires in the area in 2017. The Healthcare Foundation Northern Sonoma County (where Santa Rosa sits) is leading an ambitious project called the Wildfire Mental Health Collaborative. It’s a cooperative of the National Association for Mental Illness , psychologists, researchers, community organizations and more, all working not only to provide mental health services to survivors, but to study what kinds of treatments work and don’t work for this kind of trauma. The idea is to take what they’ve learned and put it to use in other communities ravaged by disaster, wildfire, or other misfortunes. The timing couldn’t be more critical. Climate change is intensifying natural disasters like hurricanes, because the storms feed on warm waters. Whether or not the Tubbs Fire was human-caused—equipment from the local utility, PG&E, may have been the cause —climate change is exacerbating drought in California, which in turn leads to more fuel for wildfires. Meaning more deaths, more property damage, and a supercharged assault on mental health. Climate change is coming for all of us, but what these investigators learn in the aftermath of the Tubbs Fire could change how humanity adapts. Perhaps it’s not surprising that no one is really talking about the mental health impacts of climate change—we have a hard time talking about mental health under any circumstances. But the mental health implications are massive, and they’re already here. In northern Canada, for instance, melting sea ice means Inuit hunters are having a harder time venturing out. For a people that forms an intense bond with their land, that turns into what’s known as ecological grief— psychological devastation that comes with the disruption of the natural 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 That’s a sort of chronic, long-term assault, whereas disasters strike quickly and intermittently, bringing a sudden psychological impact. Wildfires are particularly jarring. “With a hurricane, you know a storm is coming—there's preparation you can do, you have the opportunity to evacuate,” says research psychologist Adrienne Heinz , who’s working with Wildfire Mental Health Collaborative. “Wildfires can change so quickly with the winds.” That not only makes a wildfire particularly dangerous, but also means evacuees have to leave their dearest possessions behind. In the aftermath of a fire, mental health is not high on anyone's priority list. The immediate goal tends to deal with physical effects—burns, smoke inhalation—and to find shelter with friends or family. Psychological impacts may never be addressed. “There's cost, geography, competing priorities at the time,” Heinz says. “There's scheduling, there's stigma, a million reasons why people don't want to do it.” And when families settle with friends or family or in a FEMA-provided trailer, the cramped quarters can take a psychological toll. “That's a major quality of life change that's going to be associated with depression, anxiety, irritability, strained relationships,” Heinz says. Even when survivors do pay attention to mental health issues, it may be their loved ones, not their own. “It's really important that you take care of yourself,” says Debbie Mason, CEO of the Healthcare Foundation Northern Sonoma County. “Kind of like the metaphor: Put your own oxygen mask on before you take care of others.” Mason’s quest is to make that help easy to find. The Healthcare Foundation Northern Sonoma County has launched MySonomaStrong.com , a bilingual website that provides resources for self care and for finding free professional therapy. A new app called Sonoma Rises also helps connect survivors with services and allows them to track their mental well-being. Screenshots of the Sonoma Rises app, showing ways in which fire survivors can manage their trauma. Overlap Health The campaign isn’t just trying out random ideas in the hopes they’ll work. “We learned that in New Orleans, the strategy that worked really well there was community dinners, where a mental health professional would go in and facilitate a group therapy conversation,” Mason says. “So we added that to our menu.” They’ve also trained 300 mental health professionals in skills for psychological recovery, which includes strategies like the management of triggers. After the 9/11 attacks, service agencies learned that drop-in sessions were popular, so the organizers in Sonoma County added that to the mix. “Then we kind of stepped back and said, 'well, if we had the opportunity to be the case study of best response, what do we collectively think our community might respond to?' So we added yoga,” Mason says. Survivors gather for free trauma-informed, relaxation-focused sessions—they’re “invitational,” not “directional,” meaning participants are more in control of their experience—and nearly 60 specially trained instructors are compensated for their time. 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 now, Sonoma is cobbling together anecdotally successful strategies for treating trauma in the aftermath of disaster. But that creates an opportunity to finally quantify what methods work. “If we want to make a difference, and disseminate what we've learned and the tools we're making and not have communities have to reinvent the wheel,” Heinz says, “we need to put some science behind what we're doing.” The problem with studying the mental health impacts of disasters is that disasters move quicker than science. In traditional research, you’ve got to get funding and wrangle researchers and win approvals from your university. That can take half a year. But Sonoma’s case is different. Funding has poured in from donors, and experts have offered to train therapists. Which is not to say this is purely a grassroots campaign—Stanford University has stepped in to help. “What we realized was that for the kind of work and evaluation they were needing to do, we really needed some infrastructure,” says Shannon Wiltsey Stirman , a psychologist and researcher at Stanford. These researchers can store sensitive health information, for instance. How, though, can you determine the effectiveness of therapy post-disaster? In part by getting the therapists to break things down into components. “So for example,” Stirman says, “have they been working on helping people increase their social support? Have they been helping them work on using particular coping skills? Have they been working on them with processing or writing about the trauma?” In a way, mental care isn’t unlike physical care, which means the researchers can squeeze hard data out of it. So for instance, patients take surveys to self-report how they’re coping. “That's kind of like taking their blood pressure,” Stirman says. In this way, researchers can systematically look at things like depression symptoms and sleep quality over time. Determining the effectiveness of MySonomaStrong.com is a bit easier, in that you can track usage of the site. Same with the app. Gauging yoga can be done along the same lines—tracking the frequency of use. With data, the researchers can build a better picture of what strategies work post-disaster. Which is not to say every community will respond to these things the same way. You can’t just figure out what works in Sonoma then apply it by rote elsewhere—not every place is as open to yoga as California. You have to consider the needs and the attitudes of the people affected. But this new research is helping determine what might be a community’s best bet. 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 view this time as obviously scary,” Heinz says. “But it's also a window of opportunity to improve what we're doing so we have a standard operating procedures for, 'hey, this community has been hit by a wildfire. We know from the science that this, this, and this can be effective.‘” Just as every community is different, so too are the types of disasters. What might work for mental health after wildfires might not be so effective after hurricanes, where people may be able to return to damaged yet salvageable homes. Regardless, the climate reckoning is here, and humanity is way, way behind in considering the mental health implications of what we’re up against. “I honestly think that the NIH should have a disaster recovery institute,” Heinz says. “There's one for alcoholism, there's one for drug abuse, there's aging and heart and lung. We need to have institutionalized mechanisms to study and support communities. With the anticipated increased frequency of these events, you need systems of care.” Sharon Bard wasn’t well in the months following the fire. “I would get hysterical over something very tiny,” she says. “I was on constant overload and I couldn't process the new information. I was tired, I felt fragile, I was shaky.” Bard went through therapy, and now that she’s getting more settled, she’s improving. She just moved into a new rental, not far from where I met her for tea. She can multitask again. In short order she can go out shopping, put together an Ikea desk, and do some gardening. “That's pretty good for a day for me,” she says. But the fire will always be there. Even something as simple as countertops are a reminder—they’re higher here than in her lost home. “Every time I reach, it’s a trigger” she says. Now Bard has to decide whether to rebuild, to pile on still more triggers. To wade through infuriating bureaucracy, with permitting and insurance and contractors. “That kind of triggers a panic,” she says, “as well as a, what am I doing? What am I doing? " Bard is a victim of the most destructive fire in California history, but also a victim of climate change. Soon enough, the rest of us will be as well in our own ways, be it heat waves or sea level rise or melting ice or monster storms. But maybe what Sonoma learns from this experiment can give us the tools for our brains to fight back. The long, strange history of the presidential text alert Inside the secret conference plotting to launch flying cars It’s time to talk about robot gender stereotypes Cities team up to offer broadband and the FCC is mad PHOTOS: The space shuttle program's golden age Get even more of our inside scoops with our weekly Backchannel newsletter Staff Writer X Topics climate change mental health Vauhini Vara Steven Levy Samanth Subramanian Amit Katwala Gideon Lichfield Christopher Beam Lindsay Jones Lexi Pandell 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 "

"What's Different About the Brains of Heroes? | WIRED"

"https://www.wired.com/2014/08/hero-brains"

"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 Christian Jarrett Science What's Different About the Brains of Heroes? Julian Fong/Flickr Save this story Save Save this story Save There's a scene from a disaster movie I watched as a small child that I'll never forget. As passengers attempted to flee a ship sinking and on fire, they reached a missing section of walkway above a perilous drop. It looked like they were all doomed, but one of the male passengers turned himself into a human bridge. The others walked across him to safety. He then dropped to his death, exhausted. I can't remember the name of the film, and I can't remember why the passengers couldn't just jump across the gap. But the self sacrifice of the man was seared in my memory - his sheer heroism, his willingness to risk his own life for others. So it is that a new brain imaging study caught my attention. Marco Zanon and his colleagues scanned the brains of 43 young adults (30 women) while they took part in a virtual reality (VR) experience of a disaster. Wearing VR goggles and headphones, each participant began the study by meeting up with what they thought were three other volunteers in a virtual waiting room. In fact, these other avatars were computer controlled. After exploring the room for a while, the participants were surprised by the sound of a fire alarm. Having earlier been instructed to behave as they would in the real world, the participants raced to evacuate the building. Simulated smoke, flames and coughing and heart beat sound effects added to the drama. Crucially, near the building exit, their "life energy" bar nearly depleted, the participants encountered one of the other people they'd met in the waiting room, finding them trapped injured under a fallen filing cabinet and surely doomed to die. Each participant faced the same choice - try to save the stricken individual (they'd earlier learned that objects could be moved by tapping a joystick key; saving the other human required 150 such button presses), or plough on to safety. Throughout this VR experience the researchers scanned the participants' brains. They used an approach known as independent component analysis, which is about looking for networks of correlated activity across the brain. There were 16 heroes, including 11 women, who rescued the trapped man. Nineteen others, including 12 women, passed by without helping. The remaining 8 tried to help but gave up - they were omitted from the subsequent brain analysis because they were so few in number. Zanon and his colleagues identified three functional hubs in the brain that they said were differently activated in the heroes and the more selfish folk. The first was more active (throughout the VR experience) in the selfish participants, and took in the anterior insula and the anterior mid-cingulate cortex (areas buried deep in the cerebral cortex), but also included other regions such as the thalamus and the cerebellum. Zanon's team said this network has previously been associated with finding things salient, which is itself a state associated with anxiety. Activity in this network has also been linked with harm avoidance, the researchers said. In other words, greater activity in this functional hub may reflect the fact that the selfish participants felt more endangered (there was a trend for them to report feeling more anxious than the heroes, but this didn't reach statistical significance) and a greater motivation to protect themselves. Two other networks were more active in the heroes, specifically while they encountered the trapped victim. The first included areas such as the medial orbitofrontal and anterior cingulate cortex, activity which the researchers said is involved in taking other people's perspective. The second included an area over the junction of the temporal and parietal lobes, and has previously been linked with thinking about other people, and distinguishing the self from others. The obvious interpretation is that the greater activity in these networks in the brains of heroes reflects their greater empathy for the trapped victim. However, the researchers admitted it's also possible this brain activity could reflect increased concern for one's reputation. What to make of this study? I admired its ambition. So much research into altruism and so-called "pro-social" behaviours depends on financial games, in which people's generosity or trust is measured. Or researchers pretend to drop pens on the floor and they see if participants will bend down to help pick them up. These methods are obviously a far cry from real-world heroism. And so it is refreshing to see a study that involved a little existential drama, albeit in a virtual reality context. Unfortunately, in most other regards I found this research disappointing - it just seemed to involve so much speculation. Take the first brain network (the one involving the anterior mid cingulate and insula) - the researchers identified this as a salience network, and linked it with increased anxiety. But one could just as easily interpret this activity as being involved in empathy, given that other research has linked the anterior insular cortex with this function. In which case, how come the selfish people showed more empathy-related activity? Perhaps we should remember, as the Neuroskeptic blogger recently pointed out , that the link between activity intensity and function isn't straightforward - perhaps the selfish participants in this study showed extra activity in this network because they had to work harder to empathise with the victim whereas for the heroes this concern came more naturally. But now I'm doing it - speculating wildly about the meaning of recorded brain activity. In the end what really have we learned from this research? It feels like we have preconceptions about heroes - that they have more feeling for other people, for example - and then the brain scan results are interpreted in line with those prior beliefs. This makes me think again (I've made this point in previous blog posts ) that actually far more psychology research is needed to lay the groundwork, in this case on extreme acts of bravery, and perhaps then with more sophisticated psychological understanding we would be better placed to explore the neurophysiological correlates of heroism. Even then, if our aim is to understand heroism, is the brain really the place to look? I can't help feeling skeptical - I'd be interested to hear what you think. To be fair to the researchers, they do admit that they can't draw "definitive conclusions" from their findings, and they express the modest hope that their study "might inspire new hypotheses or experimental protocols". Meanwhile, if anyone knows what that ship-based disaster movie was that I saw as a child (I watched it on TV in the 80s), please let me know! 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 X Topics Brains and Behavior Brain Watch Elizabeth Finkel Maryn McKenna Max G. Levy Grace Browne Erica Kasper Emily Mullin Celia Ford Jorge Garay 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 "

"RealNetworks Launches Free Facial Recognition Tool for Schools | WIRED"

"https://www.wired.com/story/realnetworks-facial-recognition-technology-schools"

"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 Issie Lapowsky Security Schools Can Now Get Facial Recognition Tech for Free. Should They? Chris Ryan/Getty Images Save this story Save Save this story Save Like many parents in the United States, Rob Glaser has been thinking a lot lately about how to keep his kids from getting shot in school. Specifically, he’s been thinking of what he can do that doesn’t involve getting into a nasty and endless battle over what he calls “the g-word.” It’s not that Glaser opposes gun control. A steady Democratic donor, Glaser founded the online streaming giant RealNetworks back in the 1990s as a vehicle for broadcasting left-leaning political views. It’s just that any conversation about curbing gun rights in America tends to lead more to gridlock and finger-pointing than it does to action. “I know my personal opinions aren’t going to carry the day in this current political environment,” Glaser says. So he started working on a solution that he believes will prove less divisive, and therefore more immediately actionable. Over the past two years, RealNetworks has developed a facial recognition tool that it hopes will help schools more accurately monitor who gets past their front doors. Today, the company launched a website where school administrators can download the tool, called SAFR, for free and integrate it with their own camera systems. So far, one school in Seattle, which Glaser’s kids attend, is testing the tool and the state of Wyoming is designing a pilot program that could launch later this year. “We feel like we’re hitting something there can be a social consensus around: that using facial recognition technology to make schools safer is a good thing,” Glaser says. SAFR 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 while Glaser’s proposed fix may circumvent the decades-long fight over gun control in the US, it simultaneously positions him at the white-hot center of a newer, but still contentious, debate over how to balance privacy and security in a world that is starting to feel like a scene out of Minority Report. Groups like the Electronic Frontier Foundation, where Glaser is a former board member, have published a white paper detailing how facial recognition technology often misidentifies black people and women at higher rates than white men. Amazon’s own employees have protested the use of its product Rekognition for law enforcement purposes. And just last week, Microsoft President Brad Smith called for federal regulation of facial recognition technology, writing, “This technology can catalog your photos, help reunite families or potentially be misused and abused by private companies and public authorities alike.” "This isn’t just sci-fi. This is becoming something we, as a society, have to talk about." Rob Glaser, RealNetworks The issue is particularly fraught when it comes to children. After a school in Lockport, New York, announced it planned to spend millions of dollars on facial recognition technology to monitor its students, the New York Civil Liberties Union and the Legal Defense Fund voiced concerns that increased surveillance of kids might amplify existing biases against students of color, who may already be over-policed at home and in school. "The use of facial recognition in schools creates an unprecedented level of surveillance and scrutiny," says John Cusick, a fellow at the Legal Defense Fund. "It can exacerbate racial disparities in terms of how schools are enforcing disciplinary codes and monitoring their students." Glaser, who says he is a “card-carrying member of the ACLU,” is all too aware of the risks of facial recognition technology being used improperly. That’s one reason, in fact, why he decided to release SAFR to schools first. “In my view, when you put tech in the market, the right thing to do is to figure out how to steer it in good directions,” he says. “I personally agree you can overdo school surveillance. But I also agree that, in a country where there have been so many tragic incidents in schools, technology that makes it easier to keep schools safer is fundamentally a good thing.” RealNetworks began developing the technology underpinning SAFR shortly after Glaser returned from a three-year hiatus. He hoped to reinvent the company , a pioneer of the PC age, to compete in the mobile, cloud computing era. RealNetworks’ first major product launch with Glaser back at the helm was a photo storing and sharing app called RealTimes. Initially, the facial recognition technology was meant to help the RealTimes app identify people in photos. But Glaser acknowledges that RealTimes “was not that big a success,” given the dominance of companies like Google and Facebook in the space. Besides, he was beginning to see how the technology his team had developed could be used to address a far more pressing and still unsolved 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 Glaser approached the administrators at his children’s school in Seattle, University Child Development School, which had just installed a gate and camera system, and asked if they might try using SAFR to monitor parents, teachers, and other visitors who come into the school. The school would ask adults, not kids, to register their faces with the SAFR system. After they registered, they’d be able to enter the school by smiling at a camera at the front gate. (Smiling tells the software that it’s looking at a live person and not, for instance, a photograph). If the system recognizes the person, the gates automatically unlock. If not, they can can enter the old-fashioned way by ringing the receptionist. According to head of school Paula Smith, the feedback from parents was positive, though only about half of them opted in to register their faces with the system. The school is approaching the technology with a light touch. It decided deliberately not to allow their students, who are all younger than 11, to participate, for instance. “I think it has to be a decision that’s very thoughtfully made,” Smith says of using this technology on kids. Today, University Child Development School uses SAFR’s age filter to prevent children from registering themselves. The software can predict a person's age and gender, enabling schools to turn off access for people below a certain age. But Glaser notes that if other schools want to register students going forward, they can. Each face logged by SAFR gets a unique, encrypted hash that’s stored on local servers at the school. Today, Glaser says it's technically unfeasible to share that data from one site with another site, because the hashes wouldn't be compatible with other systems. But that may change going forward, Glaser says. If, for instance, a school system wanted to deploy SAFR to all of its schools, the company may allow data to flow between them. "It's tempting to say there's a technological solution, that we're going to find the dangerous people, and we're going to stop them." Rachel Levinson-Waldman, Brennan Center For now, RealNetworks doesn’t require schools to adhere to any specific terms about how they use the technology. The brief approval process requires only that they prove to RealNetworks that they are, in fact, a school. After that, the schools can implement the software on their own. There are no guidelines about how long the facial data gets stored, how it’s used, or whether people need to opt in to be tracked. That's concerning, says Rachel Levinson-Waldman, senior counsel to the Brennan Center's Liberty and National Security Program. "Facial recognition technology can be an added danger if there aren't well-articulated guidelines about its use," she says. Schools could, for instance, use facial recognition technology to monitor who's associating with whom and discipline students differently as a result. "It could criminalize friendships," says Cusick of the Legal Defense Fund. 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 Glaser acknowledges the company will have to develop some clearer terms as it amasses more users. That’s especially true if it begins branching out to other types of customers, including law enforcement agencies, a market Glaser is not ruling out. But he says the company is still figuring out whether it will implement strict user guidelines for schools or simply offer “gentle encouragement” about how SAFR should be used. There are also questions about the accuracy of facial recognition technology, writ large. SAFR boasts a 99.8 percent overall accuracy rating, based on a test, created by the University of Massachusetts, that vets facial recognition systems. But Glaser says the company hasn’t tested whether the tool is as good at recognizing black and brown faces as it is at recognizing white ones. RealNetworks deliberately opted not to have the software proactively predict ethnicity, the way it predicts age and gender, for fear of it being used for racial profiling. Still, testing the tool's accuracy among different demographics is key. Research has shown that many top facial recognition tools are particularly bad at recognizing black women. Glaser notes, however, that the algorithm was trained using photos from countries around the world and that the team has yet to detect any such “glitches.” Still, the fact that SAFR is hitting the market with so many questions still to be ironed out is one reason why experts say the government needs to step in to regulate the use cases and efficacy of these tools. "This technology needs to be studied, and any regulation that’s being considered needs to factor in people who have been directly impacted: students and parents," Cusick says. If all schools were to use SAFR the way it's being used in Seattle—to allow parents who have explicitly opted into the system to enter campus—it seems less likely to do much harm. The question is whether it will do any good. This sort of technology, Levinson-Waldman points out, wouldn't have stopped the many school shootings that have, with a few high-profile exceptions like the shooting in Parkland, Florida, been perpetrated by students who had every right to be inside the classrooms they shot up. "It's tempting to say there's a technological solution, that we're going to find the dangerous people, and we're going to stop them," she says. "But I do think a large part of that is grasping at straws." Glaser, for one, welcomes federal oversight of this space. He says it's precisely because of his views on privacy that he wants to be part of what is bound to be a long conversation about the ethical deployment of facial recognition. “This isn’t just sci-fi. This is becoming something we, as a society, have to talk about,” he says. “That means the people who care about these issues need to get involved, not just as hand-wringers but as people trying to provide solutions. If the only people who are providing facial recognition are people who don’t give a shit about privacy, that’s bad.” A landmark legal shift opens Pandora’s box for DIY guns In the age of despair, find comfort on the "slow web" How to see everything your apps are allowed to do An astronomer explains black holes at 5 levels of difficulty Could a text-based dating app change swipe culture? Looking for more? Sign up for our daily newsletter and never miss our latest and greatest stories Senior Writer X Topics education privacy face recognition Dell Cameron Reece Rogers Reece Rogers Vas Panagiotopoulos Matt Burgess Vittoria Elliott Deidre Olsen 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 "

"An Oral History of the Day Everything Changed | WIRED"

"https://www.wired.com/story/an-oral-history-of-the-day-everything-changed-coronavirus"

"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 Garrett M. Graff Backchannel An Oral History of the Day Everything Changed ILLUSTRATION: TRACY J. LEE Save this story Save Save this story Save In the end, as history will record, the story that would have been the biggest news on Wednesday, March 11—the story that in normal times might have been the biggest headline of the month—will hardly register in America’s memory: That morning, at 11:06 am, a judge sentenced Hollywood super-producer turned super-predator Harvey Weinstein to 23 years in prison on sexual assault charges. Yet within 12 hours, the staggering fact that Weinstein—the force behind an entire generation of movie classics from Shakespeare in Love to Pulp Fiction —might very well spend the rest of his life in prison turned out not only not to be the biggest story of the day, it wasn’t even the biggest Hollywood story of the day. Instead, Wednesday, March 11, the 71st day of 2020, proved to be unlike any other in American history—the pivot point on which weeks of winter unease about the looming novel coronavirus turned in a matter of hours into a sudden, wrenching, nation-altering halt to daily life and routine. Just a day earlier, Americans across much of the country were still going into the office, meeting friends for drinks, and shaking hands in meetings. That morning, the number of coronavirus cases in the US crossed the 1,000 mark, up 10-fold from the prior week. Only 29 Americans had died. Backchannel Garrett M. Graff Backchannel Garrett M. Graff Backchannel Garrett M. Graff But on that Wednesday, the World Health Organization, which had only begun referring to the virus as Covid-19 a month earlier, declared the disease a global pandemic. Every hour seemed to bring major new developments: On Wall Street, after days of huge up-and-down gyrations, the Dow Jones Industrial Average fell 1,465 points and officially entered bear territory; Capitol Hill faced its first confirmed Covid-19 case; the NCAA announced it would play its basketball tournament without fans; and then, in rapid-fire succession that evening, President Trump gave an Oval Office address, announcing a travel ban from Europe, the NBA suspended its season after player Rudy Gobert tested positive for the virus, and Tom Hanks and his wife, Rita, posted on Instagram that they too had been diagnosed while in Australia and were recuperating. By Thursday, the national landscape had been undeniably altered, and Americans were panic-buying toilet paper. A whole new vocabulary—WFH, PPE, flattening the curve, social distancing, self-isolation, Zoom-bombing, and quarantinis—loomed ahead. Epochal events that had occurred just weeks earlier, from the Australian wildfires to President Trump’s impeachment trial to the drama of the Democratic primary, would seem instead to have occurred years ago. Within a month, thousands would be killed by the virus, as hospitals from New York to Detroit to New Orleans were overwhelmed, and more than 100,000 had been sickened. The economy would slide into a virus-induced coma, and some 17.7 million Americans would lose their jobs over the next month—a number larger than the populations of all but four states. Not even Harvey Weinstein would escape the drama: He tested positive for the virus on March 23. To capture the moment that everything in American life changed—launching us into an uncertain future of unknown duration—WIRED collected the stories and memories of more than 30 people who lived March 11’s drama first-hand, from the trading floor of the New York Stock Exchange to a basketball arena in Dallas to Capitol Hill to the airports of Europe. This oral history of a day that America will never forget has been compiled from contemporaneous quotes, social media posts, and original interviews. Quotes have been edited and condensed for clarity. All times listed are for US Eastern Daylight Time, unless otherwise noted. Tom Frieden, former director of the Centers for Disease Control (2009-2017) : By the end of January, I was saying this is either going to be bad or it’s going to be very, very bad. All through February, we were all trying to figure out how bad is this going to be? Peter Tuchman , stock trader, Quattro Securities : We’ve been on a wild tear for a year. The market has been headline-driven, news-driven, Trump-driven, tweet-driven with moves that are quite aggressive. On February 12 the Dow hit a record high of 29,551. The S&P was at a record high. We had a so-called deal in place with China. All the ducks had been lining themselves up for a massive market rally. The world had not really gauged the reality of the virus yet. 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 Mark Cuban, owner, Dallas Mavericks : I had followed all the data that was being distributed. Initially it was like, “OK, it’s flu-like, it can’t be too bad.” Then it was, “Oh, we don’t have a vaccine. And it’s not as much like the flu as it may be like SARS.” And “Oh, it hasn’t taken care of itself in Wuhan or in China.” My thought process was up and down. One day it was, “Oh, shit, this is a real problem.” Next day, “Well, maybe it’s not as bad as I thought.” The information seemed to change daily in terms of how people were describing not just the severity of it, but also the intensity and the spreadability of it. Carolyn Maloney , US Representative, Democrat, New York’s 12th district; chair, House Committee on Oversight and Reform : There were all kinds of conflicting reports on it. Many people up to that point had been treating it as something that was like a mild flu. “It will go away by the summer. It’s not that big a problem.” Dean Phillips, US Representative, Democrat, Minnesota’s third district : In the first few days of March, a number of us were invited to the White House from the Problem Solvers caucus to meet with Vice President Pence and Dr. Deborah Birx. I left the meeting convinced that there was a graphic disconnect between the risks the virus presented to the country and the administration’s either cognition or belief in the science. There was this expression that it wasn’t a great risk to Americans. A couple of days later we had the first Members of Congress briefing with a number of the agency leads. It was poorly organized, poorly coordinated. You could tell the agencies were not working well together. Elise Stefanik, US Representative, Republican, New York’s 21st district : The first real wake-up call to Capitol Hill was the American Israel Public Affairs Committee convention. When the news broke on March 4 that individuals at an AIPAC conference had self-quarantined after coming into contact with someone who tested positive, we started asking very specific questions, both from AIPAC and the broader Capitol Hill complex, as to potential exposure. It was so difficult to get any responses. 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 Douglas Brinkley, presidential historian : I live in Austin, Texas, and they canceled South by Southwest on Friday, March 6—that’s like the billion-dollar engine of the city—and when they canceled, people in Austin were wondering whether the organizers were being way too cautious. Scott Van Pelt, anchor, ESPN’s SportsCenter : Things were changing really quickly. I was at Disney the weekend before, and I said to my wife, “Are we idiots to go here?” My wife pooh-poohed it. Some of the narratives out there were that it was not that big a deal. Dan Pfeiffer, cohost, Pod Save America, former White House communications director for President Obama : I was on the third week of my book tour for Un-Trumping America. I was supposed to be on the road for the next 10 days in a different city every day. On Sunday the 8th, before I left, my wife and I had this long conversation, like, “What do we do about the coronavirus?” All my events were going forward. No one had even raised the prospect of changing them. Ryan Ruocco, play-by-play broadcaster, ESPN : In the first couple of weeks of March, I was traveling a ton and consciously booking flights at times when I could still get some semblance of sleep. That wouldn’t be my normal policy, but I was trying to make sure I was not letting my immune system down, knowing what was starting to fester with Covid-19. I’d been following it closely in Italy, because I was due to get married in June in Italy. That’s now been postponed till June 2021, unfortunately. Claudia Sahm, director of macroeconomic policy, Washington Center for Equitable Growth : When Italy shut down its northern regions that weekend—that was March 8—I was like, “Oh, we’re in for it.” We’re not South Korea. We’re a lot more like Italy. All this forecasting is playing out in my head, but it’s still early. I wasn’t sure if I was overreacting. Peter Tuz, president, Chase Investment Counsel Corp. : That Friday and Saturday, Russia and Saudi Arabia decided to try to drive US shale oil producers out of business and make life very painful for them. That helped trigger the big sell-off on Monday—the stock market was down 2,000 points, the largest point plunge for the Dow Jones Industrial Average ever. Our thought was, “This is going to be painful for the energy sector,” but it wasn’t clear that it was going to spill over to the larger economy. 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 Dan Pfeiffer : I get to San Francisco airport Monday the 9th, and it was totally packed, like it normally would be. I’m like, “OK, this seems like a thing not to be totally worried about yet.” I do an event in Milwaukee on Monday night, totally normal crowd. Everything you’d expect. The bookstore brought Purell, and we put some rules in about not doing photos, to minimize touching, but that was it. I woke up the next morning and flew to Minnesota. My wife, who had been talking about the coronavirus for a very long time now, called and said, “You really should cancel the rest of your events.” I called my publisher, and at first they thought I was being a little crazy and thought the venues would react pretty negatively. Within an hour, they’d had a bunch of other authors and venues cancel. We made the decision to go through with the Tuesday night event and then we pulled down everything for the rest of trip. Elise Stefanik: We were one of the first Capitol Hill offices to transition to teleworking. Monday, March 9, we were fully teleworked. We were the first door in our hallway to put up a sign that said we will be limiting excess meetings and taking public health cautions and transferring to telework. At this point there was not as much of a concern in the media and the general public. There was a real generational divide of younger members wanting to adjust the operations on Capitol Hill versus some of the older members who were adamant that business continue as usual. Patrick Hester , Stefanik’s chief of staff : We thought that there were probably already cases that weren’t being reported. So from our perspective, it was already on Capitol Hill and we wanted to make sure our staff got off the Hill as quickly as possible, just for their own health and so that we didn’t accidentally spread it on to constituents who were coming to visit. Yamiche Alcindor, White House correspondent, PBS NewsHour : The president had been downplaying this virus. You had that moment Monday night, the 9th, when Tucker Carlson was talking to his viewers, telling them, “People you trust—people you probably voted for—have spent weeks minimizing what is clearly a very serious problem.” This was one of the president’s favorite Fox News hosts speaking, it seemed, to the president himself. 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 Gabriella Orr, White House reporter, Politico : Tucker Carlson is somebody who has a fairly close relationship with Trump. He used that access to convey to him that there was a dire need for a more serious posture from this administration—that somebody needed to do something, and they needed to do it quickly. Philip Rucker, White House bureau chief , Washington Post: For me and my colleagues at the Post , we’d already started working from home. Tuesday, the 10th, was the first day the newsroom was closed. It was unsettling. The president had been really dismissing the threat and had not acknowledged the magnitude of the crisis. Liz Cheney, US Representative, Republican, Wyoming’s at-large district, and chair, House Republican Conference : Since January I had been talking to physicians, including some who served in the White House medical unit when my dad as vice president. The last time the House Republican Conference met in person was on March 10, and our guest that day was former Food and Drug Administration head Scott Gottlieb. That was one of the first times I remember hearing him explaining the whole concept of “this is what 'flatten the curve' means.” And “This is why flatten the curve matters” and talking about the extent to which we could see hospitals overwhelmed. Royce Young, NBA writer, ESPN : Things had started to shift in the NBA. On March 10, I was at an Oklahoma City Thunder practice, and we had new media policies in place. We talked to Danilo Gallinari, who was sitting at a podium, separated from us by like eight feet, which was unusual. From the reporter’s perspective, it felt a little dehumanizing. This player was up at the podium, protected. Then all of us media members are sitting shoulder-to-shoulder. It’s like, “Oh, I guess they don’t care about us.” Gallinari was Italian and has family that has been in lockdown basically for more than a month. He sat there that day and talked about how he was advocating for the NBA to close games off to fans. He was the first player to do that. President Donald Trump , via Twitter , 5:59 pm, March 10 : Best unemployment numbers in the history of our Country. Best employment number EVER, almost 160 million people working right now. Vote Republican, unless you want to see these numbers obliterated! Angela Merkel, German chancellor, news conference in Berlin, 6:51 am : The coronavirus has arrived in Germany. When the virus is out there, and the population has no immunity and no vaccination or therapy exists, then a high percentage—experts say 60 to 70 percent of the population—will be infected, so long as this remains the case. Maxi Kleber, power forward, Dallas Mavericks : Covid-19 has been around for a little while. It was a topic every day; you talked about it a little bit, but it hadn’t really hit us yet. I talk every day to my family back in Germany. At the very beginning, the first couple of days, my family in Germany was ahead of us. 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 Peter Tuchman: Even though it was across the ocean, it started all to become real. It felt like a tsunami—how it started in China, it rolled through South Korea and Iran, then it started to break over Italy. It was just a giant wave leaving wreckage in its path. Jen Flanz, showrunner and executive producer, The Daily Show With Trevor Noah: The morning of the 11th, I felt like things were definitely getting more intense and more real—it was more of a real thing. A bunch of people from The Daily Show were supposed to leave for South by Southwest that week, and it had gotten canceled very late in the game. And my father also works in hospitals in Queens, so I had been downloading with him, and I was like, “Oh, this is going to get bad.” Gabriella Orr : I remember that morning, having spoken with White House officials earlier that day and earlier that week, that the president just really needed to do something more than what the administration was already doing. I remember this collective feeling of angst inside the White House, but also among those of us covering it. At that point the virus was starting to impact the United States in a way that it hadn’t before. Peter Tuchman: The market can be skittish when it’s not sure what’s really going on. I remember trading, and everyone was starting to kind of get concerned. Markets overnight were trading in complete spirals as the virus started spreading across the world. Yamiche Alcindor: We were just beginning to realize the scale of this. It already seemed big. He had just signed this $8.3 billion law—these were huge numbers that were going to be thrown at the problem. This was all pre-2-trillion-dollars, of course. He’d asked for $2 billion, the Democrats had said it needed $8 billion. Now 2 trillion later, we’re already talking about more money. This is more expensive than anyone in either party imagined. Claudia Sahm : Frankly, the night before, the 10th, I was in a bit of a panic because I was worried that I was overreacting. It was like gaslighting the way Trump and Republicans and Fox News would talk about the coronavirus. Like, “We’ve got this one, it’s not a big deal. It’s like the common flu.” Listening to that, I was saying, “We need to get going.” Congress needs to do real things. That morning, I stood in front of the House Democrats at the minority whip breakfast and told them what they needed to do with a relief package. I told the House Democrats that the $8.3 billion package that they had passed the week before was an insult. 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 Tom Frieden : It’s been really clear that it’s been too little, too late, for a long time. Carolyn Maloney: I had worked very, very hard to get Dr. Anthony Fauci to testify before my committee. I saw him at a briefing and went up and asked him to testify. His staff was telling me that he couldn’t testify unless he had a month’s notice. He had told me he’d be glad to. He has served six different presidents, both Republican and Democrat. And in my introduction, I introduced him as America’s doctor. It was a very tense hearing, because about five minutes prior to the hearing we were told the agencies would need to cut the hearing short. There was an emergency meeting at the White House, that they could only testify for an hour and then they had to leave. 10:06 am —US House of Representatives, House Committee on Oversight and Reform Hearing, Washington, DC: Carolyn Maloney: Is the worst yet to come, Dr. Fauci? Anthony Fauci, director, National Institute of Allergy and Infectious Diseases : Yes, it is. Carolyn Maloney : Can you elaborate? Anthony Fauci : Whenever you have an outbreak that you can start seeing community spread—which means by definition that you don’t know what the index case is and the way you can approach it is by contact tracing—then it becomes a situation where you’re not going to be able to effectively and efficiently contain it … We will see more cases, and things will get worse than they are right now. How much worse will depend on our ability to do two things: to contain the influx of people who are infected coming from the outside and the ability to contain and mitigate within our own country. Bottom line, it’s going to get worse. After the hearing was cut short, there was no sign of any emergency White House meeting. Dan Pfeiffer : The Minneapolis airport that morning was empty—it was shocking. My flight was very empty. My wife had told me 100 times to make sure I wiped down everything in my area, and I’m sitting next to this guy—he’s actually watching Fox on the Direct TV next to me—and I wiped down everything. He sees me wiping down and I guess he sees that he has permission to do what his wife had also told him to do—so, he takes out his wipes and wipes out everything. 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 Ryan Ruocco: It had been particularly eerie traveling those two weeks. On Wednesday, it felt like it had hit a new crescendo. I noticed every single person wiping down their seats. Liz Hannah: I had a meeting that morning; we hugged when I came in. It was sort of an awkward joke—should we hug? Is that safe? It was this weird thing at that point. That was the last conversation or meeting I’ve had where Covid was not the primary topic of conversation. Tedros Adhanom Ghebreyesus, director general, World Health Organization , Covid-19 media briefing , 12:16 pm: WHO has been assessing this outbreak around the clock, and we are deeply concerned both by the alarming levels of spread and severity and by the alarming levels of inaction. We have therefore made the assessment that Covid-19 can be characterized as a pandemic. Pandemic is not a word to use lightly or carelessly. It is a word that, if misused, can cause unreasonable fear or unjustified acceptance that the fight is over, leading to unnecessary suffering and death … We have never before seen a pandemic sparked by a coronavirus. Peter Tuchman: That was the date that they used the word pandemic. It’s funny how keywords are so significant in the way the market trades. The minute that word came out—I remember it so well—the market just careened off a cliff. Yamiche Alcindor: The WHO calling it a pandemic made it seem like something more real. I had family in Florida—it started to seem like it was sinking into everyday life. They’re makeup artists, they work in laundries, they work in factories, and they were asking, “What’s this virus?” Peter Tuchman: The VIX—the volatility index—went from 20 to 38 to 60. That is a financial instrument based on fear. When you see it go that way, you can sense the fear. It’s like being in the room where it happened—like a Hamilton moment. Peter Tuz : The unknowningness of the situation and its ramifications on the US economy, you started thinking about that more and more. Claudia Sahm : Financial markets always look ahead. They’re reacting to things in the moment, but they’re often looking ahead and trying to react to that and pricing that into the stocks. What you saw is markets start falling. It made total sense. Investors do not like uncertainty. This is uncertainty layered on top of uncertainty. 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 Peter Tuz : I’ve been doing this since ’84—those are gut-wrenching moments for anyone who manages other people’s money. You feel it in your core. You wish you saw it coming, but the reason the markets fall so much is it’s unpredictable. Gabriella Orr: Every hour on the hour until the president sat behind the Resolute Desk to give that address, there was something happening that just propelled the urgency more. Douglas Brinkley : In 1929 Herbert Hoover acted like the Great Depression and the collapse of the stock markets and bank foreclosures weren’t his problem, it was a global issue—don’t blame me—it’s not as big as people say. And it’s why Hoover is ranked very low as a president. And early in the coronavirus crisis, Trump behaved like Herbert Hoover. He was like an ostrich with his head buried in the sand, still wanting to talk in political terms about the pandemic, thinking how a pandemic would damage his brand instead of really grappling with the dimensions of the shit storm that might be hitting America. Gabriella Orr: The primary motivation behind the president’s Oval Office address was that they really wanted to do something to stabilize the stock market. They were concerned about uncertainty and fluctuations. They felt a primetime Oval Office address—the second one that Trump has given since taking office—would somehow alleviate the anxiety. So they organized this moment where he was to address the nation from the Oval Office, give a somber but also serious speech about the direction that his administration would take to combat coronavirus. Peter Tuchman: At that point during that week, everybody was desperate for leadership—whether you are a Republican or a Democrat or whatever you are. As an American or as a human being, we were desperately looking for some leadership. There were so many mixed tales being told about, “Are we prepared or not? Is the world coming to an end or not? Is anybody telling the truth or not? Are we going to support whatever happens economically or not?” We needed leadership—the market needed leadership. Dan Pfeiffer : A national televised address is the biggest weapon in the president’s communications arsenal. It is a card you really only get to play once. I’ve been involved in many, many conversations about if, when, and how you do these remarks. Obviously, there are times when events force them to happen faster than you would like—the most famous example in the Obama era would be bin Laden—but other times, like when you’re in the midst of an ongoing crisis, you have to get all of your ducks in a row. 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 Douglas Brinkley: Usually the Oval Office address is the time when you really could drive points home—Ronald Reagan in 1986 after the Challenger disaster or George W. Bush talking from the Oval Office on 9/11. Gabriella Orr: In talking to White House officials, they really thought that this was a plan that would work. They thought that the president had worked carefully on his speech with advisers like Stephen Miller and Jared Kushner, that close inner circle that has always been around the president, that has always made him feel the most comfortable. They were the ones directly involved in writing the address that President Trump delivered that evening. Ryan Ruocco: As I’m getting ready for the game, I am definitely distracted—constantly following what the latest updates are on how different leagues and teams and conferences are reacting to what’s going on with coronavirus. I love what I do, I love it—and normally on a game day, those hours before we actually go to the arena, I’m just totally, completely engrossed in the preparation for the game—going through storylines and stats and updating numbers and making sure I’m ready to go on air. But on this day, it just felt like it was taking a backseat to the news. It was hard to totally lock in. Royce Young: There was a Sports Illustrated reporter, Chris Mannix, who had written something earlier in that afternoon about how the NBA is going to have to shut down the season. I read it with this totally dismissive mindset, like, “Get a load of this thing! Chris Mannix shut down the NBA season? Jeez, man. Pump the brakes.” President Donald Trump, via Twitter , 2:52 pm : America is the Greatest Country in the world. We have the best scientists, doctors, nurses and health care professionals. They are amazing people who do phenomenal things every day. Together we are putting into policy a plan to prevent, detect, treat and create a vaccine against CoronaVirus to save lives in America and the world. America will get it done! Peter Tuchman: We were in hyper-stress mode because of what the market had been doing. You can sense the fragility of a market on the floor of the stock exchange. That room is full of press. It’s full of brokers. It’s full of market makers. It’s the epicenter of all things headline. In a very visceral way, you could feel it. You have these billboards—these screens running in real time, the S&P, the Dow Jones Industrial Average, the volatility index, the real estate index, and whatnot. It’s a plethora of information. You could just feel the sense that the screen is almost shivering in a way. When you see stocks and markets trading at intervals of hundreds of points—stocks dropping 5, 10, 15, 20, 30 percent at a clip—there’s something just extraordinary about 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 Claudia Sahm : I started at the Federal Reserve in 2008. I focused on consumers. I did a lot of work on how fragile the finances of a lot of families are. I kept working on the macro economy on through the recovery from the Great Recession. And it was horrible—policymakers didn’t do what they needed to do, they really abandoned many Americans. When I saw all these events starting to play out—the public health crisis, the response of some countries like Italy to shut down—all of a sudden I was looking into the future, and the future was moving really fast. I was convinced that not only were we basically falling off the cliff economically, but we were going to fall really far. Many, many Americans are never ready for a recession—and no one was ready for this recession. Peter Tuchman: We’re at a crossroads where people’s fear about what’s happening in the market moment by moment in real time is meeting up against their fear of the health and well-being of their family— which is unheard of. Everybody kept asking me, “So what does this relate to? Does it remind you of the crash of ’87? Does it remind you of 9/11? Does it remind you of the financial crisis?” I had to be honest with them. I said, “It reminds me of none of that stuff.” Claudia Sahm : The stock market was giving us a very clear signal that we have a problem—a big problem. This is a real thing they’re reacting to. Peter Tuchman: What differentiated that week as the market was going—you could just see in people’s eyes—first they were worried about how they were going to do the best for the customer with the order they had in their hands, whether it was a buy or sell, in a market that was just careening off a cliff. Then, how they were going to navigate through—God forbid—their family members, their elderly parents or something, getting sick. What was going to be the condition of their 401k and retirement funds when all this was said and done? Then, you know, what is life going to look like on the other side of this? That’s unprecedented. You had the sense in people’s eyes that this was more than just a financial sell-off, that we were really at the epicenter of some epic shit about to happen. 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 Peter Tuz : In a really dramatic market crash, very few things hold up well. When you have these big crashes, you’re just frozen like a deer in the headlights. It’s a very paralyzing feeling. Peter Tuchman : The fastest sell-off in history. CBS MarketWatch , market snapshot , 4:55 pm : The Dow Jones Industrial Average plunged 1,464.94 points, or 5.9 percent, to settle at 23,553.22, with the blue-chip benchmark’s close below 23,641.14 marking a bear market, widely defined as a drop of at least 20 percent from a record intraday peak. Miles Kahn , executive producer , Full Frontal with Samantha Bee: Everything got really, really crazy really, really quick, like everything ramped up in like a matter of 72 hours that was really kind of shocking. Jen Flanz: Throughout that week, me and a few of the other late night showrunners—we’re normally friendly anyway, but we don’t usually discuss show plans—had started regrouping about what we were doing. It started to seem like it was a bad idea to have big groups of people. For the safety of everyone we should stop having an audience. That Wednesday night, we all coordinated to put out a press release saying that as of Monday, we’re no longer going to have audiences. Miles Kahn: That morning, we got word that there was someone sick in our building—just one floor below us at CBS News. Some worry really started creeping into the office. We pretty much sent everybody home that we possibly could, except for the core crew in the studio. The building sent out an email saying that they did a decontamination, but we’re writers and TV people, and we can be a neurotic bunch. I think everyone was a little on edge, and I think then there was some misinformation that maybe it was more than one person. Jen Flanz: I check my email, and a bunch of other late-night shows are like, “We’re evacuating. Our building’s being evacuated.” Miles Kahn: We were supposed to shoot at 6 pm, and we’re pretty sure they’re going to try to throw us out of our own studio. We bust a move and go through our rehearsal and our rewrite process as quickly as possible. We canceled the audience altogether, and we decided just to have a smattering of people in the audience. I think there was maybe just six or seven people. And we shot it as sort of a joke. We ended up shooting the show about an hour early. Our head writers Mike Drucker and Kristen Bartlett, they had a great idea to pepper the script with jokes that Sam had never seen. We had to change the show from like this big presentational show for a crowd to like, it’s going to be more like The Soup With Joel McHale. That was our last day in the office or in the studio. 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 Sean Lane, chair, St. Patrick’s Day Parade Board, New York City : The New York City St. Patrick’s Day parade is the largest civilian parade in the world, by far. We could have anywhere up to a quarter of a million people marching and 1 to 3 million people on the sidelines. We have over 6,000 first responders in the parade. We have the National Guard, the 69th Regiment leads the parade—they’ve led the parade for 169 years. We were hearing a lot of concern. I had spoken to Governor Cuomo, and he said, “What would we think if we postponed the parade?” I said, “It wouldn’t be up to me because I’d have to have a board vote”—we had a board meeting the next morning. And he said, “I think we need to do this now.” I said, “Fair enough.” I respect that he’s the chief executive in New York. And then he went on CNN and announced it was postponed. In the American Airlines Arena in Dallas, an NBA game was about to get underway: Dallas Mavericks versus Denver Nuggets. Maxi Kleber, power forward, Dallas Mavericks : Before the game, there was an announcement that Rudy Gobert is sick and is not at the game, but they didn’t say the reason yet. Mark Cuban: I went in to the locker room and talked to the team and coaches. One of the players, Luka Dončić, asked me if I thought the season could be canceled or postponed, because he’s European and there were some things that were happening over in Europe with soccer leagues. And I said, “You know what, Luka? No one knows for certain. But I’d say if I was a betting man, five, maybe max-out 10 percent chance that the season gets postponed or canceled. But that’s so highly unlikely.” Maxi Kleber : Five percent—that was the number that we talked about before the game. We were all like, “OK.” Doris Burke, broadcaster, ESPN : We were over there early, because Luka Dončić wanted to do interviews early. Then you do the coaches. At that point, that rule is instituted about no shaking hands, sit six feet away. Normally, you’d exchange a handshake or even a hug, depending on how well you know these guys. We’re just looking at one another. We sit down in chairs six feet away. It just felt strange. 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 Mark Cuban : I come out into the arena right with the opening introductions. I’m walking out, the lights are down, and I’m expecting to look up and have an arena that’s half-full at best. I’m thinking, “This is the ultimate example of someplace individuals should be concerned about spread of the virus.” I walk out and the place is packed— packed —like it was any other day of the week, the day before, a month before, a year before. That was just incredible to me. I thought, “Maybe the markets are telling me something. Let’s go play this game and see what happens.” In Oklahoma City, the home team Thunder was scheduled to play the Utah Jazz at the Chesapeake Energy Arena. David Holt, Oklahoma City mayor : We still didn’t have a case in the Oklahoma City Metro at that time. Our first state case had been found in Tulsa the previous Friday. Over the weekend, I had reached out to our Oklahoma City-County Health Department—they had a relatively new director—and I reached out to him and suggested that we probably needed to meet and talk. I was starting to see cancellations in other places in the country. We actually had that meeting the morning of the 11th in my offices. We talked in general about some of these things and started to broach these topics. Royce Young: Rudy Gobert’s status for the game—it was bizarre, he was listed as questionable just 30 minutes before tip-off. Then I saw the Thunder’s head doctor, Donnie Strack, come running off the bench, literally seconds before tip-off—the ref’s already got the ball in his hands. Players are lining up in a circle, getting ready for tip-off. I see Donnie Strack running out, and I knew right then and there: Something’s going down. David Holt: If Rudy Gobert’s test results had came back at 6 o’clock or 8 o’clock, it would have been a totally different situation. If it had come at 6 o’clock, they just would have canceled the game. That would have been dramatic, but not in the same way—it wouldn’t have happened in front of everybody. At 8, they probably would have finished the game. But at 7 o’clock, when it did come back, it caused this surreal decisionmaking process to occur not just in front of 18,000 people but in front of the world. Royce Young: Still, nobody knew it specifically had something to do with the virus, but I remember all these arena employees coming out and spraying and wiping down and sanitizing the first four rows of chairs. That was really like, “whoa.” You felt like you were in a movie at that point. Oh, the outbreak is happening here. They’re sanitizing the arena floor? That’s kinda crazy. 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 Scott Van Pelt, anchor, ESPN’s SportsCenter : I was in Bristol, Connecticut, in the conference room where I prepare to do SportsCenter every night. It’s this big fishbowl—we’ve got six or seven screens on a wall, one big screen with the biggest game of the night. The Thunder and the Jazz were on one of the ancillary screens. We looked up like, “What the fuck’s going on? What’re they doing?” Royce Young: Everybody was confused. To me, it was obvious: This has something to do with Covid-19. Duh! David Holt: That night, I was at home. I’d put on my pajamas, and we were sitting down to dinner and following what was happening at the arena. Obviously, it was just as surreal on television as I’m sure it was in person. My phone started blowing up, and it was just a million different things going on. Royce Young: After Donnie met with the three games officials, the Thunder’s Rob Hennigan came out onto the court as well. They’ve got this little pow-wow going on. One of the officials, Ben Taylor, comes over to the sports table and tells the public address announcer, “Hey, we’ve been told by the league to delay the start of the game. I don’t know why, but we’re just delaying the start of the game.” They sent the players back to the locker rooms. Fans knew then something more significant is going on. Dan Pfeiffer: When that day started moving so fast for me was Rudy Gobert—he was on my fantasy basketball team and this was the final week to make the playoffs. Six teams make the playoffs, and I was in seventh place battling with the person in sixth place. This game was going to determine whether I made the playoffs, and so the health of Rudy Gobert was high on my list, because he had been marked as questionable. Royce Young: I left the floor when the players left—they wanted me to go on SportsCenter as fast as they could get me on. The fans were still out there, and they brought out some entertainment—they did the halftime show before the game, trying to fill the time. 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 David Holt: Normally, you can handle things from home, but I definitely felt at that moment like I had to go somewhere. I got dressed and began to make my way toward the city-county health department, where a bunch of the public health leadership gathered. A lot of the city management leadership gathered at City Hall, and we were linked on a phone call. We just started working through various issues. Royce Young : Eventually, the public address announcer did end up making an announcement, saying, “The game has been postponed.” He said it twice. He said, “You’re safe. We want you to leave in an orderly manner. You’re safe.” He tried to stress it. They make that announcement, and then the arena goes silent. Everybody complied. As the 9 pm hour began in Washington, DC, Americans and across the country settled down to watch the president’s address from the Oval Office. President Donald Trump, Oval Office, White House, 9:02 pm : My fellow Americans, tonight I want to speak with you about our nation's unprecedented response to the coronavirus outbreak that started in China and is now spreading throughout the world. Philip Rucker : I was on tap to write the lead story for the front page. I spent the afternoon reviewing the president’s public record on the virus. We’d heard rumors that there might be a travel ban, but no one knew for sure. When the speech started, I just sat down on the couch, had a La Croix—Pamplemousse, the grapefruit one—and took notes as he was speaking. Yamiche Alcindor: I watched the president’s speech on-set at PBS NewsHour. I was watching alongside Judy Woodruff, our anchor, and with Lisa Desjardins, our congressional correspondent. We were sitting very, very close. The social distancing hadn’t sunken in, and I definitely wasn’t making personal changes in my life yet. Elise Stefanik : In times of crisis, it’s very important to hear directly from the president. I remember thinking, “this is a historic moment.” This is only the second presidential address. It was important to help raise the profile of this issue, because he has the ability to speak to everyone in the country and get the immediate media coverage. 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 Philip Rucker : At the very beginning, I remember thinking his heart wasn’t in it. There was a lack of passion and enthusiasm that I’m used to from other speeches. He was just going through the motions. It was a speech written for him and designed for him to show leadership in a crisis he didn’t really believe in. Yamiche Alcindor: Watching him speak, I was thinking, “This is President Trump at a teleprompter, when he’s carefully delivering prepared statement.” He’s calm, not joking around, he’s using every single minute of his time to explain his message. The President Trump I’ve covered, he goes off on tangents, he makes light of things, he lashes out at opponents—there was none of that. This is a very calm and prepared version of President Trump, but he was still managing to get digs in to other countries—this was still a Trumpian worldview. America First. We have to protect ourselves from other countries, and because of their own shortcomings, America now is at risk. President Donald Trump: And taking early, intense action we’ve seen dramatically fewer cases of the virus in the United States than are now present in Europe. The European Union failed to take the same precautions and restrict travel from China and other hot spots. Douglas Brinkley: He seemed nervous and distracted. Philip Rucker : He was twiddling his thumbs from behind the desk. It was striking how different it was from the tone and passion of other speeches—like when they killed Baghdadi. He really believed in that. He wanted that moment; he lived it fully. This was not a very carefully thought-through public moment. President Donald Trump: These prohibitions will not only apply to the tremendous amount of trade and cargo but various other things as we get approval. Anything coming from Europe to the United States is what we are discussing. Gabriella Orr: I remember watching it, and the moment that he said he was suspending all travel from Europe, I paused my TV and rewound to and make sure I’d heard him correctly. He’d already placed a travel ban on China, and we knew that there was something that he was going to be doing to restrict further travel affected, but the way that he phrased that just came out of left field. It caught a lot of us off guard. 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 Yamiche Alcindor: That travel ban was a huge deal. The president was saying our European allies are no longer welcome in the United States? The president was already starting to blame other countries, saying the EU should have taken more action. It was clear he was trying to take control, but he was already deflecting responsibility. Dan Pfeiffer : In the moment, it wasn’t clear that Trump was offering any solutions. There was no distinct purpose for it other than speaking. Was he telling people to be afraid? Was he telling people not to be afraid? Was he offering specific guidance on the things you should and shouldn’t do to protect yourself? Not really. Dean Phillips : It was so troublesome and so dismaying and so clear that the leader of the free world didn’t seem to grasp or understand the magnitude of what was forthcoming. Elise Stefanik: As a former White House staffer during the financial crisis, I vividly recall that circumstances change so quickly in these times of crisis. I could sense from a former staffer’s perspective that this speech was written very quickly. That’s where you find yourself oftentimes in these crises. Looking back at the financial crisis, which was changing at a similar pace, it’s tough as a White House staffer to deliver a message that will be consistent when delivered, as where you’ll be a week or two weeks later. I think they did an admirable job, but I understand how challenging it is when the turnaround time is that quick. Philip Rucker : As it became clear what had happened with the speech, my task for writing the story shifted. Here was a president trying to take command of the moment, and all of a sudden the president wasn’t correct in regard to the actual wording of the order. We have a really dramatic discrepancy. As the president was making his address, the NBA games were under way. Doris Burke: The Mavericks-Nuggets game starts to unfold, and I open up Twitter in a commercial break and I see that Rudy Gobert has tested positive. I hit the talk-back button and say to my producer, Ian, “I’m 99 percent sure that the game in Oklahoma City is not going to happen. Rudy Gobert has tested positive.” And he says, “We can’t go with it, Doris, because we don’t have it confirmed. Just give me a minute.” 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 Royce Young: I think it might’ve been around 9:30 pm Eastern time where somebody actually tweeted out, “Rudy Gobert has tested positive for coronavirus.” I’m thinking he had just gotten a test, and they’re waiting on the results to clear it so they could start the game. Then it was like, “Oh, no, he actually had it.” That was jarring. Dan Pfeiffer : All of a sudden, it’s like, “He has coronavirus.” And then: “The game is canceled.” Ryan Ruocco, anchor, ESPN : When I saw Gobert was diagnosed, I knew everything was going to change. Scott Van Pelt: Five minutes later, the NBA season was postponed. David Holt: The management of the 21C Hotel, where the Jazz had been staying, was obviously stressed, because Rudy Gobert was there. Here it was being broadcast around the world that he had Covid, which at that moment was like finding out that you had the black plague. People didn’t know what that meant: He has Covid. OK, does that mean everyone in this hotel now has Covid? That’s what the reaction was. Ryan Ruocco: We go through the next chunk of action in the Mavericks game in Dallas before the next time-out, and then as we go to break, my producer Ian’s already giving me 10 counts, and tells me in my ear: “Ten, Nine, Ry—tease on the other side, ‘Huge news coming in the NBA’—three, two, one.” So I just get in, “Big news in the NBA when we’re back,” just super quick to get out that tease. I don’t know what it is. Royce Young: It was like a double whammy there—Rudy Gobert’s tested positive for the coronavirus, and then a few minutes after that, Woj tweeted out that the NBA suspended its season. It crystallized very fast. Mark Cuban : The game’s going on, back and forth—good game. People were having fun. We’ve got this one guy, Bobi—Boban Marjanović—he’s 7 foot 4. Huge. The biggest human being you’ve ever seen in your life. He was having the game of his career. The game was going our way. Then in the middle of the third quarter, or whatever the timing was, somebody tapped me on the shoulder and that’s when the news of the season being suspension hit me. I was just stunned. 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 Ryan Ruocco: The shot of the night, from our director, Jeff Evers, was the shot of Mark Cuban on his phone getting the news about the NBA season. He’s just totally shocked. Doris Burke: To see his face was a really, really powerful, powerful moment. Mark Cuban: The shit had hit the fan. This is for real, and this is much bigger than basketball. Ryan Ruocco: The shot was so poignant because it seems this incredibly raw reaction to ridiculous news. You realize that none of us are impervious to the shock of this moment. Mark Cuban : On one hand, I was like, “Oh, my goodness, what’s going on?” And then number two was, “Oh, my goodness, are we at risk?” And then number three is, “Oh, my goodness, what about everybody here?” The CEO-slash-entrepreneur in me started taking over: “What do I have to do? Who do I have to consider? What comes next?” Scott Van Pelt: Everything in that moment is just, “Holy shit, this is all over, man. Like, everything’s done.” I don’t know why, but I just had absolute clarity: We’re done. The NBA just said, “We’re not playing.” Well if the NBA isn’t playing, the NHL is not going to play. If the NBA’s not playing, college basketball, there’s no way to justify it. The dominoes were going to fall in every direction and they weren’t going to stop. Maxi Kleber : I came off the court, I was sitting on the bench next to Luka, and Luka looked at me and said, “Season’s over.” I was like, “Ha, ha, funny.” And he was like, “No season is really over.” And I was like, “What? There’s no way.” He said, “Gobert, he tested positive. So they had to shut down like the whole league.” And I was like, “Wow, that’s crazy.” It happened so fast. Doris Burke: We go to the first break, we come out and the tone and tenor of everything is entirely different, as you could imagine. The game felt inconsequential, and it was hard to concentrate. Ryan Ruocco: Doris herself did the broadcast. We didn’t know it at the time, but she turned out to be positive testing for Covid-19. 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 Scott Van Pelt: In real time, it went from going to do an update about one story and then, very quickly, it became the story. And it wasn’t just the story in sports. Rudy Gobert getting the virus was the story that changed the entire narrative of this pandemic in our country, period. End of story. The players finished the game. The 9 pm hour unfolded with alarm across the US. Tom Hanks, actor, 9:08 pm ET, via Instagram : Hello, folks. @ritawilson and I are down here in Australia. We felt a bit tired, like we had colds, and some body aches. Rita had some chills that came and went. Slight fevers too. To play things right, as is needed in the world right now, we were tested for the Coronavirus, and were found to be positive. Well, now. What to do next? The Medical Officials have protocols that must be followed. We Hanks’ will be tested, observed, and isolated for as long as public health and safety requires. Not much more to it than a one-day-at-a-time approach, no?* Gabriella Orr: Oh, my gosh! I had just watched the movie about Mr. Rogers a couple weeks before, and I couldn’t believe it. It was just surreal to see. Jen Flanz: The Tom Hanks diagnosis, I remember hearing and being like, “OK, this is one of those urban legends—like, Zack Morris died in a car crash kind of thing.” Tom Hanks, the biggest actor ever—of course, that’s who the first rumor is, right? Then once it was confirmed, I was like, “Oh wow.” Of course, there were already people in New York who were dying, but hearing Tom Hanks had it made it real for a lot of people. Elise Stefanik: You cannot think of a more iconic figure to test positive as being a reality check for the American people. Liz Hannah: It hit the most beloved actor and one of the nicest actors—it wasn’t just that the virus hit someone I knew, it touched someone who was a spokesperson for what the good part of our industry can be. And it wasn’t just him—it was him and Rita. It was really frightening. 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 Mark Cuban: I got my kids, had them ready to leave. And then I went to the locker room, talked to the players and coaches—primarily individually—and basically just said, “Look, I don’t know what’s next” and “We’ll go home. Don’t go anywhere else!” And “We’ll see what was going to happen next.” As soon as we know anything, you’ll know something. We’ll communicate everything. Walking out with my kids, it was like, “Oh, shit, what comes next?” That’s when your parental instincts take over. What world are these kids growing into? My kids are 10, 13, and 16. What are they going to face? Where does this take the world—their world? David Holt: It was just a remarkable moment in history, because if you had designed an event with the intent of getting people’s attention, you wouldn’t have changed a thing. It was the most dramatic way for Covid-19 to be thrust into the lives of every American. Marina Fang, reporter, Huffington Post, via Twitter , 9:39 pm : What a year the last hour has been. In Europe, Americans were scrambling, reacting to the president’s announcement of a travel ban. Laura Lawson Visconti, Lisbon, Portugal : My husband and I own a couple of businesses together, and it’s really hard for us to take time to travel and just escape. We had planned a trip to Europe for literally 11 months. We flew into Barcelona for a few days, spent some time in Spain, and then we flew over to Portugal. We’d been in Lisbon for a total of five hours. We had maybe been asleep for two hours when our phones started going off at 1:15 am our time [9:15 EDT]. It was my husband’s stepdad, in the Bay Area in California, and he had watched Trump’s address on the European travel ban. It was just instant pandemonium and chaos: “Holy shit. How do we get home immediately?” It was very confusing initially. Mike McIntire, Paris, France : My wife and I were in an apartment in Paris nearing the end of a week-long stay. Everything was still open in France. At that point, there was no social distancing really going on. All of a sudden, my cell phone rings—it woke me up at 2:15 am. My daughter calling us, “I don’t know if you guys know, but Trump just announced that they’re banning all travel from Europe, effective like midnight Friday.” We hadn’t heard that, obviously. We were asleep. 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 Laura Lawson Visconti : We had a lot of concerned friends and family members back home who were urging us to get home as quickly as possible. We watched the Oval Office address, we called our airline, Virgin Atlantic, we were on hold for two hours in the middle of the night. Mike McIntire: I jumped online to see if I could reschedule the two tickets we had. I immediately got the sense that a whole bunch of people were trying to do this at the same time. We tried calling the airline and were told it was a four-hour wait-time to talk to somebody. Not knowing what else to do, I just start looking for two completely new tickets. These fares would show up, and then you go to click on it and it would say it was not available. It was very apparent that people were very quickly—just like we were—trying to snap up any kind of last-minute one-way flights they could get out of Europe. I finally found two economy seats available through for the next day, March 12, for $2,500 apiece. There was nothing else available. Laura Lawson Visconti : We thought, “Well, we don’t want to be stuck here.” We booked out-of-pocket tickets from Lisbon to London the next morning, then an overnight stay in London on the way back to San Francisco. Mike McIntire: No sooner had I pressed the purchase button than on CNN they came back on and said, “Wait! Now it looks like Americans are exempt from the travel ban.” I went back and tried to cancel the tickets I had just bought, and I couldn’t do it. I call the airline number, and now it was up to a six -hour wait time. It was a nightmare. In the US, the day’s implications were still coming to light. Gabriella Orr: It was less than an hour after the president’s speech that acting acting deputy secretary of Department of Homeland Security, Ken Cuccinelli, tweeted out a statement to clarify the president’s remarks. And then after that, the White House released text of Trump’s order to provide further clarity. Dan Pfeiffer : To allow that to happen was both an obvious breakdown of how government works and very scary. If you can’t get the speech right, you’re not prepared to contain the pandemic. 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 Gabriella Orr: Almost immediately, you saw agency officials trying to clarify the president’s remarks. Trump himself posted a tweet saying the travel ban wouldn’t apply to cargo coming in from European countries, with the White House adding that it would not apply to US citizens traveling back from Europe. There was a whole mess of statements that he made during that Oval Office address that needed to be cleaned up after the fact. Yamiche Alcindor: This is the time when everyone gets scared. As a reporter, you’re trying to do your job, and then I’m fielding calls from my mom and other people wondering, “What the heck?” This is a moment where everyone says, “What does this mean for my personal life?” Peter Tuchman: We all the lead different lives. We all have different priorities. There are people who love food and fashion; there are people who love travel; there are people who love sports; people who love money and markets. We have this amazing ability as humans to disconnect from stuff that’s very real, unless it’s in our back door. There were people who still were able to buffer themselves from the reality of this whole thing until they found out that the NBA was shut down for the year, until Tom Hanks, one of the greatest actors in the world, somebody we all identify with. It made it real for people. “Oh, my God.” The market had already taken a trillion dollars out of it, and people were dying in the streets of Italy, but it had not really been real yet to anybody. Claudia Sahm : I grew up on a farm in Indiana, and I call back home now daily to talk to my parents. It wasn’t until the NBA shut down that my dad, who is an Indiana basketball fan, was like, “Oh, this is real.” It got attention. Fox News could tell you over and over again it isn’t a problem, but when what you do every single night is watch basketball and it’s gone—it’s a wake-up call. Peter Tuz : That was the day that disbelief went to belief. Your thoughts went from “I know this will affect the US, but I don’t know whether this will dramatically affect life as we know it” to “this is a real crisis. It just affected life as we know it.” The NBA getting called off opened the door to everything else being called off. Everything reverberated from that point on. 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 Gabriella Orr: The feelings inside the White House changed in a matter of minutes that day. From heading into the president’s remarks, thinking that this is going to be a moment that really marked a change in his response to this virus—a moment that really rallied the country behind the White House and behind the president—and then, right afterward, talking to White House officials, they were just so disheartened. They were so disappointed at the way it unfolded. Morale just bottomed out, and it hasn’t really repaired itself. That night, the first confirmed case of Covid-19 was identified on Capitol Hill, a staffer in Washington senator Maria Cantwell’s office. Liz Cheney: We knew that it was inevitable that there would be positive cases on Capitol Hill. But the news that somebody actually did test positive on Capitol Hill helped to encourage a lot of people to recognize that we needed to take action to begin operating in a different way. When it became public that a staffer on the Senate side had tested positive for Covid, I made the decision that we were not going to hold the conference meeting that was scheduled for the next day, that we were going to do that by phone. To us, the news of the positive test on Capitol Hill was more significant than Tom Hanks. Elise Stefanik: The past two years are extraordinary if you think about the concept of time and focus. The Mueller testimony—that seems like years ago. The impeachment hearings in the House, which obviously was November, December—that seems certainly more than a few months ago. The January Senate trial also seems like a distant part of the past. The pace of these very significant events. It’s just so unpredictable, the vastness and the severity of the issues over these past two years. LeBron James, via Twitter : Man we canceling sporting events, school, office work, etc etc. What we really need to cancel is 2020! Damn it’s been a rough 3 months. God bless and stay safe. Matt Warburton, executive producer, The Mindy Project, via Twitter , 12:08 am, March 12 : Today was like if “We didn’t start the fire” was a day. 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 Claudia Sahm : That’s one of those days that I don’t think we ever thought we would live. Elise Stefanik : Already, March 11 seems like months ago. Claudia Sahm : I went into March 11 thinking maybe I’m overreacting. I came out of March 11 being like, “Oh, no—I was right.” It’s bad. I’m praying that there’s a day coming very soon where I’m totally wrong, because I have more and more pessimistic views about what’s happening. Gabriella Orr: There hasn’t really been a moment since that speech and in the few weeks that have passed where White House officials have felt like they’ve finally got a grip on things. Yamiche Alcindor: There was before this day and there was after this day. Doris Burke: I landed home on Thursday, started to feel really poorly on Saturday. I started thinking, “My God, my symptoms aren’t aligning with what we’re hearing most closely associated with the virus, but I’m not well and I’m getting worse.” I tested on Tuesday night, the 17th. They said when I left the hospital, “You’ll know in three to five days.” And I didn’t hear until eight days later. Basically, a physician from that hospital calls you with the test result and then tries to cultivate as much information as possible. They’re trying to track where did I get it? Who have I come into contact with? Then the next day, the Health Department of Pennsylvania also called. What were your symptoms? When did they start? When I had documented the number of places and modes of transportation and the size of the venues I had been in—they both chuckled. They were like, “Well, no chance we’ll trace your exposure.” And I said, “Yeah, no kidding.” Peter Tuchman : The following Tuesday night, I got sick. I got tested on Wednesday morning. I never came back to work after that. That was the week that the shit really went crazy with testing, and it took about five days to get my results. I was Covid-positive. By Friday, I started spiking temperatures. Over the next 10 or 12 days I got sicker and sicker every day. I lost sense of taste and smell. My skin hurt. I was black and blue in my body, as if I’d been in a boxing match with Mike Tyson. I’m on day 35 now. I started walking three days ago. Editor’s Note: The NBA, Oklahoma City Thunder, and Utah Jazz all declined to participate in the reporting of this article or did not respond to interview requests. After repeated requests to multiple officials, the White House initially agreed to participate but did not follow through. Nora McGreevy contributed research and reporting to this article. Sign up for our Coronavirus Update newsletter for the latest updates, and subscribe to support our journalism. 📩 The latest on tech, science, and more: Get our newsletters ! Premature babies and the lonely terror of a pandemic NICU How to remember a disaster without being shattered by it The raging evolutionary war between humans and Covid-19 The secret behind North Dakota’s speedy vaccine rollout We still don’t know how well vaccines stop transmission Read all of our coronavirus coverage here Contributing Editor Topics longreads Covid Spring COVID-19 coronavirus congress NBA Vauhini Vara Christopher Beam Amit Katwala Samanth Subramanian Steven Levy Virginia Heffernan Gideon Lichfield Lexi Pandell 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 "

"What Does It Mean If a Vaccine Is ‘Successful’? | WIRED"

"https://www.wired.com/story/what-does-it-mean-if-a-vaccine-is-successful"

"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 What Does It Mean If a Vaccine Is ‘Successful’? Photograph: Richard Drury/Getty Images Save this story Save Save this story Save When representatives from the drug company Pfizer say that they could know as soon as the end of October if their Covid-19 vaccine works, here’s what they mean: If their trial, involving perhaps as many as 44,000 people , pops just 32 of them with mild Covid-19 symptoms and a positive test—and if 26 of those people got a placebo instead of the vaccine—that, potentially, is it. According to the guidelines laid out by the Food and Drug Administration, that would be an “effective” vaccine: 50 percent efficacy with a statistical “confidence interval” that puts brackets around a range from 30 percent to 70 percent. At that point, per Pfizer’s protocol, the company could stop the trial. Technically, that vaccine would be successful. Now to be fair, nobody, least of all those selfsame Pfizer representatives, is explicitly claiming that will happen—or that if it does, Pfizer would take those numbers to the FDA and ask to start giving people shots. “The protocol only specifies that the study would stop in the case of futility, and does not outline a binding obligation to stop the study if efficacy is declared,” a Pfizer spokesperson told me by email. Translation: They have wiggle room to keep going. On the other hand, they could ask for an emergency use authorization, which the FDA and President Donald Trump seem to be angling for—and which could, for various ethical and practical reasons, then become a roadblock in front of all the other trials in progress. It’s hard to tell! Which is a problem. Now that several pharmaceutical companies have released detailed plans for how they’re testing their Covid-19 vaccine candidates, researchers are asking questions about these protocols. Even if anyone can reliably say whether a particular vaccine works—for various definitions of “works”—it’s less clear that the trials will be able to tell which one works better , and for whom. No one is yet testing vaccines head-to-head. The goal here hasn’t changed: To get one or more vaccines that protect lots of different kinds of people against Covid-19. At issue is how the many candidate vaccine trials are designed, what the trials will actually show, and how the vaccines compare to each other. Big vaccine trials all depend in part on defining “end points,” the signs of infection or illness that the researchers say they’re going to count. Basically, the setup is: You give tens of thousands of people the vaccine and a few thousand other people a placebo, and you see who gets to those predetermined end points. If more people who got the placebo do—by a mathematically predetermined proportion—you got yourself a vaccine. The tricky bit is, what really constitutes an end point ? Obviously a big one is “infection with the virus SARS-CoV-2.” But after that, reasonable minds could disagree. You could also choose “correlates of immunity,” like antibodies found in a blood test. Or you could use symptoms, as these trials do. That’s common practice. But does it matter if someone gets a little sick, with mild illness like a cough or muscle aches, versus a lot sick, with severe illness that requires a ventilator or an intensive care unit? Pfizer and the other companies with trials underway are using mild symptoms and a positive Covid-19 test as their primary end points, and severe illness as a secondary end point, something for later statistical analysis. But incidence of mild cases might not be the most useful thing to count. If you’re looking for vaccines meant to eventually reach billions of people, maybe you actually want to first ensure they beat back the most severe symptoms, not the mild ones. “What you’d like, in this very small number of events, going to the planetary population, is to have the most confidence you possibly can. That would be suppressing the worst events, sickness that requires a hospitalization and anything worse than that,” says Eric Topol, a professor of molecular medicine at the Scripps Research Institute who has been watchdogging the trial protocols. Mild, coldlike symptoms, he says, “are not very good signals of efficacy. And my understanding is there was tremendous internal debate about that when these protocols were being discussed, but I think they made a bad decision.” 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 the problem? Nominally, the trials are looking for what scientists call vaccine efficacy , or VE—calculated as “1 minus the relative risk of infection of someone who gets vaccinated versus someone who does not.” The end point is the difference between those groups. But the reason that trials need tens of thousands of people is that they’re trying to pick up subtle differences in the effectiveness of the medicine. Also, different people— kids versus the elderly , say—get sick differently. So the potency of the vaccine might matter too. If a vaccine isn’t a grand-slam success—and few are—tiny variations in how sick people get and how infectious they are to others will make a real difference across hundreds of millions of people. Technically the FDA has requested a vaccine with 50 percent efficacy, with a margin ranging from as low as 30 percent to as high as 70 percent. “Anything 30 to 50 percent is pretty darn low efficacy, but that’s just one measure,” Topol says. “Another level of efficacy is: What type of events is it suppressing? Are you suppressing important infections? That’s a measure of potency. We don’t know that blocking only mild ones is the same here. We just don’t know that.” Even weirder, the trials all use slightly different definitions for those mild symptoms, which means they’re tracking different end points. The vaccines from Pfizer and Moderna—both based on similar technologies that deliver the genetic material mRNA packaged in a sort of bubble of fat, both requiring two doses—will have subtly different criteria for success. So, for example, Pfizer defines its primary end point as a positive Covid-19 test and any one of these: fever, cough, shortness of breath, chills, muscle aches, loss of sense of taste or smell, sore throat, diarrhea, or vomiting. It also has a second definition it's working with based on CDC definitions that includes fatigue, headache, stuffy or runny nose, and nausea. Moderna says the primary end point, in addition to a positive test, is cough, shortness of breath, pneumonia, and any two of these—fever, chills, muscle aches, headache, sore throat, and loss of the sense of smell or taste. But the Janssen/Johnson & Johnson protocols invert all that, using severe symptoms like respiratory failure and hospitalization as primary end points, and mild ones as secondary—with lots of follow-up evaluations and frequent testing for the virus itself. 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 Now, maybe that’s not a huge problem. “They have approached the problem similarly with respect to the primary end point of disease of any severity,” says Natalie Dean, a biostatistician at the University of Florida and vaccine trial design expert. “The FDA would have accepted an infection end point and probably a severe-disease-only end point, but they’ve all landed at disease of any severity. There’s some details that vary on the particular definition of disease, but it’s not like a striking difference.” More striking, perhaps, is when the companies decide to count up those end points. Vaccine trials define in advance whether and under what conditions they’ll conduct “interim analyses,” when a data monitoring team—independent of the researchers—looks at the numbers. If, after running the stats, the data is either terrible or amazing, the data committee can call a halt to the trial. That’s called “futility”—it means there’s no point in continuing. But so does amazing, or “efficacy.” It works, goes the logic, so we can stop. But stopping early has a cost, both in terms of having rock-solid numbers to prove you’re right, and in an inability to see possible safety implications or side effects that would’ve only shown up later. Moderna and the other companies have only built in one or two interim analyses; Pfizer has four, and the company’s CEO has said they might have the data from the first one as soon as late October. That would be the one that could show efficacy with just a couple dozen “events,” if they’ve happened: 26 mildly symptomatic infections in the placebo group out of 32 in total. That’s it. “What if those 26 events are headaches and sore throats? Would that give you great confidence we have an effective vaccine? It sure wouldn’t give me confidence,” Topol says. It’d be statistically significant. But that’s not the only criterion to look at in a trial. “They could declare overwhelming efficacy at that time,” Dean says. “The question then is: If the trial declares efficacy after an early analysis, then do they stop the trial at that point?” That would have tremendous significance. That Pfizer spokesperson told me they might not. But it seems like they could. It wouldn’t even violate the multi-company pledge Pfizer and others signed to produce a safe and effective vaccine via ethical trials without political influence. (Senior FDA officials pledged much the same in an opinion piece in USA Today in mid September, though President Trump has threatened to ignore tougher standards for approval.) Technically, even those seemingly small event numbers would show overwhelming efficacy. Pfizer could go straight from there to a request for an emergency use authorization. If that goes through, they could start giving people shots. But the trial will have stopped so early that it might miss potential side effects or variability in how different demographic groups respond to the vaccine. “They can technically meet that definition the FDA has set: 50 percent efficacy and a 30 percent lower bound,” Dean says. “But the big risk I see in having relatively few events is that you could have very little information about other secondary end points or other things that are going to be important for decisionmaking.” 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 worst of all, nobody knows what effect an EUA will have on the other ongoing trials. In the strictest possible definition of medical ethics, having a vaccine that works means other labs and companies with other formulas might stop testing theirs, because technically those trials would pose unnecessary risks to the subjects. That probably isn’t true here—more than one Covid-19 vaccine will almost certainly be necessary, if for no other reason than the logistics of distributing hundreds of millions of doses. But still: What happens to the other trials? “My guess is that if somebody gets an EUA, nobody is stopping their trials. It doesn’t become unethical to continue,” says Elizabeth Halloran, a vaccine trial design expert at the Fred Hutchinson Cancer Research Center and another vaccine trial design expert. “But if at a point somebody has a licensed vaccine that went through Phase III and gets a licensure, then you do have an ethical issue.” An FDA spokesperson said that the agency plans to put out more guidance about what pharmaceutical companies will need to get an EUA, and potentially how it would affect other ongoing trials. Meanwhile, though, all of this could have perhaps been avoided if the federal government hadn’t authorized multiple simultaneous trials of multiple vaccines. The government jump-started these trials with billions of taxpayer dollars. Yet it made few demands on the design of the trials—and manifestly failed to set up a head-to-head, multiarm adaptive trial with a shared placebo group, which could’ve assessed not only safety and efficacy but also “non-inferiority,” which is to say, which one’s better. Since each trial defines slightly different end points, it’s that much more difficult (though, to be sure, not impossible) to compare the trials to each other. “It’s reasonable to argue that you would care about picking a vaccine that’s 2 percent more effective. Two percent is thousands of lives, so all things being equal, you’d rather have that one,” says Peter Bach, director of the Center for Health Policy and Outcomes and the Drug Pricing Lab at Memorial Sloan Kettering Cancer Center. “These things use very different platforms, very different technologies; in some sense the biological hypotheses underlying them are different. There’s a reasonable chance that they won’t all work the same.” 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 Europe, the World Health Organization is organizing just that kind of trial—the Solidarity trial , aiming to test multiple vaccines against Covid-19 and against each other. But it’s fair to note that while several companies are in Phase III trials of their vaccines, the Solidarity trial hasn’t even fully gotten off the ground yet. “By sharing a placebo arm, you can have fewer participants overall or fewer people receiving placebo, or you can facilitate a direct comparison,” Dean says. “But the other side of that argument is that this has gone really fast [in the US], and I do think we need to be realistic about the added time it takes to get all these companies on the same page.” That’s a true thing, but it also sucks. “It’s worth it to do these things. And the companies don’t want us to do it. They’d much prefer being oligopolists than to compete,” Bach says. Head-to-head tests would let the market compare their products, and the companies would have no way of spinning the results. (He pitched the idea in an op-ed in Stat. ) “They don’t want binary events that would cause their market to evaporate,” Bach says. “Here we have a situation where we have financed a lot of the development, there’s a lot of government IP, we’ve given advance marketing commitments—which are guarantees of revenue—and we’re paying for the distribution. We’ve run the table on reasons why the government should have an interest in managing and guiding the science.” Yet that only happened in one case—the government-run trial of the antiviral drug remdesivir. It didn’t happen with any other therapeutics, and hasn’t happened with vaccines. Instead, the regulatory agencies let the pharmaceutical companies define the terms of their own trials. “It makes me bonkers that we think we should let the companies decide on the study designs, because their incentives are off,” Bach says. “When we know definitively that X or Y are not what we want, and we want something slightly different, that’s where the government is supposed to step in and modify the market’s behavior.” To be clear, these are scientifically rigorous trials taken on their own terms; the people who work for these companies are good at their jobs, and nobody wants to see a world without a vaccine, or with one that doesn’t stop the disease or has untenable side effects. Those are two very real fail modes. But there’s a third one that isn’t getting addressed. It seems like one so-so vaccine could actually preclude a better one. Or maybe worse: Multiple vaccines that are protective against Covid-19 could get approved, but people might get one or the other almost capriciously. It could depend on factors as prosaic as which one their local pharmacy happened to get access to, or whatever was available at the terrifying dystopian distribution center, rather than which one was better, or perhaps better suited to a person like them. And the people who need the shot (all of us) might not even have the right data to know the difference. The vaccines will be a success— and a failure. 📩 Want the latest on tech, science, and more? Sign up for our newsletters ! If you've just had Covid, exercise might not be good for you Colds nearly vanished under lockdown. Now they’re coming back Covid-19 vaccines could end up with bias built right in What teaching online classes taught me about remote learning Hey students! Here's how to deal with school in a pandemic Read all of our coronavirus coverage here Senior Correspondent X Topics COVID-19 coronavirus pharmaceutical industry vaccines medicine Grace Browne Max G. Levy Dhruv Mehrotra Dell Cameron Matt Simon Amit Katwala Max G. Levy 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 "

"The Tricky Ethics of Knightscope's Crime-Fighting Robots | WIRED"

"https://www.wired.com/story/the-tricky-ethics-of-knightscopes-crime-fighting-robots"

"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 The Tricky Ethics of Knightscope's Crime-Fighting Robots Save this story Save Save this story Save In November, the San Francisco SPCA deployed a 5-foot-tall, 400-pound robot to patrol its campus. Not for muscle, mind you, but for surveillance. The SPCA, a large complex nestled in the northeast corner of the city's Mission neighborhood, has long dealt with vandalism, break-ins, and discarded needles in its surrounding parking lots. Fearing for the safety of its staff, the SPCA figured the robot could work as a deterrent, a sort of deputy for its human security team. The robot came from a Silicon Valley startup called Knightscope, whose growing family of security machines work as slower, more disciplinarian versions of self-driving cars. SPCA used their K5 robot, which is good for outdoor use. Its scaled-down cousin K3 is meant for the indoors, while the K1 is a stationary pillar that will soon monitor things like building entrances. And the K7, a four-wheeled robot meant for patrolling perimeters of airports and such, is going beta next year. The company is on a mission to take a bite out of crime by augmenting human security guards with machines. The path there, though, is fraught with ethical pitfalls. The K5, along with almost 50 other Knightscope robots across 13 states, sees its world by coating it with lasers, autonomously patrolling its domain while taking 360-degree video. In an on-site control room, a human security guard monitors this feed for anomalies. Knightscope says K5 can read 1,200 license plates a minute to, say, pick out cars that have been parked for an inordinate amount of time. If you get in the robot’s way, it says excuse me. In the event of an emergency, the security guard can speak through the robot to alert nearby humans. The SPCA's robot patrolled both its campus and the surrounding sidewalks while emitting a futuristic whine , working as a mobile camera to theoretically deter crime. None of these machines are equipped with tasers or flamethrowers or anything like that. “This is not for enforcement,” says William Santana Li, chairman and CEO of Knightscope. “It's for monitoring and giving an understanding of the situation for those humans to do their jobs much more effectively.” Again, the SPCA’s robot wasn’t meant to replace humans, but supplement them. “Very simply,” Li adds, “if I put a marked law enforcement vehicle in front of your home or your office, criminal behavior changes.” So does other behavior, it turns out. After the SPCA's Knightscope was set out on its route, homeless residents took it to task. A group of people setting up camp allegedly threw a tarp over the robot and knocked it over and smeared BBQ sauce on its sensors. 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 Now, by this point you probably don’t recoil when you see a security camera and throw rocks at it—for better or worse, we’re all under surveillance in public. But the K5 just feels different—and it elicits different reactions. In a shopping mall, the robot seems unassuming, even vaguely endearing. Kids run up and hug it. But in the outdoors, it's a roaming embodiment of surveillance, recording video of everything around it. Which is particularly unsettling to people who make the outdoors their home. “Keep in mind, this concept of privacy in a public area is a little bit odd,” says Li. “You have no expectation of privacy in a public area where all these machines are operating.” Still, a camera on a wall is one thing. A giant camera that roams the streets of San Francisco is another. “When you’re living outdoors, the lack of privacy is really dehumanizing after awhile, where the public’s eyes are always on you,” says Jennifer Friedenbach, executive director of San Francisco’s Coalition on Homelessness. “It’s really kind of a relief when nighttime comes, when you can just be without a lot of people around. And then there’s this robot cruising around recording you.” After the San Francisco Business Times published a piece on the SPCA’s foray into security robotics, public outcry grew that the organization was using the robot to roam the sidewalks around its facility to discourage homeless people from settling. The SF SPCA denies its intent was anti-homeless. “The SF SPCA was exploring the use of a robot to prevent additional burglaries at our facility and to deter other crimes that frequently occur on our campus—like car break-ins, harassment, vandalism, and graffiti—not to disrupt homeless people,” said the group’s president, Jennifer Scarlett, in a statement. Nevertheless, the group discontinued its pilot program with Knightscope last week. Deploying robots in a mall is fairly innocuous, but clearly in a more sensitive use case like this, the ethical conundrums of human-robot interaction got out of hand quick. More on Security Bots Robots Robbie Gonzalez Hack Bots Cade Metz Security Kim Zetter If you think the ethics of security robots are murky now, just you wait. Knightscope wants to keep humans in the loop with its robots, but it’s not hard to imagine a day when someone else gets the bright idea to give other security machines a lot more autonomy. Meaning, have AI-powered robots recognize faces and look for patterns in crimes. Patrol this area preferentially at this time of day, for instance, because this suspicious group of people tends to come around. Algorithms are already forming biases. In 2016, an investigation by ProPublica revealed that software used to determine criminal risk was biased against black defendants. Now imagine a security robot loaded with algorithms that profile people. It’s especially troubling considering the engineers developing artificial intelligences don’t necessarily know how the algorithms are learning. “There should be not only a human at the end of the loop, but a human at the beginning , when you're learning the data,” says computer scientist Michael Anderson of the Machine Ethics program. Really, what robot makers will need are ethicists working alongside engineers as they develop these kinds of systems. “Engineers aren't necessarily able to see the ramifications of what they're doing,” says ethicist Susan Anderson, also of Machine Ethics. "They're so focused on how it can do this, it can do that.” Could a robot at some point help an organization like SPCA? Yeah, maybe. These are early days of human-robot interaction, after all, and humans have as much to learn from the robots as the robots have to learn from us. Maybe there are ways to go about it without rolling over somebody’s toes. Staff Writer X Topics robotics ethics Grace Browne Dell Cameron Max G. Levy Dhruv Mehrotra Amit Katwala Matt Simon Max G. Levy 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 "

"Spot the Robot Dog Trots Into the Big, Bad World | WIRED"

"https://www.wired.com/story/spot-the-robot-dog-trots-into-the-big-bad-world"

"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 Spot the Robot Dog Trots Into the Big, Bad World Photograph: Harry Murphy/Getty Images Save this story Save Save this story Save This autumn, after years of dropping view-amassing videos of Spot the robot dog fending off stick-wielding humans and opening doors for its pals , Boston Dynamics finally announced that the machine was hitting the market—for a select few early adopters, at least. BD’s people would be the first to tell you that they don’t fully know what the hypnotically agile robot will be best at. Things like patrolling job sites , sure. But Spot is so different than robots that have come before it that company execs are, in part, relying on customers to demonstrate how the machine might actually be useful. After a few months on the job, Spot is beginning to show how it’ll fit in the workforce. BD’s researchers have kept close tabs on the 75 or so Spots now working at places like construction companies and mining outfits. (Oh, and one’s with MythBuster Adam Savage for the next year.) They’re seeing hints of a new kind of cooperation between humans and machines, and even machines and other machines. Starting today, you can even customize Spot to your liking—the software development kit is now publicly available on GitHub. The robot is not included, though. 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 an example of how Spot can help, says Michael Perry, VP of business development at BD, the mining industry now employs self-driving subterranean vehicles. But if something goes awry, like a sensor malfunctions or a truck gets hung up on a rock, the operation has to shut down so a human worker can safely troubleshoot the problem. But with Spot, early adopters found, the human operator can stay at a safe distance, seeing through Spot’s eyes. “It's kind of an interesting cognitive leap to start thinking about robots mending and minding other robots,” says Perry. “It's a little far-fetched and it'll be interesting to see how successful these customers are with that application, but it was certainly something that I was really surprised by.” It’s the old robotics mantra dirty, dangerous, and dull in action: Advanced robots like Spot can tackle jobs humans can’t. (Or shouldn’t , really, unless you enjoy venturing into mines to get autonomous vehicles out of subterranean trouble.) But there remains much that Spot can’t do. BD, for instance, hasn’t yet deployed the arm that allows the robot to open doors. That’ll come later this year, so for the time being Spot can’t fix a problem it might find with an autonomous mining truck. And the company has to confront the very magic that made it famous. A running criticism is that by viralizing slick videos of their robots pulling off amazing feats (a humanoid robot doing backflips , anyone?), they’re setting the public’s expectations too high. It takes a lot of work to get those tricks right, and what you’re not seeing are the many times the robots fail. So BD’s researchers and execs have had to sit down with each prospective early adopter and talk through what their needs are, and what the robot can and can’t do for them—or whether they even need such an advanced platform in the first place. “We really try to work with customers and our own internal expectations to make sure that we're not tackling a sensing task that, if you just installed a bunch of Nest cameras, you'd have the same result,” says Perry. At the same time, BD is trying to make Spot a flexible platform, so adopters can tailor the robot to fit their needs—think of it more like Android than iOS. That’s where the newly downloadable SDK comes in, allowing operators to program new behaviors. For example, if Spot is working a construction site, a project manager might want it to recognize and photograph certain objects. The SDK allows them to connect Spot’s cameras to computer vision models running either onboard the robot or in the cloud. Once they set Spot’s path by joysticking it around so it can remember the route, then they can let Spot autonomously roam the site, doing the work of a human who’d have to wander around doing the same. What's tricky is figuring out how customizable to make such an advanced machine. Higher-level customization—getting Spot to recognize certain objects or walk certain routes—is one thing. But BD isn’t particularly interested in letting clients toy with how the robot’s joints work in concert to produce that famous agility. “We're assuming that our customers believe that we've got that problem solved,” says Perry. “It's not how it gets from point A to B. It's that it gets from point A to B while doing something that I care about.” By making the SDK public, BD is opening up a platform to coders and roboticists of diverse specialties. “Developers will still need to become part of the early adopter program to lease the robot to execute their code,” adds Perry, “but all interested parties will now be able to view the SDK and existing early adopters can open source their own code.” BD is also announcing today that it’ll be putting on a developer conference in May in Boston. 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 as those machines grow more capable, BD itself is transitioning: Longtime boss Marc Raibert is moving from CEO to chairman, with Robert Playter, the company’s COO, taking his place. “This is partly a transition away from us being a research-only shop to a company that's fielding commercial products,” says Perry. “So [Raibert] is still setting higher-level vision for pushing forward the envelope on robotics development at Boston Dynamics.” But with increasingly advanced robots like Spot come increasingly sticky PR problems. From politicians and economists we're getting dire warnings about how the machines will replace humans in the workforce. It’s true that as robots have gotten better at sensing the world, they’ve been freed from factory floors, where they worked in isolation from humans. As they get better at navigating our world—be it as self-driving trucks or delivery robots —the concern is they’ll muscle people out of jobs. Nevertheless, the outside world is awful for robots. Humanoid robots have nowhere near our stability to stay upright, never mind getting back up. Wheels may give them some traction, but then are confounded by stairs. The world outside an orderly factory is unpredictable and treacherous, even for as nimble a machine as Spot. Humans still need to hold Spot’s paw—it can only autonomously navigate an environment after you show it around. It still can’t manipulate objects. And you have to swap out its battery if you want continuous operation. It’s worth noting that as robots escape the factory floor and enter the real world, they’re typically taking over certain parts of jobs—Knightscope’s security robots can patrol the perimeter of a building, but a human security guard still has to supervise it (especially if someone gets angry and assaults it ). And that’s when its operators aren’t busy fishing it out of water fountains. Which is all to say that Spot is delicately exploring a new kind of automation, in which sensitive machines work closely with humans, instead of replacing them outright. Where exactly Spot trots from here is anyone’s guess—including BD’s. But with these first few baby steps, the internet’s most famous robot dog finally gets to work. Chris Evans goes to Washington What Atlanta can teach tech about cultivating black talent The display of the future might be in your contact lens Scientists fight back against toxic “forever” chemicals All the ways Facebook tracks you— and how to limit it 👁 The secret history of facial recognition. Plus, 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 Staff Writer X Topics boston dynamics robotics Tammy Rabideau Matt Simon Jim Robbins Matt Simon Rob Reddick Tristan Kennedy Sushmita Pathak Amit Katwala 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 Derechos Are So Devilishly Difficult to Predict | WIRED"

"https://www.wired.com/story/why-derechos-are-so-devilishly-difficult-to-predict"

"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 Megan Molteni Science Why Derechos Are So Devilishly Difficult to Predict Derechos are often referred to as “inland hurricanes” thanks to their whipping, destructive winds, and sideways pelting rain. But they’re completely distinct weather phenomena. Photograph: Daniel Acker/Getty Images Save this story Save Save this story Save At 8:30 am on Monday, Mark Licht was sitting in his home outside of Ames, Iowa, on a conference call with other agronomists and meteorologists from around the state. Iowa had been having a dry spell, the western half of the state stricken with severe drought. What farmers needed was a big storm, thought Licht, a cropping systems specialist at Iowa State University. The meteorologists on the call told him that one was just getting started in South Dakota and Nebraska. But, they said, it didn’t look like it would have the energy to make it into Iowa. Everyone crossed their fingers and hung up. Around 10:15 am, Licht got an email from the group; the storm looked like it might be sticking together after all. Less than an hour later, he heard storm warning sirens blaring from the closest town. He went outside. It was sunny, barely a cloud in the sky. The air was still and the humidity suffocating. “That’s weird,” he thought. But when he checked radar he saw a huge mass barreling in his direction at about 60 mph. He got his family into the basement, and 10 minutes later the storm was on top of them. Rain so heavy you couldn’t see more than a few feet ahead. Winds so fierce they could shear a tree in half. When Licht and his family emerged about 45 minutes later, the steel shed where their cars were parked had completely collapsed. “We were smack in the middle of one of the more devastated storm paths,” says Licht. “It’s going to be a long process to deal with the damage, but we’re lucky it wasn’t worse.” Iowa knows summer storms. But the one that tore across the Midwest on Monday, traveling 770 miles in 14 hours, leveling 10 million acres of crops, twisting grain silos , and knocking out power for hundreds of thousands of people for days , was a rare type of storm known as a derecho. The term means “straight ahead” in Spanish, and was coined in the late 1800s by a Danish physics professor at the University of Iowa, who used it to describe the “straight blow of the prairies,” in contrast to the circular winds associated with tornadoes. Today, for a derecho to meet the National Oceanic and Atmospheric Association’s definition, it must travel at least 240 miles and move at speeds of at least 58 mph. This week’s derecho hit top speeds around 112 mph in Cedar Rapids, Iowa, about two hours due east of Licht’s 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 “Derechos are these long-lived, fast-moving walls of super-thunderstorms,” says Paul Huttner, a meteorologist who watches the weather for Minnesota Public Radio. They’re regular but not common events, occurring in the Midwest one or two times a year. Derechos come in two varieties: linear and progressive. Monday’s storm was a progressive derecho, which moves faster, is more compact, and packs more of a punch than its more spread-out sibling. And this one, says Huttner, “was a real doozy.” X content This content can also be viewed on the site it originates from. Derechos are often referred to as “ inland hurricanes ,” because the experience on the ground—whipping, destructive winds; sideways pelting rain—is similar to being inside a Category 1 hurricane. But they’re completely distinct weather phenomena. Derechos are fueled by different factors and behave more like a stampede of wildebeests than a bloat of hippopotamuses. And unlike the path and severity of hurricanes, which scientists have gotten good at forecasting days or even weeks in advance, predicting where and when a derecho will form remains one of the most challenging tasks facing meteorologists. The difficulty comes down to two things: patchy data and the complexity of the storm itself. Derechos can arise at random, almost out of nowhere, says Victor Gensini, a meteorology professor at Northern Illinois University. On many days during the year, the ingredients are all present for a derecho—but they’re missing something to start the storm. “In other words,” he says, “you need a trigger.” 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 could be a cool pool of air left by a previous storm, high terrain, or a sudden sea breeze. In the summer months, these triggers can be especially difficult for meteorologists to detect. That’s in part because the fast-flowing global air current known as the jet stream slows down during that time, as the temperature contrast between the poles and the equator shrinks. The result is that instead of distinct and regular waves of warm and cold fronts being forced eastward across the US, the atmosphere is more stagnant. And small, random disturbances can more easily kick up warm air from the surface. If there’s enough water vapor in the air to buoy the updraft, it will keep rising and accelerating, triggering a thunderstorm. Sometimes these disturbances come from other storms that have recently passed through—the cold air they leave behind can be the seeds of the next storm. “That’s why the weather changes so rapidly in the summer without warning,” says Gensini. These storms actually modify the environment around them, often determining the next day’s weather. And sometimes, it’s the lack of a storm that determines the next day’s weather. That’s what happened in the run-up to this week’s derecho. On Sunday night, Patrick Marsh, the science support chief at the National Weather Service Storm Prediction Center in Norman, Oklahoma, was working a forecasting shift alongside four other colleagues. (In pre-pandemic times they would have been in a mission control room together; now they sit in separate rooms rigged up with video monitors and talk to each other over Google Hangouts.) Their models were telling them that a decent-sized thunderstorm was going to develop across the Dakotas and move into Minnesota. They expected it to take the warm moisture from the surface and swap it with cool air from higher up in the atmosphere. This flip-flopping takes some of the water vapor out of the atmosphere, stabilizing it. “But that’s not what happened,” says Marsh. The storms on Sunday never materialized. So the atmosphere stayed volatile, a huge amount of energy just primed for the next disturbance to tap into. Watching this potential continue to build overnight, the Storm Prediction Center upgraded the risk of severe weather for some parts of Iowa from marginal to enhanced. Early that morning, a new storm system began to form. But it wasn’t until a few hours before the winds in Iowa began gusting to 90 mph that Marsh realized they were about to have a derecho on their 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 “We see these kinds of environments happen multiple times a year, but something almost always goes wrong that prevents a storm from evolving into a high-end situation,” he says. By mid-morning, his team wasn’t seeing any of those typical failure modes. “That’s when we knew this was going to be a problem.” X content This content can also be viewed on the site it originates from. Though the derecho eventually grew large enough for satellites to chart its destructive path, the processes that drove its initial evolution were happening at a scale too small for the National Weather Service’s monitoring network to pick up. The NWS has more than 1,000 surface locations from which it collects information. Data from high up in the atmosphere is far patchier. The only way to get that intel is with weather balloons, about 200 of which are launched daily around the US—half at 8:00 am Eastern, and the other half 12 hours later. “All we have is these snapshots two times a day at 100 points for the entire country, which makes it really hard to get good wind data in the upper levels of the atmosphere,” says Andrew Mercer, a meteorologist at Mississippi State who studies derecho formation. “What our models really need is much more frequent sampling, especially in the hours leading up to the event.” 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 because one of the key ingredients for derecho development is strong vertical wind shear. Imagine a flagpole extending from the ground 10 miles into the air, with flags placed every few hundred feet. Under ideal conditions for derecho formation, those flags at every level would be blowing at different speeds. That’s vertical wind shear. It’s not the only indication that a derecho is coming—the exact atmospheric alchemy that leads to one is still not totally understood—but it’s an important input for weather models. (Here’s another X factor: Scientists don’t really know how increased moisture impacts derecho development—sometimes water-enhanced downdrafts fuel them, sometimes they short-circuit. Why? Who knows?!) X content This content can also be viewed on the site it originates from. Forecasters can request additional balloon launches to try to get that wind shear information. The National Weather Service did that on Monday morning, says Marsh. And the picture it returned—an incredibly unstable atmosphere conducive for strong winds making it down to the surface—told Marsh a derecho was imminent. “It ruled out another failure mode and told us this thing is not going to go away,” 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 Improving derecho prediction then hinges on more frequent data collection from the upper reaches of the atmosphere. But it’s not exactly practical to send massive fleets of instrument-laden balloons skywards every hour. (And would be a huge headache for the commercial flight industry.) So, the National Oceanic and Atmospheric Administration has recently begun experimenting with autonomous drones to make these critical measurements. Scientists like Mercer think the problem can’t be solved just by putting more stuff in the sky. His lab has been collaborating with the National Weather Service to build an entirely different kind of prediction model. Rather than the decades-old forecasting workhorse models based on math and statistics, these employ machine learning , running a large number of high-resolution simulations, and teaching the system to identify and predict different characteristics of a storm. Will it be primarily wind-dominant or hail-dominant? Will it be tornadic or non-tornadic? The research is still in the early stages, and likely years away from being operational. But the idea is to let the machines determine the processes that influence whether a storm dies out or goes derecho, and to pinpoint at what point in time those processes commit a weather system to form one kind of storm versus another That could theoretically help improve some of the rather crude representations of these processes currently used by numerical models. Mercer recognizes that these types of models will also be hampered by scarce data from the skies. “There are always going to be limitations if we don’t have the upper wind data,” he says. But even with better methods of forecasting, there will never be a lack of information for scientists to measure. There’s always another storm coming. San Francisco was uniquely prepared for Covid-19 How courthouse break-ins landed two white hat hackers in jail Tips to make your video calls look and sound better How to spot—and avoid— dark patterns on the web The fantasy and the cyberpunk futurism of Singapore 🎙️ Listen to Get WIRED , our new podcast about how the future is realized. Catch the latest episodes and subscribe to the 📩 newsletter to keep up with all our shows ✨ Optimize your home life with our Gear team’s best picks, from robot vacuums to affordable mattresses to smart speakers X Topics extreme weather atmosphere climate change weather climate Matt Simon Matt Simon Ramin Skibba 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 Hollywood Writers AI Deal Sure Puts a Lot of Trust in Studios to Do the Right Thing | WIRED"

"https://www.wired.com/story/writers-strike-hollywood-ai-protections"

"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 Alex Winter Ideas The Hollywood Writers AI Deal Sure Puts a Lot of Trust in Studios to Do the Right Thing Photograph: Allen J. Schaben/Los Angeles Times/Getty Images Save this story Save Save this story Save I've been in the entertainment industry since I was nine. I joined the Screen Actors Guild (SAG) when I was 11 in 1977, the Writers Guild of America (WGA) when I was 22, and the Directors Guild of America (DGA) the following year. I got my start as a child actor on Broadway, studied film at NYU, then went on to act in movies like The Lost Boys and the Bill & Ted franchise while writing and directing my own narrative work. I've lived through several labor crises and strikes, but none like our current work shutdown, which began last spring when all three unions’ contracts were simultaneously due for renegotiation and the Alliance of Motion Picture and Television Producers (AMPTP) refused their terms. The unifying stress point for labor is the devaluing of the worker, which reached a boiling point with the rapid advancement of highly sophisticated and ubiquitous machine learning tools. Actors have been replaced by AI replications of their likenesses, or their voices have been stolen outright. Writers have seen their work plagiarized by ChatGPT, directors' styles have been scraped and replicated by MidJourney, and all areas of crew are ripe for exploitation by studios and Big Tech. All of this laid the groundwork for issues pertaining to AI to become a major flashpoint in this year’s strikes. Last summer, the DGA reached an agreement with the AMPTP, and on Tuesday the WGA struck its own important deal. Both include terms the unions hope will meaningfully protect their labor from being exploited by machine-learning technology. But these deals, while a determined start, seem unlikely to offer expansive enough protections for artists given how much studios have invested in this technology already. The DGA's contract insists that AI is not a person and can’t replace duties performed by members. The WGA's language, while more detailed, is fundamentally similar, stating that “AI can't write or rewrite literary material, and AI-generated material will not be considered source material” and demanding that studios “must disclose to the writer if any materials given to the writer have been generated by AI or incorporate AI-generated material.” Their contract also adds that the union "reserves the right to assert that exploitation of writers' material to train AI is prohibited." But studios are already busy developing myriad uses for machine-learning tools that are both creative and administrative. Will they halt that development, knowing that their own copyrighted product is in jeopardy from machine-learning tools they don't control and that Big Tech monopolies, all of which could eat the film and TV industry whole, will not halt their AI development? Can the government get Big Tech to rein it in when those companies know that China and other global entities will continue advancing these technologies? All of which leads to the question of proof. Alex Winter is an actor and filmmaker. He starred in the Bill & Ted franchise and his narrative features include the cult classic Freaked and the critically acclaimed Fever. His current feature documentary, The YouTube Effect , premiered at Tribeca and is now available on digital. It's hard to imagine that the studios will tell artists the truth when being asked to dismantle their AI initiatives, and attribution is all but impossible to prove with machine-learning outputs. Likewise, it's difficult to see how to prevent these tools from learning on whatever data the studios want. It's already standard practice for corporations to act first and beg forgiveness later, and one should assume they will continue to scrape and ingest all the data they can access, which is all the data. The studios will grant some protections for highly regarded top earners. But these artists are predominantly white and male, a fraction of the union membership. There will be little to no protection for women, people of color, LGBTQIA+, and other marginalized groups, as in all areas of the labor force. I don't mean to begrudge the work of the DGA and WGA in crafting terms that may not adequately represent the scope of the technology. But we can go further—and SAG has the opportunity to do so in its ongoing negotiations. SAG is still very much on strike, with plans to meet with the AMPTP next on Monday. In their meeting, I hope they can raise the bar another notch with even more specific and protective language. It would be good to see terminology that accepts that AI will be used by the studios, regardless of any terms thrown at them. This agreement should also reflect an understanding that studios are as threatened by the voracious appetites of Big Tech as the artists, that the unions and the AMPTP are sitting on opposite sides of the same life raft. To that end, contractual language that recognizes mutual needs will serve everyone's interest, with agreements between AI users and those impacted by its use on all sides of our industry. It would also be helpful to see language that addresses how AI’s inherent biases, which reflect society’s inherent biases, could be an issue. We must all make a pact to use these technologies with those realities and concerns in mind. Mostly, I hope everyone involved takes the time to learn how these technologies work, what they can and cannot do , and gets involved in an industrial revolution that, like anything created by humans, can provide tremendous benefit as well as enormous harm. The term Luddite is often used incorrectly to describe an exhausted and embittered populace that wants technology to go away. But the actual Luddites were highly engaged with technology and skilled at using it in their work in the textile industry. They weren't an anti-tech movement but a pro-labor movement, fighting to prevent the exploitation and devaluation of their work by rapacious company overlords. If you want to know how to fix the problems we face from AI and other technology, become genuinely and deeply involved. Become a Luddite. WIRED Opinion publishes articles by outside contributors representing a wide range of viewpoints. Read more opinions here. Submit an op-ed at [email 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 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 Topics hollywood Film Movies artificial intelligence Nika Simovich Fisher 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 "

"Why Hollywood Really Fears Generative AI | WIRED"

"https://www.wired.com/story/hollywood-actors-artificial-intelligence-performance"

"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 Why Hollywood Really Fears Generative AI ILLUSTRATION: WIRED STAFF; GETTY IMAGES Save this story Save Save this story Save The future of Hollywood looks a lot like Deepfake Ryan Reynolds selling you a Tesla. In a video , since removed but widely shared on Twitter , the actor is bespectacled in thick black frames, his mouth mouthing independently from his face, hawking electric vehicles: “How much do you think it would cost to own a car that’s this fucking awesome?” Artificial Intelligence Will Bedingfield Movies Amos Barshad Yippee Ki-Yay Will Bedingfield On the verisimilitude scale, the video, which originally circulated last month, registered as blatantly unreal. Then its creator, financial advice YouTuber Kevin Paffrath, revealed he had made it as a ploy to attract the gaze of Elon Musk. (Which it did: the Tesla CEO replied to Paffrath’s tweet with a “nice.”) Elsewhere on Twitter, people beseeched Reynolds to sue. Instead, his production company responded with a similarly janky video in which a gray-looking Musk endorsed gin made by Aviation, a company Reynolds co-owns. That video has also since been deleted. “Finance guy sucks up to Musk on Twitter” is far from earth-shattering news, but the exchange is indicative of a much bigger problem: AI is making it possible for anyone to deepfake famous faces into whatever video they like. And actors, in turn, are becoming increasingly aware of the potential of AI to encroach on their work. With the Writers Guild of America already on strike, in part because of a similar threat , upcoming negotiations between the actors’ union and studios will likely reference images like Fake Bruce Willis and Fake Ryan Reynolds as the latest steps toward a future dominated by AI. The hype around the technology means it will be a focus of the talks, especially given that contracts are negotiated just once every three years, explains Duncan Crabtree-Ireland, executive director and chief negotiator for the Screen Actors Guild—American Federation of Television and Radio Artists (SAG-AFTRA). “Considering how far [AI has] advanced in the last 18 months, it’s hard even to imagine where it’ll be in three years,” he says. In a message asking its members to authorize a strike, the guild noted that it was seeking a contract that would protect members from losing income due to “ unregulated use of generative AI. ” The deadline is Monday, June 5; on June 7, SAG-AFTRA begins negotiations with the Alliance of Motion Picture and Television Producers (AMPTP), which represents the studios. If actors go on strike, it would be the first time since 2000. SAG has been concerned about machine learning tools since the days of pixelated sports video games. Back then, the guild worried about how easy it was for game studios to insert pro athletes into Madden games. Now, Hollywood studios are de-aging Harrison Ford and recreating the voices of the dead. 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 Given this, it’s not hard to imagine a future in which a wide-eyed actor signs up for one season of a vampire TV show, and then two seasons later their AI replacement busts out of a coffin. Meanwhile, they receive no additional compensation, even if the AI-generated character was based on their likeness and performance. “The nature of the impact on performers is unique, especially with generative AI tools that can be used to recreate a performer image, likeness, or voice persona, or to do things that they didn’t originally contemplate ever doing,” says Crabtree-Ireland. “That’s a concern.” Actors, like all Americans, are protected against commercial appropriation of their identity by the right of publicity —also known as name, image, and likeness rights. SAG wants to buttress these protections and stomp out exploitative terms like the vampire example by adding “informed consent” into future contracts: Certain kinds of AI use must be disclosed and compensated, the union argues. But writers cannot lean on publicity rights in the same way. If they own the rights, they can seek recourse or compensation if their work is scraped by large language models, or LLMs, but only if the resulting work is deemed a reproduction or derivative of their script. “If the AI has learned from hundreds of scripts or more, this is not very likely,” says Daniel Gervais, a professor of intellectual property and AI law at Vanderbilt University. And it’s this scraping, applied to performers, that concerns talent reps. Entertainment lawyer Leigh Brecheen says she’s most worried about her clients’ valuable characteristics being extracted in a way that isn’t easily identifiable. Imagine a producer conjuring a digital performance with the piercing intensity of Denzel Washington while entirely skirting his wages. “Most negotiated on-camera performer deals will contain restrictions against the use of name, likeness, performance in any work other than the one for which they are being hired,” Brecheen says. “I don’t want the studio to be able to use the performance to train AI either.” This is why, as Crabtree-Ireland explains, it is crucial to reframe AI works as an amalgam of countless humans. But will people care if what they’re watching was made by an AI trained on human scripts and performances? When the day comes that ChatGPT and other LLMs can produce filmable scenes based on simple prompts, unprotected writers rooms for police procedurals or sitcoms would likely shrink. Voice actors, particularly those not already famous for on-camera performances, are also in real danger. “Voice cloning is essentially now a solved problem,” says Hany Farid, a professor at the University of California, Berkeley who specializes in analyzing deepfakes. 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 Short term, most AI-generated actors may come off like Fake Ryan Reynolds: ghoulishly unlikeable. It seems more likely that people will accept audiobooks made by AI or a digitally rendered Darth Vader voice than a movie resting on the ripped shoulders of an AI-sculpted GigaChad-esque action hero. Long term, though, if AI replicants escape the uncanny valley, audiences of the future may not care whether the actor in front of them is human. “It’s complicated,” says Matthew Sag, a professor of law and artificial intelligence at Emory University. “The job of writing can be encroached on in a marginal or progressive way. Performers are likely to be replaced in an all-or-nothing way.” As the actors’ union and Hollywood studios head into talks next week, the key concern will be economic fairness: The union states that it has become increasingly difficult for guild members to “ maintain a middle-class lifestyle. ” There is a modern disconnect between a film or TV show’s success and residual compensation, unions argue, as well as longer gaps between increasingly shorter seasons, which means less time spent working. In this context, AI could be Hollywood’s next gambit to produce more content with fewer humans. Like the AI-generated Reynolds, the whole thing would be banal if it wasn’t so critical. As such, union strikes remain a possibility. “They’ve got a 2023 business model for streaming with a 1970 business model for paying performers and writers and other creatives in the industry,” says Crabtree-Ireland. “That is not OK.” 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 hollywood Movies TV artificial intelligence Angela Watercutter Alex Winter Angela Watercutter Kate Knibbs Angela Watercutter Amanda Hoover 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 "

"Why Robots Should Shake the Bejeezus Out of Cherry Trees | WIRED"

"https://www.wired.com/story/why-robots-should-shake-the-bejeezus-out-of-cherry-trees"

"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 Why Robots Should Shake the Bejeezus Out of Cherry Trees You can’t have flawless cherries if you use a giant machine to shake a tree trunk willy-nilly. You've got to get algorithmic. Vesna Jovanovic/Getty Images Save this story Save Save this story Save I don’t think sci-fi saw this coming. For so long, futuristic books and films have promised us robots like C-3PO that translate alien languages and assist us in hijinks. Or ones like Rosie that clean our houses. Or, on the other end of the spectrum, robots that level our houses and destroy humanity. Looking at you, Arnold. The reality of modern robotics couldn’t be more different. These days, it’s more about developing robots that ... shake the bejeezus out of cherry trees. Researchers at Washington State University have developed algorithms that scan a tree for individual branches, then determine what bit of each branch to grasp and shake to extract the most cherries— up to nearly 90 percent of them. Sure, that’s not as dramatic as the machine-driven apocalypse. But at least it gives us an intriguing vision of a robotics-fueled agriculture industry. If the idea of a tree-shaking robot seems a bit oddball to you, know that you’re the reason it may soon exist. Americans don’t just want a lot of produce; they want a lot of flawless produce, free of dings and bruises and discoloration. And you can’t have flawless cherries if you’re using a giant machine to shake a tree trunk willy-nilly, flinging fruit all over the place. (Though that method works fine with hardier fare like almonds. ) So this algorithm is a little more genteel in its approach—starting by pinpointing the branches. The researchers were working with a special variety of cherry tree that grows "upright fruiting offshoots" (yes, known in the industry as UFOs). A more traditional bushy tree may hide fruit in its core, but this kind has a trunk that comes out of the ground and bends almost horizontally, out of which branches grow upright. It looks a bit like a menorah, really. This kind of cherry tree may be optimally arranged for picking by human hand, but it’s a challenge for an algorithm. “In a lot of different situations, the branches were hidden by berries or leaves,” says Manoj Karkee , an agricultural roboticist at Washington State University. “We used some mathematical modeling to estimate their location based on the cluster of fruit, as well as some visible sections of the branches.” So, the algorithm’s got sight of the obscured branch. Next is figuring out where to grasp and shake. Rule number one, of course: Avoid any clusters of fruit. “What we've found is that if we start shaking a tree at about one third of the height, we'd be able to remove about 70 to 80 percent of cherries,” says Karkee. “Then for the remaining cherries, we go to about two thirds of the height and shake it again.” Do this with all six or seven upright branches and a robot might be able to extract almost 90 percent of the fruit. (So a small crew would still need to trail the robot to pluck the remaining cherries, at least until the researchers improved the machine's efficiency.) More Farming Bots AI Agriculture Matt Simon Robots Matt Simon agriculture Matt Simon Might. The robot to do the actual work doesn’t exist yet. But what Karkee envisions is a machine with six, maybe eight arms that rolls through the orchard grabbing branches and giving them a good shake. Specifically, each shake buzzing at 18 hertz for five seconds, is what he and his colleagues found works best. Actually developing a robot that works outdoors, though, is no small task. “You're potentially dealing with moisture, with driving on rugged ground,” says Jon Binney, co-founder & CTO of Iron Ox, which has developed an automated indoor farming system. “All solvable mechanical problems, but non-trivial.” Problems that are important to solve soon, as agricultural employment continues to dwindle in the United States. Between 2002 and 2014, American farms lost nearly 150,000 laborers , or 20 percent of the workforce. People just aren't flocking to the jobs. So the future of agriculture will be increasingly robotic. One startup, for instance, has developed a robot that spots apples and picks them with a suction tube. And a machine called the LettuceBot rolls through fields eyeballing weeds and automatically spraying them. “What you’re going to see is people trying a lot of very specific things outdoors, most of which aren’t going to end up being cost effective or reliable enough, but some of which work,” says Binney. Which is not to say farmers can’t engineer outdoor farming to introduce some of the order you get with indoor farming. For instance, farmers in California plant a special kind of lettuce that grows like a bulb, which makes it easier for a fancy machine to cut the base with a knife made of water. It’s easy to imagine, then, that humans will create all manner of new varieties of fruits and vegetables—maybe even a differently-branching cherry tree—to better get along with robot harvesters. No matter how, if humanity wants to feed its ballooning population, it must lean heavily on the machines. So stay out of our way, Arnold. 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 Staff Writer X Topics agriculture robotics Max G. Levy Max G. Levy Matt Simon Dell Cameron Grace Browne Dhruv Mehrotra Amit Katwala 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 "

"What Is a Robot? | WIRED"

"https://www.wired.com/story/what-is-a-robot"

"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 What Is a Robot? Save this story Save Save this story Save Editor’s note: This is the first entry in a new video series, HardWIRED: Welcome to the Robotic Future , in which we explore the many fascinating machines that are transforming society. And we can’t do that without first defining what a robot even is. When you hear the word “ robot ,” the first thing that probably comes to mind is a silvery humanoid, à la The Day the Earth Stood Still or C-3PO (more golden, I guess, but still metallic). But there’s also the Roomba , and autonomous drones , and technically also self-driving cars. A robot can be a lot of things these days―and this is just the beginning of their proliferation. With so many different kinds of robots, how do you define what one is? It's a physical thing―engineers agree on that, at least. But ask three different roboticists to define a robot and you’ll get three different answers. This isn't a trivial semantic conundrum: Thinking about what a robot really is has implications for how humanity deals with the unfolding robo-revolution. I’d like you to think about two drones. One you have to pilot yourself, and the other is autonomous, taking off, navigating obstacles, and landing all on its own. Are these both robots? Nope. “I would say that a robot is a physically embodied artificially intelligent agent that can take actions that have effects on the physical world,” says roboticist Anca Dragan of UC Berkeley. According to that definition, a robot has to make decisions that in turn make it useful―that is, avoiding things like running itself into trees. So your dumb, cheapo RC quadcopter is no more a robot than an RC car. An autonomous drone, however, is a thinking agent that senses and interacts with its world. It’s a robot. Intelligence, then, is a core component of what makes a robot a robot and not a wind-up toy. Kate Darling , a roboticist at the MIT Media Lab, agrees. “My definition of a robot, given that there is no very good universal definition, would probably be a physical machine that's usually programmable by a computer that can execute tasks autonomously or automatically by itself,” she says. “What a lot of people tend to follow is this sense, think, act paradigm." An RC drone can act, but only because you order it to. It can’t sense its environment or think about its next action. An autonomous drone, however, can do all three. It’s a physical embodiment of an artificial intelligence. 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 how intelligent does a machine have to be to qualify as a robot, though? Lots of systems take in information from the outside world, process it, and then output an action—take the autopilot software that flies commercial planes. Hanumant Singh , a roboticist at Northeastern University, says a robot is "a system that exhibits 'complex' behavior and includes sensing and actuation.” He gives that definition to his students, then asks them to consider whether a Boeing 747 fits the bill. "It is automated, it is complex, it has sensing, it has actuation," he says. "The students argue that it is not a robot because humans operate it a lot of the time, even though it has an autopilot." Also confusing are swallowable, magnetic " origami bots " that automatically unfold when they hit the acid of the stomach—reacting to their environment like an actually intelligent bot would. But then a human operator has to use magnets to steer them around the digestive system to pick up things that shouldn't be there, like swallowed batteries. Not so much a bot. If a machine is truly autonomous, there's a good chance it's a robot—but there are different degrees of autonomous intelligence. It's easy enough to program a machine to respond to a single environmental input with a single output. But as machine learning algorithms improve, robots will respond to their environments in ways that humans didn't explicitly teach them to. And that's the kind of intelligence that will get robots driving us around, helping the elderly, and keeping us company. “I'd say, yes, a robot is a physically embodied artificial intelligent agent," says Dragan, "but an artificially intelligent agent to me is an agent that acts to maximize a person's utility.” Meaning, new thinkier robots are more sensitive to the user's needs. To demonstrate, in her lab Dragan shows me a robotic arm her team has programmed. Grasping a mug, the arm sweeps across a table. But Dragan doesn’t want it sweeping so high, so she grabs the arm and forces it closer to the surface. But she hasn’t programmed the robot to sweep this low, so it returns to its previous altitude. Its intelligence is limited to the simple rules it's been given. 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 second time around, though, the arm reacts differently to Dragan’s correction. She forces it to a lower altitude and it recognizes her new demand, continuing the rest of its sweep at that level. It’s a responsive brand of robot that we’ll be seeing more of in this world. Think robots that are not only sensitive to our needs, but anticipate them. More and more, we won't need to intervene to correct robots' behavior, but will interact with robots that learn to adapt to our whims. This nuance is important, because "robot" is a powerful word. It is at once something that makes people uncomfortable ( killer robots , job-stealing robots, etc.) and that makes them feel nice (Kuri the extremely endearing companion robot ). “The word robot generates a lot of attention and fascination and sometimes fear,” says Darling. “You can use it to get people's attention. I mean, it's much sexier to call something a robot than call something a dishwasher.” For that matter, "robot" certainly sounds sexier than “physically embodied artificially intelligent agent.” But a robot is a machine that senses and acts on its world. And soon enough, our world will be full of them. Just probably not in, you know, a The Day the Earth Stood Still kind of way. Staff Writer X Topics robotics Tammy Rabideau Ben Brubaker Maryn McKenna Matt Simon Erica Kasper Ramin Skibba Emily Mullin Kate Yoder 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 "

"This Clever Robotic Finger Feels With Light | WIRED"

"https://www.wired.com/story/this-clever-robotic-finger-feels-with-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 Matt Simon Science This Clever Robotic Finger Feels With Light Courtesy of Columbia University Save this story Save Save this story Save Robots already have us beat in some ways: They’re stronger, more consistent, and they never demand a lunch break. But when it comes to the senses, machines still struggle mightily. They can’t smell particularly well, or taste (though researchers are making progress on robotic tongues ), or feel with their robotic grips—and that’s a serious consideration if we don’t want them crushing our dishes or skulls. In a lab at Columbia University, engineers have developed a strange yet clever way for robots to feel: Let’s call it the finger of light. It’s got a 3D-printed skeleton embedded with 32 photodiodes and 30 adjacent LEDs, over which is laid a squishy skin of reflective silicone, which keeps the device’s own light in and outside light out. When the robot finger touches an object, its soft exterior deforms, and the photodiodes in the skeleton detect changing light levels from the LEDs. This allows the system to determine where contact is being made with the finger, and the intensity of that pressure. In other words, if you shook this robot’s hand, it wouldn’t feel it, in a traditional sense; it would see it. For decades, roboticists have been developing ways for machines to feel, a field called tactile sensing. A very basic method is using a transducer to convert pressure into an electrical signal. But, says Columbia roboticist Matei Ciocarlie, “the gap that's been really hard to cross, traditionally, is there is a difference between building a touch sensor and building a finger.” Courtesy of Columbia University 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 rigid transducer might sit well on a table, where it can freely sprout all kinds of wires, but fitting all that into a small, deformable finger has been a big challenge. A robot, after all, needs to have flexible digits if it’s going to pick up objects and feel them. Soft fingertips also help establish a firm grip. So roboticists have had to find workarounds. A company called SynTouch, for example, has pioneered a finger covered in electrodes, which is overlaid with a soft skin. Then, they inject saline in between the skin and the electrodes. When someone touches the finger, the electrodes detect the changing resistance through the saline, registering the location and intensity of that touch. The Columbia team’s new finger works in much the same way, but instead of electrodes and saline, it’s got those LEDs and photodiodes. When someone pokes the finger, all of the photodiodes look for changes in the amount of light they’re receiving. A photodiode closer to the poke will detect more of a change, while a photodiode on the opposite side of the finger will detect less. The system gets that information in fine detail, because 32 photodiodes times 30 LEDs equals 960 signals, which is a ton of data from a single poke. “Extracting information out of those 1,000 signals in an analytical way—it's very, very hard to do,” says Ciocarlie, who developed the system. “I would venture to say that it's impossible without modern machine learning.” Courtesy of Columbia University Machine learning comes into play when they’re calibrating the system. They can stick the finger on a table, point it upward, and use a separate robotic arm to prod the finger in precise spots, using a specific amount of pressure. Because they know exactly where the robotic arm is jabbing the finger, they can see how the photodiodes detect light differently at each location. (If you take a look at the GIF above, you can see the system both localizing the touch and the intensity as the red dot swells with more pressure.) Despite the large amount of data collected per jab, with machine learning, the system can crunch it all. “So that's the missing piece, the thing that's really become available to the field really in the last maybe five years or so,” says Ciocarlie. “We now have the machine-learning methods that we can add on top of these many, many optical signals, so that we can decipher the information that's in there.” This mimics how humans learn to wield our own sense of touch. As children, we grab everything we can, banking our memories of how objects feel. Even as adults, our brains continue to catalog the feel of things—for example, how much resistance to expect from a steering wheel when you’re turning left, or how hard to bang a hammer against a nail. “If we were to put you into the body of another person somehow, you would have to relearn all the motor skills,” says Columbia electrical engineer Ioannis Kymissis, who developed the system with Ciocarlie. “And that's one of the nice things about the plasticity of the brain, right? You can have a stroke, you can knock out half of the brain and still relearn and then function.” 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 new robotic finger, though, has its limits. While it can gauge the pressure it's placing on an object, it’s missing out on a bunch of other data that people can sense through our own hands but often take for granted, like temperature and texture. But interestingly enough, the researchers think they could listen to the robotic finger’s slip, or its motion as it slides over a surface. “When you have slip, there's a little bit of a singing—if you ever put your ear against the table and run your finger on the table,” says Kymissis. If you’re holding on to, say, a wet glass, the slip might happen on a small scale, then “spread” to your hand’s entire contact area as the glass slides out of your grasp. By listening to the characteristic noise of an object slipping out of a robot hand equipped with these new fingers, the machine could correct its grip before the slip spreads across the whole hand. What’s fascinating about this research is that while the engineers take inspiration from human biology, they mix up the sensory inputs in a decidedly un-human way. Human fingers rely on nerves to feel, but this new robotic finger sees objects, and perhaps one day will hear its contact with the surface. In the future, this may lead to robots that can better manipulate human objects, because they’ll be able to combine vision with a sense of touch, just as we do. The ability to use both is particularly helpful when dealing with cluttered environments that contain a bunch of objects, or situations in which a direct line of sight is blocked. Think about how you might reach into a messy drawer: Your primary sense is vision, but you switch to your sense of touch as your hand gets deeper into the drawer and closer to the object you want. A robot might have the same kind of problem: Perhaps the robotic arm can’t find an object it needs to grab because it’s at the bottom of a pile. Or maybe the robot arm itself gets in the robot’s line of sight. To be truly masterful at manipulating objects in the real world, a robot will have to freely switch between vision and touch. 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 “Tactile sensing can facilitate robot manipulation, especially when the robot gripper occludes objects from cameras,” says UC Berkeley roboticist Ken Goldberg, who wasn’t involved in this work. This new system, he adds, is a great improvement over previous robotic fingers that used electrodes overlaid with rubber to sense touch. These collected limited data, like simply determining whether or not the robot was making contact with another object. But thanks to the power of light, the new finger can provide much finer detail about everything it touches. Robots are a long way from matching the sensitivity of the human hand, sure, but we’ve got a good feeling about this clever new finger. Algae caviar, anyone? What we'll eat on the journey to Mars Deliver us, Lord, from the startup life A code-obsessed novelist builds a writing bot. The plot thickens The WIRED Guide to the internet of things How to share files securely online 👁 The secret history of facial recognition. Plus, 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 Staff Writer X Topics robotics Celia Ford Elizabeth Finkel Jorge Garay Rhett Allain Max G. Levy Emily Mullin Matt Simon Emily Mullin 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 a Real Dog Taught a Robot Dog to Walk | WIRED"

"https://www.wired.com/story/how-a-real-dog-taught-a-robot-dog-to-walk"

"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 How a Real Dog Taught a Robot Dog to Walk Photography: Kiyoshi Ota/Getty Images Save this story Save Save this story Save What you see when Boston Dynamics’ humanoid robot does a backflip or its Spot dog robot fights off a human and opens a door is incredible hardware engineering, to be sure. But what you don’t see is the wildly complex underlying code that makes it possible. What comes so easily to you—OK maybe not backflips, just walking—requires extreme coordination, which roboticists have to replicate, a kind of dance of motors working in concert. Pity the engineers who have to write out all that code. Over at Google, researchers have a secret weapon to teach robots to move that’s both less taxing and more adorable: dogs. They gather motion-capture videos from a public dataset, then feed that data into a simulator to create a digital version of the pooch. The researchers then translate the digital version of the real dog into a digital version of their four-legged robot—Laikago, which has a rectangular body and skinny legs. Then they port those algorithms into the physical version of Laikago. (The robot is named, by the way, after Laika , the Soviet space dog who was the first animal to orbit Earth.) A robot works quite differently than a biological dog; it has motors instead of muscles, and in general it’s a lot stiffer. But thanks to this translation work, Laikago has learned to move like a real-life canine. Not only that, its learned gait is faster than the fastest gait provided by the manufacturer of the robot—though in fairness it’s not yet as stable. The new system could be the first steps (sorry) toward robots that learn to move not thanks to exhaustive coding, but by watching videos of animals running and jumping. “The drawback with the kind of manual approach is that it's not really scalable for every skill that we want a robot to perform,” says AI researcher Jason Peng, lead author on a new paper describing the system. “We need long engineering hours in order to come up with the different strategies.” With this new approach, reinforcement learning algorithms do much of that work. Even though they’re both quadrupeds, the robot’s body is quite different from the dog’s body, so in the computer simulations the digital version of the robot has to figure out how to imitate the motion of the digital version of the dog without directly copying its mechanics. “So what the reinforcement learning algorithm does is it tries to find a way that allows the robot to be as close to the original reference motion as possible,” Peng says. By Matt Simon The algorithm tries random movements, and gets a digital “reward” if it gets closer to the dog’s reference motion—basically a thumbs-up message that says that was good, do that kind of thing again. If it tries something that’s not so hot, it gets a digital “demerit”— don’t do that kind of thing again. With this reward system, over many iterations the simulated robot teaches itself to move like the dog. The next challenge is known as sim-to-real; that is, taking what the system has learned in simulation and getting it to work in a physical robot. This is tricky because a simulation is an imperfect and highly-simplified version of the real world. Mass and friction are represented as accurately as possible, but not perfectly. The actions of the simulated robot in the digital world don’t map precisely to movements of the real robot in the lab. Courtesy of Google So Peng and his colleagues built not one definitive robot simulation, but a range of possibilities for what the robot’s behavior could be. They randomized friction in the simulation, for instance, and tweaked the latency between when you send the robot a command and when it actually executes the order. “The idea is that if we train the simulation with enough diversity, it might learn a good enough set of strategies, such that one of those strategies will work in the real world,” Peng says. All of these strategies are reasonable for the robot to pull off, by the way—they don’t want it to move so rapidly or violently that it will injure itself or humans. The system has already made its most catastrophic mistakes in the computer simulation—remember those demerits—so the robot doesn’t have to make them in the real world. But some of those behaviors result in a better gait than others. They ended up being remarkably dog-like behaviors, despite the robot’s lack of a dog anatomy; the researchers even got it to chase its nonexistent tail, spinning around in circles. It also learned a few that weren’t dog-like at all, like little dances from animations created by an artist. Courtesy of Google To be clear, this isn’t the first time that roboticists have looked to animal motion for inspiration. Boston Dynamics’ Spot robot is obviously modeled after the fluid motions of quadrupeds, and its Atlas humanoid is modeled after those of people. By taking such inspiration, Spot can clamber over the most difficult of terrains , thanks to meticulously-coded control algorithms. This new system? Not so much. “This thing is walking around on flat floors,” says Chris Atkeson, a roboticist at Carnegie Mellon University, who wasn’t involved in the research. “The state of the art is way beyond that in terms of rough terrain, particularly the Boston Dynamics stuff.” But there’s a bigger picture: If we want robots to be useful in an environment like the home, they’ll have to learn like we learn. Think about the last time you struggled to open a jar. You didn’t eventually get into it by smashing the top off. You went to the utensil drawer, got out a spoon, and pried the edge of the lid, releasing the seal, because you once saw another human do the same. Courtesy of Google “Let's say that that's how we do everything,” says Atkeson. “So what does that mean? Well, that means you’ve got to have this massive library of stuff you've seen other humans do. If you're presented with a situation that isn't in the library, you have to look among the elements of the library, find a couple cases that seem close, and maybe interpolate or pick the closest one, and use the techniques of this paper to make it work for the problem you really care about.” It’s going to take a whole lot of work to build such a library of movements that would be useful to legged robots. But doggonit, it’s better than hand-coding everything. Update, 4/3/20, 2 pm ET: The story originally noted that the researchers gathered their own motion-capture video, when in fact they used a public data set. Special issue: How we will all solve the climate crisis Why life during a pandemic feels so surreal OK, Zoomer! How to become a videoconferencing power user The Postal Service's surprising role in surviving doomsday Amazon workers face high risks and few options 👁 Why can't AI grasp cause and effect ? 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 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 Staff Writer X Topics robotics Ramin Skibba Matt Simon Amit Katwala Rob Reddick Matt Simon Ramin Skibba 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 "

"Iron Ox Brings Robotics to Hydroponic Greenhouse Farming | WIRED"

"https://www.wired.com/story/the-hydroponic-robotic-future-of-farming-in-greenhouses-at-iron-ox"

"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 The Hydroponic, Robotic Future of Farming in Greenhouses Save this story Save Save this story Save End User Startup Sector Agriculture Source Data Images Technology Robotics Machine learning When you think of automation, you probably think of the assembly line, a dramatic dance of robot arms with nary a human laborer in sight. But that’s child’s play. The grandest, most disruptive automation revolution has played out in agriculture. First with horses and plows, and eventually with burly combines—technologies that have made farming exponentially cheaper and more productive. Just consider that in 1790, farmers made up 90 percent of the US workforce. In 2012, it was 1.5 percent, yet America still eats. Here in 2017, the automation revolution in agriculture is poised to take on a whole new life—thanks to robots. In a nondescript office park in Silicon Valley, a startup called Iron Ox is taking the first steps toward roboticizing greenhouse farming, which has so far stubbornly resisted automation. In the very near future, then, the salad on your table may come from the hand of a robot. Unlike a lot of indoor farming operations, Iron Ox isn’t joining the booming movement of LED-powered grow houses. It’s still very much interested in harnessing the energy of the sun (free energy!). So it’s invading the greenhouse instead. “The problem up until today is that greenhouse production costs around twice as much to grow a head of lettuce as the outdoor farm,” says Brandon Alexander, CEO of Iron Ox. “And one reason is there's no tractors or anything indoors.” Iron Ox doesn't have a tractor, but it also doesn't need one. Its solution begins with a custom hydroponics tray filled with nutrient-rich water. Over that is a cover with a grid of holes, in which the plants sit in little pods. This is all designed so a custom robot—essentially an intelligent rectangular frame—can come along and slide lifters under the tray, then cart it to a different part of the greenhouse. Why bother with all the shuttling around? Because they can. Out in a field, farmers have no choice but to leave plants where they planted them—and because plants grow, farmers have to space out seeds to accommodate their fully-grown dimensions. But Iron Ox doesn't have to waste that extra space. Here in the greenhouse, they’re using different trays with different spacing of their holes, some farther apart than others. Leafy greens in particular need more horizontal room to expand, so baby plants start off in a more densely packed tray, then graduate to trays with more room as they grow. “This, combined with the fact that we don't have to worry about seasonality—we can always be seeding, always be harvesting—allows us to grow over 30X per acre compared to an outdoor farm,” says Alexander. 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 then becomes transplanting between trays. That’s where the robotic arm comes in. It sees with stereo cameras on its wrist, and grabs the plants with a gripper custom-designed to fit the pods (which the plants never outgrow, by the way). The arm sits between two trays of different densities, eyeballing the plants and moving them from one tray and to another. Because it’s equipped with a camera, it can simultaneously build a 3-D image of each plant. “Is it the size that we expect?" says Jon Binney, CTO of Iron Ox. "Is it the shape that we expect? If it's going to fall one way or the other, that could be a lighting problem. Brown spots on the edges of the leaves could be too much light and not enough air coming through.” So Iron Ox’s system not only automates greenhouse growing, but supercharges it. The company is developing machine learning algorithms that will automatically detect diseased plants and kick them out of the system before the sickness spreads. Underdeveloped plants would also get the boot. What you end up with is a system that does the repetitive tasks of greenhouse farming faster and more precisely than a human, and uses that data to make the process all the more efficient. More Robots Pause. Rewind Matt Simon Robots Matt Simon Robots Robbie Gonzalez Whether in the greenhouse or the field, it’s this kind of automation that will be essential to the future of humanity. Our species has to figure out how to feed a rapidly growing population on a planet that refuses to grow bigger. So we’ll have to get smarter about how we use the land we’ve got, or we’re going to have trouble. That and climate change will monkey with water supplies around the world, so the inefficiencies of traditional outdoor farming are going to start looking more and more untenable. (Iron Ox claims its hydroponics system uses 90 percent less water than outdoor farming. Studies of hydroponics in general have found about the same efficiencies. ) But automation means humans lose jobs though, right? Not in this industry. “We've talked to dozens of commercial farmers, outdoor and indoor, and the biggest issue by far is labor scarcity,” says Alexander. “So the truth is today, it doesn't matter what country, newer generations are not taking up farming. And so there's a significant labor shortage especially here in California.” (He ain’t lying— between 2002 and 2014, the number of full-time farm workers in the US plummeted by 20 percent. ) The solution is to hand the future of our food supply to the machines. There’s simply no other way to go about it. So be careful not to bite the robotic hand that feeds you. Staff Writer X Topics robotics agriculture Matt Reynolds Matt Simon Kate Yoder Matt Reynolds Maryn McKenna Matt Simon Jim Robbins Amit Katwala 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 "

"What Is Lidar, Why Do Self-Driving Cars Need It, and Can It See Nerf Bullets? | WIRED"

"https://www.wired.com/story/lidar-self-driving-cars-luminar-video"

"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 Alex Davies Transportation What Is Lidar, Why Do Self-Driving Cars Need It, and Can It See Nerf Bullets? Save this story Save Save this story Save If you've been in Silicon Valley, Pittsburgh, Boston, San Francisco, or any of the other cities where autonomous cars are crawling the streets in a 21st century version of drivers ed, maybe you've wondered: What's up with that overgrown gumdrop-looking spinning thing on the roof? That, dear carbon-based life form, is lidar, perhaps the most important piece of hardware in the race to unlock self-driving cars for everybody. Lidar works much like radar, but instead of sending out radio waves it emits pulses of infrared light—aka lasers invisible to the human eye—and measures how long they take to come back after hitting nearby objects. It does this millions of times a second, then compiles the results into a so-called point cloud, which works like a 3-D map of the world in real time—a map so detailed it can be used not just to spot objects but to identify them. Once it can identify objects, the car's computer can predict how they will behave, and thus how it should drive. Self-driving cars use other sensors to see, notably radars and cameras, but laser vision is hard to match. Radars are reliable, but don't offer the resolution needed to pick out things like arms and legs. Cameras deliver the detail, but require machine-learning-powered software that can translate 2-D images into 3-D understanding. Lidar, by contrast, offers hard, computer-friendly data in the form of exact measurements. That's why every serious player in the self-driving car race believes the laser sensor is an indispensable ingredient for a fully robot car, the kind that doesn't need a steering wheel or a human hand. (The notable exception is Tesla's Elon Musk , who insists cameras can do the job. ) This is why lidar is at the center of the blockbuster legal case between Waymo and Uber: The company that started life as Google's self-driving car project says that when its longtime engineer Anthony Levandowski left for Uber, he brought Waymo's lidar trade secrets with him. It's also why dozens of companies are competing to overcome lidar's key weakness: It's too young for a rough life on the road. This laser sensing technique has been around for decades—NASA's Apollo 15 used it to map the moon—but it wasn't until 2005 that it came to the world of cars. That's when an engineer named Dave Hall, CEO of a speaker manufacturer called Velodyne and a participant in Darpa's Grand Challenge self-driving vehicle race , decided he needed a better way for his Toyota Tundra to see its surroundings. He built 64 laser emitters into a device that resembled a flattened disco ball, stuck it on the pickup's roof, and all of a sudden had a new kind of vision. Other teams that had been using primitive laser scanners gushed over the development. So Velodyne stopped making high-end speakers and started making lidars. When the teams came back for another race in 2007 , every serious contender had a Velodyne lidar on its roof. 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 More than a decade later, autonomous driving is on the verge of commercialization, but lidar remains relatively underdeveloped. First, it's expensive. The cheapest sensor on the market is the $4,000 Velodyne puck , but any city-dwelling robocar would need several to see all its surroundings. That's a lot of money to add to the cost of every car. (Big players like Waymo and General Motors have in-house versions of lidar , and they don't reveal what they cost.) Second, making it work on a car is really hard. Anything going into vehicles has to be robust and reliable, able to withstand a life of potholes and temperature extremes, and it has to keep working for years. Deploying AVs in fleets run by a single operator will ease those problems (you can amortize cost by running the vehicles nonstop and bringingf them in for regular maintenance), but still: Lidar needs to get better. For a look inside this all-important laser sensor, we met up with Austin Russell, the CEO of Luminar, the lidar company he founded six years ago, after dropping out of Stanford at 17. (Slacker.) Russell, who has already signed a deal to work with Toyota , says his sensor can see much farther and with better resolution than anything on the market now. But can it see the dart from a Nerf gun? Watch the video above to find out. An oral history of the Darpa Grand Challenge, the grueling robot race that launched the self-driving industry Prepping self-driving cars for the world's most chaotic cities Waymo v. Uber kicks off with Travis Kalanick in the crosshairs Senior Associate Editor Facebook X Instagram Topics Self-Driving Cars Uber Waymo Aarian Marshall Aarian Marshall Aarian Marshall Gregory Barber Steven Levy Andy Greenberg Steven Levy 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 "

"The Little Robot That Taught the Big Robot a Thing or Two | WIRED"

"https://www.wired.com/2017/05/little-robot-taught-big-robot-thing-two"

"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 The Little Robot That Taught the Big Robot a Thing or Two Save this story Save Save this story Save Your brain is great and all, but it has a serious limitation: You can’t just download new information instantly, like in The Matrix. Robots, however, certainly can. Just imagine a future where they’re hooked up in the cloud---when one of them learns something, they all learn something. Let’s just hope that certain something is nice, like how to give hugs. The problem, though, is that you can’t just have a little rover learn to grasp something, then expect that knowledge to translate into a hulking bipedal robot. But new research out today from the MIT Computer Science and Artificial Intelligence Laboratory takes a big step toward making such seamless transfers of knowledge a reality. It all begins with a little robot named Optimus and its friend, the famous 6-foot-tall humanoid Atlas. The researchers started by teaching Optimus---a two-armed robot meant for bomb disposals---how to pull a tube out of another tube. First, they gave it some information about how different objects require different manipulations. Then they held its hand in a sim. “Imagine kind of a videogame where the robot is inside that 3-D world,” says roboticist Claudia Perez-D’Arpino , co-author of the study. “With the mouse you can basically grab the hands and move them around.” This way, you don’t have to be a gifted coder to be able to command a robot. And it’s all the more intuitive for the operator because it’s a lot like how humans learn: Toddlers have a knowledge base of, say, grasping a binky, but can recontextualize that knowledge of manipulation as they encounter new objects. Now, how to transfer the robot’s skills to a biped Atlas many times its size? After all, this bot has a new challenge: not falling on its face. “So mathematically that can be written as another series of constraints,” says Perez-D’Arpino, “which if you can imagine is like, keep your center of mass within some region. ” Essentially, the operator has to give the new robot some rules, like how to balance correctly, to perform the same task as Optimus. Combine those rules with what Optimus has already learned about manipulating the tubes, and you get a smooth transfer of knowledge. It's not an automatic handoff, to be sure, but it's a start. At the moment, Atlas can only do the handoff in a simulator. But the development is a glimpse into a future where, more and more, robots communicate without humans at all. They might, for instance, teach themselves to pull tubes out of tubes through a process known as reinforcement learning ---essentially trying and trying and trying until they finally get it right. Imagine the power of this in a factory setting: If one robot learns how to manipulate something more efficiently, it can distribute that knowledge to its comrades through the cloud. And with tweaks like what Perez-D’Arpino has demonstrated, that knowledge might even work with other species of robot as well. Meaning soon enough, robots will think gooder without human help and disseminate those skills freely. Skills like hugging, right? 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 Staff Writer X Topics machine learning robotics Ben Brubaker Swapna Krishna Charlie Wood Erica Kasper Tammy Rabideau Grace Browne Elizabeth Finkel Celia Ford 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 "

"Astrobee: The Adorable Little Robot That'll Soon Jet Around the ISS | WIRED"

"https://www.wired.com/2017/05/astrobee-adorable-little-robot-thatll-soon-jet-around-iss"

"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 Astrobee: The Adorable Little Robot That'll Soon Jet Around the ISS Save this story Save Save this story Save It is, without a doubt, the most expensive air hockey table on Earth. Surrounded by three walls papered with pictures of the International Space Station’s interior, the perfectly polished, perfectly level granite slab at NASA’s Ames Research Center supports not a puck, but a robot riding on a cushion of CO 2. Astrobee, it’s called, is a cubic bot outfitted with 12 thrusters spitting blasts of air. It glides cautiously across the granite, sounding not unlike a muted jet engine. It’s weirdly soothing. This is a training exercise---the wallpaper is for Astrobee to get its bearings. Because soon the robot will break free of this replica of a microgravity space lab and head to the real ISS, where it will float around in 3-D space, assisting astronauts in a range of tasks. It’s an impressive feat of engineering, and a fascinating glimpse at NASA’s robotic future in space. Astrobee is a semi-autonomous machine. Most of the time, and especially in the early days of its deployment (likely early next year), an operator will control the robot to make sure it’s getting along with the crew. But Astrobee can also putter about on its own, taking video of the astronauts---so, for instance, an expert on the ground might walk them through particular problems---and return autonomously to a dock to recharge. Somebody Just Buy the ISS Already NASA Is Finally Sending a Hotel Magnate’s Inflatable Habitat to the ISS Watch NASA Launch 38 Itty Bitty Satellites to the ISS To find its way around, the robot uses an array of sensors, from a camera that builds a 3-D map like Microsoft’s Kinect system, to a general purpose camera that keeps an eye out for landmarks. Astrobee can, say, spot a pole attached to the wall, grab it with a robotic arm, then idle its engines to save energy while it continues eyeballing the crew. On top of working like an ultra-expensive baby monitor, Astrobee will function as a scientific workhorse for researchers. “They'll be able to put new software on our system, basically reprogram how it works,” says Trey Smith , systems lead for Astrobee. “And they'll also be able to plug in additional payloads to the system to try out new sensors or new arms or anything like that.” All of this of course demands precise control, no easy task when you're floating around willy-nilly. To that end, Astrobee uses blasts of air to steer itself. Bookending a central module are two propulsion modules, which draw in air with a propeller and blow it out any of 12 total nozzles. “Each nozzle is pointed in a fixed direction but it has two flappers inside that can open or close the air flow out of that nozzle,” says Smith. Activate the right nozzles and you can steer Astrobee in any direction. Astrobee’s biggest sell, though, is its autonomy. That feature makes it a significant upgrade from NASA’s Spheres robots (deep breath: Synchronized Position Hold, Engage, Reorient, Experimental Satellites), more-or-less cylindrical research tools that have been floating around the ISS for over a decade, giving researchers insights into satellite movement in microgravity. Astrobee is far more advanced and far more autonomous, meaning Astrobee is going places. Like, maybe one day outside the space station to inspect damage or perform routine maintenance. That all depends, though, on the fate of the ISS itself, which NASA is only funded to operate through 2024. Regardless, you can expect more helpful robots like Astrobee as NASA tries to automate mundane or dangerous tasks to push human exploration to Mars and beyond. For the near future, though, Astrobee will be NASA’s eye way, way up in the sky. 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 Staff Writer X Topics NASA robots space Ramin Skibba Ramin Skibba Ramin Skibba Ramin Skibba Matt Simon Ramin Skibba Matt Simon 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 Future of Humanity's Food Supply Is in the Hands of AI | WIRED"

"https://www.wired.com/2016/05/future-humanitys-food-supply-hands-ai"

"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 The Future of Humanity's Food Supply Is in the Hands of AI Blue River Technology Save this story Save Save this story Save Humanity’s got itself a problem. As Homo sapiens balloons as a species---to perhaps nearly 10 billion by 2050---the planet stubbornly stays the same size, meaning the same amount of land must support way, way more people. Add the volatility of global warming and consequent water shortages, and the human race is going to have some serious trouble feeding itself. Perhaps it’s serendipitous, then, that the machines have finally arrived. Truly smart, truly impressive robots and machine learning algorithms that may help usher in a new Green Revolution to keep humans fed on an increasingly mercurial planet. Think satellites that automatically detect drought patterns, tractors that eyeball plants and kill the sick ones, and an AI-powered smartphone app that can tell a farmer what disease has crippled their crop. Forget scarecrows. The future of agriculture is in the hands of the machines. Deep learning is a powerful method of computing in which programmers don’t explicitly tell a computer what to do, but instead train it to recognize certain patterns. You could feed a computer photos of diseased and healthy plant leaves, labeled as such. From these it will learn what diseased and healthy leaves look like, and determine the health of new leaves on its own. That’s exactly what biologist David Hughes and epidemiologist Marcel Salathé did with 14 crops infected by 26 diseases. They fed a computer more than 50,000 images, and by learning on its own, the program can correctly identify 99.35 percent of the new images they throw at it. Still, those are manipulated images, with uniform lighting and backgrounds so it’s easier for the computer to make sense of the leaves. Pluck an image of a diseased plant from the Internet and feed it to the computer and the accuracy is around 30 to 40 percent. Not terrible, but Hughes and Salathé hope to see this AI power their app, PlantVillage, which currently allows farmers around the world to upload a photo of their ailing plants to a forum for experts to diagnose. To smarten up the AI, they'll continue feeding it photos of diseased plants. “More and more images from various sources, in terms of how the pictures were taken, time of year, location, and so on,” says Salathé. “And the algorithm can just pick up on that and learn.” 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 isn’t simply a matter of ferreting out infections: Plenty of other things beat plants up. “Most diseases that hamper growers are physiological stresses, so not enough calcium or magnesium or too much salt or too much heat,” says Hughes. “People often think it's a bacterial or fungal disease.” Misdiagnoses can lead to farmers wasting money and time on pesticides or herbicides. In the future, AI could help farmers quickly and accurately pinpoint the problem. After that, the humans will wrest back control—because while an app might be able to find the problem, only an extension expert can tailor a solution to a specific climate or soil or time of year. The UN’s Food and Agriculture Organization considers such technology a “useful tool” for crop management, but the expert’s word is doctrine. Thus, says Fazil Dusunceli, a plant pathologist with the FAO, such electronic results are welcome, but “final pest management decisions should be taken in collaboration with experts on the ground.” While the developing world is hungry for agricultural knowledge, the developed world is drowning in pesticides and herbicides. In the US each year, farmers use 310 million pounds of herbicide---on just corn, soy, and cotton fields. It’s the spray-and-pray approach, not so much sniping as carpet bombing. A company called Blue River Technology may have hit upon solution, at least as far as lettuce is concerned. Its LettuceBot looks like your typical tractor, but in fact it’s a machine-learning-powered … machine. Blue River claims the LettuceBot can roll through a field photographing 5,000 young plants a minute, using algorithms and machine vision to identify each sprout as lettuce or a weed. If that seems too impossibly fast to you, "it's well within the computing of machine learning and computer vision," says Jeremy Howard, founder of deep-learning outfit Enlitic. A graphics chip can identify an image in just .02 seconds, he adds. With an accuracy within a quarter inch, the bot pinpoints and sprays each weed on the fly. If it eyeballs a lettuce plant and determines it isn’t growing optimally, it’ll spray that too (farmers overplant lettuce by a factor of five, so they can sacrifice plenty of extras). If two sprouts ended up too close to one another during planting (not ideal), the machine can discern them from, say, one particularly large plant, and zap them as well. 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 Now, consider the alternative: spraying a field with herbicides willy-nilly. “It's akin to saying if a few people in the city of San Francisco had an infection, your only solution would be to give every man woman, and child in the city an antibiotic,” says Ben Chostner of Blue River Technology. “People would be cured, but it's expensive, it's not using the antibiotics to the best of their potential.” With the LettuceBot, on the other hand, Chostner says farmers can reduce their use of chemicals by 90 percent. And the machine is already hard at work---Blue River treats fields that supply 10 percent of the lettuce in the US annually. Blue River Technology LettuceBot is so powerful because it uses machine learning to make one of the few things robots are already great at even better: precision. Robots can’t run like us or manipulate objects quite like we do, but they’re consistent and meticulous---the perfect agricultural snipers. Orbiting over 400 miles above your head, NASA’s Landsat satellites provide a downright magical survey of Earth’s surface in a slew of bandwidths far beyond the visible spectrum. All of these layers of information are hard to digest for a human, to be sure, but for machine learning algorithms, they ain’t no thing. And that could be extremely valuable for monitoring agriculture, particularly in developing countries, where governments and banks face a dearth of data when making decisions about which farmers they give loans or emergency assistance to. During a drought in India, for instance, not only will regions suffer to different degrees, but within those regions some farmers might have better means to procure water than others. 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 a startup called Harvesting is analyzing satellite data on a vast scale with machine learning, with the idea to help institutions distribute money more efficiently. “Our hope is that in using this technology we would be able to segregate such farmers and villages and have banks or governments move dollars to the right set of people,” says Harvesting CEO Ruchit Garg. While a human analyst can handle 10, maybe 15 variables at a time, Garg says, machine learning algorithms can handle 2,000 or more. That’s some serious context. Choosing where to allocate resources is a particularly pressing problem for governments as a warming Earth sends the climate into chaos. Traditionally, farming in India has been a relatively predictable affair, at least as far as humans holding dominion over their environment goes. “So what I learned from my father, my grandfather, that's how I grow, these are the seasons I know,” Garg says. “However because of drastic climate change, things are no longer what my father or my grandfather used to do.” It’s the new world order, folks. Farmers can take the punches, or they can farm smarter. More data, more AI, and more chemical-spraying robots. As for those tomato plants you keep neglecting---that one’s on you, I’m afraid. Staff Writer X Topics agriculture machine learning Max G. Levy Grace Browne Max G. Levy Matt Simon Amit Katwala Dell Cameron 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 "

"Why We Need Brain Scan Data Guidelines | WIRED"

"https://www.wired.com/story/why-we-need-brain-scan-data-guidelines"

"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 D. Morris Science Why We Need Guidelines for Brain Scan Data Could a court order someone to undergo fMRI or PET? Photograph: Department of Cognitive Neurology/Science Source Save this story Save Save this story Save Your brain is a lot like your DNA. It is, arguably, everything that makes you uniquely you. Some types of brain scans are a lot like DNA tests. They may reveal what diseases you have (Parkinson’s, certainly; depression-possibly), what happened in your past (drug abuse, probably; trauma, maybe), or even what your future may hold (Alzheimer’s, likely; response to treatment, hopefully). Many people are aware—and properly protective—of the vast stores of information contained in their DNA. When DNA samples were collected in New York without consent, some went to great lengths to have their DNA expunged from databases being amassed by the police. Evan D. Morris, Ph.D., is a professor of radiology and biomedical imaging at Yale. He uses PET and fMRI to study drug abuse and drug action in the brain. In August 2019, he was a visiting scholar at the Hastings Center to study the ethics of brain imaging. Fewer people are aware of the similarly vast amounts of information in a brain scan, and even fewer are taking steps to protect it. My colleagues and I are scientists who use brain imaging (PET and fMRI) to study neuropsychiatric diseases. Based on our knowledge of the technologies we probably ought to be concerned. And yet, it is rare that we discuss the ethical implications of brain imaging. Nevertheless, by looking closely, we can observe parallel trends in science and science policy that are refining the quality of information that can be extracted from a brain scan, and expanding who will have access to it. There may be good and bad reasons to use a brain scan to make personalized predictions. Good or bad, wise or unwise, the research is already being conducted and the brain scans are piling up. PET (Positron Emission Tomography) is commonly used, clinically, to identify sites of altered metabolism (e.g., tumors). In research, it can be used to identify molecular targets for treatment. A recent PET study of brain metabolism in patients with mild cognitive impairment predicted who would develop Alzheimer’s disease. In our work at Yale, we have used PET images of a medication that targets an opioid receptor to predict which problem drinkers would reduce their drinking while on the medication. fMRI (functional Magnetic Resonance Imaging) detects local fluctuations in blood flow, which occur naturally. A key discovery in the 1990s found that fluctuations in different brain regions occur synchronously. The networks of synchronized regions have been shown repeatedly to encode who we were from birth (our traits) and also long term external effects on our brains (from our environment). fMRI analysis techniques are getting so powerful that the networks can be used like a fingerprint. fMRI networks may be even richer in information than PET–but also more problematic. The networks (sometimes called “functional connectivity” patterns) have been used to predict intelligence. They have been used to predict the emergence of schizophrenia or future illicit drug use by at-risk adolescents. Functional connectivity is being used to predict which adult drug abusers will complete a treatment program and who is likely to engage in antisocial behavior. Some predictions are already 80 to 90 percent accurate or better. Driven by AI and ever-faster computers, the predictive ability of the scans will improve. Most medical research using brain imaging is funded by the NIH (National Institutes of Health). At least one institute (the National Institute of Mental Health) requires that its grant recipients deposit all of their grant-funded brain scans into an NIH-maintained database. This and similar databases around the world are available for other “qualified researchers” to mine. Some uses of brain imaging would seem to have only upsides. They might provide certainty for patients and their families who desperately need help planning for their colliding futures. They could avoid unnecessary and costly treatments that are destined to fail. But other uses of brain imaging lie in an ethical gray area. They foretell behaviors and conditions that could be stigmatizing or harmful. They generate information that an individual may wish to keep private or at least manage. In the right circumstance, the information may even be of great interest to the police or the court system. As the New York Times recently reported , the police in New York City tricked a child into leaving his DNA on a soda can. I recognize that fMRI networks cannot be captured surreptitiously by enticing a 12-year old to drink a soda. The police will not use fMRI fingerprints solely as identifiers. It would be too much trouble. But many questions arise. Could a court order someone to undergo fMRI or PET? Could a prosecutor subpoena a brain scan that a suspect consented to in the past as a research volunteer? Forensic genealogists tracked down the Golden State Killer without ever taking a sample of his DNA. They triangulated using DNA markers he shared with unacquainted third cousins who had uploaded their DNA sequences to a public database. Could a forensic brain imager identify you as unlikely to complete drug treatment and thus a bad candidate for diversion? What if we could predict your future behavior by similarities that your fMRI networks share with those of psychopaths who had been analyzed and whose data now resides in a database? Even now, it seems plausible that a qualified scientist working with police could download the data. If that didn’t work, the police might get a warrant. Will the NIH relent and share their databases of images when the police come calling? 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 are questions that brain imagers, legal experts, ethicists, and the public should be debating. Scenarios that may seem far-fetched right now raise troubling questions that ought to be anticipated. Genetic testing controversies of today can serve as models for how we think about the potential uses and misuses of brain imaging. Thorough debate should lead to guidelines or policies. A report by the National Academies on the Ethics of Brain Imaging may be needed. What is at stake? The integrity of the scientific enterprise. As scientific researchers, we are obligated to obtain “informed consent” from our research subjects. Volunteers must be apprised of the risks they may incur by agreeing to participate in our studies. Scientists generally do a good job of explaining risks to volunteers. “The radiation exposure you will receive is comparable to the natural radiation you would get from three round-trip trans-continental airplane rides.” But brain scanning may be moving toward new uses and abuses that come with risks we have not yet considered. The principle of “autonomy” establishes the right of volunteers to control how their brain scans will be used – scientifically or otherwise. The public who funds, and the volunteers who participate in research studies must have confidence that brain scanning is being conducted ethically and that the far-reaching personal information being generated is being used only as intended. WIRED Opinion publishes articles by outside contributors representing a wide range of viewpoints. Read more opinions here. Submit an op-ed at [email protected]. The unbuilt streets of California's ghost metropolis Computer scientists really need to take ethics classes London is changing its skyscraper designs— to favor cyclists Jeffrey Epstein and the power of networks A history of plans to nuke hurricanes (and other stuff too) 👁 How do machines learn ? Plus, read the latest news on artificial intelligence ✨ Optimize your home life with our Gear team’s best picks, from robot vacuums to affordable mattresses to smart speakers. Emily Mullin Emily Mullin Ramin Skibba Emily Mullin Swapna Krishna Emily Mullin Rhett Allain 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 "

"How a Crispr Lab Became a Pop-Up Covid Testing Center | WIRED"

"https://www.wired.com/story/crispr-lab-turned-pop-up-covid-testing-center"

"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 Megan Molteni Gregory Barber Science How a Crispr Lab Became a Pop-Up Covid Testing Center Photograph: Wladimir Bulgar/Getty Images Save this story Save Save this story Save Like many of the first 6.7 million Americans asked to shelter in place, Enrique Lin Shiao was spending more time than usual on Twitter. The molecular biophysicist had moved to the Bay Area in September to join Crispr luminary Jennifer Doudna’s lab at UC Berkeley. Among his projects was improving the widely used genome editing technology so that it could cut and paste long strings of DNA instead of just making simple cuts. But on March 16, local health officials ordered residents of six Bay Area counties to stay at home to prevent the further spread of Covid-19. So he stayed home, and scrolled. Then a tweet from UC Berkeley’s Innovative Genomics Institute dropped into his timeline. “We are working as hard as possible to establish clinical #COVID19 testing capability @UCBerkeley campus,” it read, with a link to a volunteer sign-up page. Lin Shiao clicked. When Lin Shiao showed up to the first floor of the glistening glass IGI building the next day, he wasn’t exactly sure what he was walking into. The once-cramped lab space, usually used for gene sequencing projects, was being dismantled. People Lin Shiao had never seen before unplugged machines and wheeled them away. Others carted out boxes of chemicals. Within days, it would be filled with new equipment: towering glass-encased robots, a sterile hood for working with dangerous pathogens, and—scattered across tables, desks, and the floor—test tubes of every possible shape and size. It’s here, less than two weeks later, that Lin Shiao and dozens of fellow volunteers are now getting ready to begin testing their first patient samples for Covid-19. By Sara Harrison If you’ve been following the US’s slow-motion testing trainwreck , it should be obvious why they had heeded the call: The country needs more testing. Recently, the capacity for administering tests in California has surged, especially as commercial labs like Quest Diagnostics and Lab Corps have begun taking samples. But according to official tallies, the state still has a major backlog when it comes to processing those results. As of Wednesday, 87,000 tests had been collected. But of those, more than 57,000 were still pending results. And while they wait, many of those patients are taking up space in isolation wards and disrupting hospital operations. IGI is among several academic labs that have wasted no time booting up operations to fill the still yawning void in Covid-19 testing. Right now, California is on par with national averages, testing about one out of 1,000 people. By contrast, South Korea, which has brought its own outbreak under control using aggressive testing and contact tracing, has tested one in 170 people. But the path to opening up the state’s academic research labs to testing hasn’t been simple. How does a crew of Crispr researchers with no prior clinical diagnostic experience jump into the trenches so quickly? It requires long hours, connections with equipment suppliers, a willingness to test regulatory boundaries, and burning through lots of cash. On March 9, after a few days idling at sea, the Grand Princess cruise ship arrived at the Port of Oakland. The ship had returned from Hawaii after infected passengers were discovered from a prior voyage—some travelers had remained and spread the virus to others. But of the more than 3,000 people on board—all at high risk of infection in the ship’s close quarters—just 46 had been tested while at sea, with 21 returning a positive result. As for the rest: Nobody knew. As the passengers went into 14 days of quarantine after they landed, Vice President Mike Pence promised all would be tested. (Due to delays, few ever were. ) As the passengers disembarked, Julia Schaletzky, head of Berkeley’s Center for Emerging and Neglected Diseases, watched the news coverage with frustration. The federal government’s testing failures were, by then, well-acknowledged. At first, the Centers for Disease Control had attempted to do all screening itself, requiring samples to be shipped to the agency’s headquarters in Atlanta—a plan scuttled by flawed tests and surging demand. Over time, starting in mid-February, the feds began slackening those rules, first by allowing state labs to conduct tests using the CDC’s kits and, later, permitting other labs with clinical certification to screen their own tests. 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 to Schaletzky, the Grand Princess demonstrated that the US was still lagging far behind. Which was silly, she decided. Schaletzky, who researches vaccines, knew her university was filled with genetics equipment, including the tools needed to screen Covid-19 tests for viral RNA. (Finding the virus' unique genetic sequence in a swab from a person's nose or throat is sure evidence that the person has been infected.) And the campus is usually full of competent technicians and professors to do it. What UC Berkeley doesn’t have, however, is a medical school, which means it lacks a lab space with all the right certifications to handle patient samples. On March 13, Schaletzky wrote an editorial in The Mercury News in San Jose, calling for the federal government to relax regulations for academic research labs that wanted to participate in Covid-19 testing. “What’s stopping us? Red tape,” she wrote, listing the amount of time it would take to get the lab certifications needed to begin testing: months for certification through regulations called Clinical Lab Improvement Amendments, which govern all labs that involve human testing; permission from the FDA to conduct a Covid-19 test; weeks to handle viral samples. The other problem was funding. Barring an infusion of new cash, how would they get permission from funders like the National Institutes of Health to reallocate grants meant for other research? Little did Schaletzky know that on the same day her op-ed published, Jennifer Doudna was giving a rousing speech to the core members of the IGI, a three-year-old Crispr research hub where Doudna is the executive director. According to people present, the usually understated Crispr co-discoverer looked up at her colleagues seated in the auditorium and said, “Folks, I have come to the conclusion that the IGI must rise and take on this pandemic.” “When I heard that, I had this vision of Lady Liberty not lifting up a torch but raising a micropipette,” says Fyodor Urnov, the IGI’s scientific director. While some work at IGI would pivot toward Covid-19, including existing efforts to develop Crispr-based diagnostics and genetic therapies, Doudna deputized Urnov to put together a new team to tackle the testing issue from scratch. 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 theory, they already had everything they needed to conduct a Covid-19 test like those being run at state public health labs and big commercial testing labs. These tests are based on a decades-old technology called RT-PCR, which picks out and amplifies any bits of the coronavirus’s genetic material floating around in a patient’s nose or throat. It requires the machines that do this, known as thermocyclers, and people who know how to use them. But most microbiology labs are chock full of these kinds of people, because RT-PCR comes up all the time when you’re studying genes, or gene editing. Berkeley had lots of both. However, until very recently, the federal government wouldn’t allow just any of these researchers to do diagnostic testing. Per US Food and Drug Administration rules, only CLIA-certified labs can test patient samples for the purposes of providing a diagnosis. On March 16, under continually mounting pressure to make tests more widely available, the FDA updated its policy , shifting responsibility for regulating clinical testing sites to individual states. “The feds totally washed their hands of the shitshow,” Schaletzky says. The state's subsequent guidance allowed the researchers to fall back on an executive order from Governor Gavin Newsom, issued earlier in the month, which had removed state licensing requirements for people running Covid-19 tests in CLIA-certified labs. As a result, the IGI researchers could skip those months of training provided they could find a clinical lab to lend them its certification. Of all the labs on campus, there was exactly one that had the right certifications to process samples from actual patients: the student health center. The venue wasn’t ideal. While the clinical testing lab at the University of California San Francisco, a major medical center, has 40 technicians, working around the clock in shifts, Berkeley’s student health center ordinarily has just two. It also lacked the required biosafety infrastructure to test for Covid-19. That’s why those two technicians had been sending samples from any potential coronavirus patients to a nearby commercial laboratory. But bogged down by an influx of samples and issues with sourcing necessary testing reagents, it was taking a week to get results back to UC Berkeley, according to Guy Nicollette, assistant vice chancellor of the university’s health services. As a result, the health center has been only ordering tests for high-risk patients: those with severe symptoms or underlying conditions. Just 30 students were tested in the month of March. “In a perfect world we’d be able to test everyone who wants to get tested,” says Nicollette. “Which is why we are thrilled to partner with researchers that will expand our testing capacity much closer to that goal.” 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 Getting the student health center to extend its CLIA certification to a 2,500-square-foot laboratory on the first floor of the IGI was key to being able to eventually deliver test results. But first a new testing lab had to be built. Acquiring all the necessary equipment and software would take a mix of buying, borrowing, and cannibalizing IGI’s own Crispr labs. RT-PCR testing flow has three basic steps. Step one: Extract any viral RNA that might be present in a patient’s sample. Step two: Make lots of copies of that viral genetic material, if it exists. Step three: Read out those copies as either a positive or negative test result and securely beam it into that patient’s electronic health record. RNA extraction can be done by hand, which is often the case at public health labs and other smaller operations. It requires the carefully orchestrated additions of different chemicals, enzymes, and tiny beads that catch the virus’s RNA. But doing these steps over and over for hundreds of samples really starts to add up not just in terms of time, but in the potential for making errors. To minimize both, IGI officials decided to buy a new robot. They chose one from Hamilton, called the STARlet, that can take 100 patient sample tubes in a single go and transfer the liquid inside each one into its own barcoded dimple on a 96-well plate. That would have been fine if they wanted to stick with the older PCR machines that had been originally recommended by the CDC for Covid-19 testing. But newer ones can run four times more samples—384 at a time—faster and more accurately. To extract RNA at that kind of scale, the IGI crew pinched a different liquid-handling robot—the $400,000 Hamilton Vantage—from one of the now silent Crispr labs upstairs. It takes the 96-well patient sample plates, purifies out the viral RNA, and converts them into PCR-ready 384-well plates, all without any human volunteers having to handle them. Among those on the lookout for more PCR equipment was an evolutionary biology professor at UC Berkeley named Noah Whiteman. On March 9, before Doudna’s rousing speech and Schaletzky’s searing op-ed, he had put out a call to his colleagues on Twitter, asking for an inventory of any PCR machines they had, in case the area’s Covid-19 testing facilities ran short. “Hopefully we won’t need the list,” he wrote at the time. He quickly compiled a list of about 30 machines into a Google Doc. 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 IGI crew rummaged through that list for newer machines capable of running 384 samples at a time. It was also important to them to pick not only the right brand of PCR machine, but also its accompanying gear. They needed to have a ready supply of reagents, swabs and even the right tubes to store the swabs so that the lab wouldn’t run into shortages down the line. “A lot of labs are running out of swabs,” Schaletzky says. “It’s not like we don’t have swabs. We could use Q-tips in a pinch, but it would take weeks to revalidate everything because of regulations.” The IGI testing protocol team, led by Lin Shiao, settled on a kit from Thermo Fisher that had already been authorized for emergency use by the FDA. The company had produced a million kits upfront. So IGI—along with some individual professors—plowed its own funds into stockpiling tons of those kits. Urnov estimates the institute has already spent $300,000 on kits from Thermo alone and plans to buy lots more in the coming months. “We are literally burning cash,” he says, adding that sitting on its donor-provided funds in a time of pandemic would be “a violation of everything we stand for.” “We have no money from the feds at all,” Schaletzky says. But to make these kits run on the newer machines required adapting the kits, miniaturizing them for the more densely packed 384-well plates. That’s where the robot comes in. “We wouldn’t use them if we were doing RNA extraction manually because the liquid sizes are so small that they’re very prone to human error,” says Lin Shiao. “The robot is way more accurate. That’s what is going to allow us to eventually scale up to 4,000 samples a day.” (Whiteman notes the list wasn’t only useful to Berkeley; at least one other PCR machine from the list was sent to UCSF to help with the high-throughput testing effort there.) Read all of our coronavirus coverage here. At Berkeley, as the robotics team was programming the robots and the protocol team was miniaturizing the protocols, other volunteers—including executives from SalesForce and laboratory information firm Third Wave Analytics— were busy setting up and testing the electronic chain of custody software that would keep track of each sample according to its unique barcode. This HIPAA-compliant code will ultimately be responsible for transmitting information about where each sample was in the testing process, including the test’s eventual result, back to the doctor who ordered it. Meanwhile, the health center brought a former technician back out of retirement to oversee the lab’s usual operations, while a certified lab director came in from UC Davis to oversee the Covid-19 testing. In addition to Lin Shiao, within a few hours, 861 other people had responded to the IGI’s call for volunteers. Several dozen of the more qualified ones—people with prior RNA extraction and PCR experience—now had to get trained up on CLIA compliance. They learned how to properly wear masks and gloves and other safety protocols for working with patient samples. They learned how to work in a biosafety cabinet—a sterile, negatively pressurized workspace—that had been dragged down from a different lab and reassembled on the first floor. 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 week, the IGI volunteers are running the last of their validation studies. That involves hitting the same limits of detection 19 times out of 20, and reproducing positive and negative results produced at other labs. While they don’t have to wait for the FDA to give them a greenlight—labs have up to 15 days to submit their validation data for approval and can technically begin testing patient samples in the meantime—IGI has opted to wait until the review proves their tests work well. “Since we’re new at this we don’t want to be in a position where we have to go back and tell patients their results were wrong,” says Lin Shiao. Once they get the go-ahead, these volunteers will work in three teams to cover two 5-hour daily shifts, with socially distanced “battle lieutenants” that can step up if anyone falls ill. The IGI testing rollout, for now, has limits. They plan to begin on Monday, running a few hundred tests per day, with teams running manual protocols on two of the older PCR machines. Later in the month, once the robots are fully validated, they expect to ramp up to as many as 4,000 daily tests, as needed, says Urnov. To start, only UC Berkeley staff and students will be eligible for testing, while the administrators work to get clearance to start accepting samples from hospitals elsewhere in the East Bay. “We would like to accept community samples,” Schaletzky says. “That was the whole goal from the start.” Other Bay Area medical centers offer high-throughput testing. UCSF, for example, can now process 400 tests a day, says Bob Wachter, chair of the Department of Medicine there, which is enough to meet the health system’s current clinical needs. That has allowed the UCSF testing facilities to begin taking on tests from regional care providers that don’t have their own testing capabilities. But most other hospitals are stuck sending samples off to commercial or state labs with a four- to five-day turnaround. Waiting a few days can be a problem, Wachter says. While doctors wait for tests to come back, they’re often forced to treat any people with respiratory issues as potential Covid-19 patients, just to be safe. That means assigning them to an increasingly short supply of isolation rooms and requiring any health care workers who interact with them to don masks, glasses, gloves, and other increasingly scarce personal protective equipment, or PPE. “It’s not that they’re not getting the right treatment, but they’re taking up beds that we might need,” he says. “The majority when they come back are negative.” 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 Kris Kury, an emergency room pulmonologist and medical director at Alta Bates Summit Medical Center in Oakland, told WIRED that being able to rule out patients more quickly would help hospitals better manage their supplies of protective gear like masks and gloves ahead of a surge in Covid-19 patients. For now, coronavirus-positive patients still make up a minority of people she sees coming in with respiratory symptoms. But until the tests come back, she and other health care workers have to treat them like Covid-19 cases and don protective gear every time they interact with them. “You can’t pull people out of isolation until you know they are negative,” says Kury. Last week, her hospital’s internal testing lab finally came online and is now turning around Covid-19 tests within 12 to 24 hours, says Kury. Before that, she was waiting up to a week for results from Quest Diagnostics, a large commercial lab which a recent investigation by The Atlantic alleged has contributed to California’s current testing backlog. (Representatives from Quest did not return a request for comment.) Since the hospital’s own lab started analyzing results, at the two Alta Bates campuses in Oakland, health care workers went from using 6,000 N95 masks per day to 1,000, according to Kury. “Turnaround time made a huge difference in being able to spare what is becoming increasingly sparse PPE,” she says. There are hopeful signs, at least in the Bay Area, that social distancing is doing the good it was projected to do—that the curve may be flattening. But that doesn’t mean the need for testing is going away anytime soon. “It’s a whole different thing when you look at, does the state or the country have enough testing for asymptomatic or mild cases?” Wachter says. “We’re still woefully inadequate at testing.” To even contemplate getting life back to some semblance of normality will require having fast, accurate tests ready for deployment, to cordon off outbreaks before they flare. Which isn’t to say volunteers like Lin Shiao hope to still be running Covid-19 testing six months from now. Someday he’d like to get back to Crispr. But for now, he’s grateful for a chance to chip in and, despite the 12- to 16-hour days, happy to have a reason to spend less time on Twitter. “My family is in all different countries—Costa Rica, Germany, Taiwan, and here,” says Lin Shiao. This is the first time they’re all experiencing a global threat simultaneously. And the first time he’s felt like all those years spent moving tiny bits of liquid around might actually directly change someone’s life for the better. “It feels good to not sit around and instead do my part to hopefully help curb this pandemic,” he says. WIRED is providing unlimited free access to stories about the coronavirus pandemic. Sign up for our Coronavirus Update to get the latest in your inbox. What's social distancing? (And other Covid-19 FAQs, answered) Don’t go down a coronavirus anxiety spiral How to make your own hand sanitizer Singapore was ready for Covid-19— other countries, take note Is it ethical to order delivery during a pandemic ? Read all of our coronavirus coverage here X Staff Writer X Topics coronavirus COVID-19 public health medicine Maryn McKenna Emily Mullin Maryn McKenna Emily Mullin Maryn McKenna Celia Ford Emily Mullin Amit Katwala 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 "

"3 Black Photographers on Capturing the George Floyd Protests | WIRED"

"https://www.wired.com/story/black-photographers-george-floyd-protests"

"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 Lauryn Hill Culture 3 Black Photographers on Capturing the George Floyd Protests Protesters march to the Georgia State Capitol from Centennial Olympic Park while chanting “Hands up! Don’t shoot!” Photograph: Lynsey Weatherspoon Save this story Save Save this story Save When protests erupted around the world after the death of George Floyd , who died in the custody of Minneapolis police, the threat of a global pandemic calmly took a backseat as a rush of justifiable rage against ongoing racial injustice flowed through all 50 American states and several countries around the world. As protesters took to the streets, it became imperative that black photographers, specifically, capture this moment. Lynsey Weatherspoon, Alexis Hunley, and Darrel Hunter participated in protests in their hometowns of Atlanta, Los Angeles, and London, respectively. Though their images have different backdrops, the trio’s personal experiences connect them and their photographs. Their work not only documents the reality of this historic moment but also demonstrates what they see as their shared responsibility to protect the narratives and moral identities of black protesters in an era of misinformation and sophisticated surveillance. WIRED spoke to them about their experiences photographing protests over the past two weeks. Atlanta Lynsey Weatherspoon is an Atlanta- and Birmingham, Alabama-based documentary and portraiture photographer. In her first attempt photographing a protest, Weatherspoon captures the resilient legacy of a Southern city. Atlanta protesters attend a rally at Centennial Olympic Park in Atlanta on May 29, marking the city’s first protest following the death of George Floyd. Photograph: Lynsey Weatherspoon 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 Lauryn Hill: When you first heard about the death of George Floyd, can you describe where you were and what you were doing at that time? Lynsey Weatherspoon: Well, I was at home because it was a holiday and, just like everybody else, we were all at home. I started seeing the video and photos of it being shared everywhere after it happened. I couldn't pull myself to watch it because there have been too many instances of watching black bodies die right in front of you. For some reason, this one was the one that really punched me in the gut, and I knew we just couldn't stand by and watch this idly. Can you describe a little bit more your reaction to his death? Though we are not surprised by any of it, there was still shock to see and know that George Floyd died in front of a crowd of people at the hands of the police. So, definitely, there was a bit of fear, a bit of rage. Just so much uneasiness that came with seeing what happened. What was the first protest that you can remember in Atlanta? It was the first day, which was Friday, May 29, and we started from Centennial Park and walked to the Georgia State Capitol. People were chanting, of course, holding signs, and there was solidarity amongst the crowd. I decided to stay back at the capitol for a little while because I just needed to catch my breath from walking with everybody, and just seeing and feeling what everybody else was feeling as we were marching. But as soon as I walked back, there was a small group that gathered right in front of one of the statues and started spray painting and giving speeches until the police ran them off. Then we all went back to Centennial Park, and there was another group that was in front of the CNN center. That's when you started seeing the range of emotions that people had around what happened. Speaking of that first night, because I remember seeing it on CNN, how were you feeling when you were seeing that happen in Atlanta? I 'm gonna keep it real with you. I didn't even know it was happening until my grandma called me. She called me to see if I was out there. And I had to zone out from everything, because I was so tired and I was like, I just want to go home, take a shower, and eat dinner. So my grandma called me, and she said, “I was just trying to see if you were out there taking pictures.” I said I was. But now I'm home and she was shocked that I was out there, and I'm like, “What happened?” So that led me to go online to CNN and that's when I saw the police car on fire. I was like, oh my God, I was actually in that vicinity before I left. I was smart enough to leave because you can feel when people are getting riled up and something could happen. Not saying it was going to, but I just felt like it was. I didn't want to see it nor be in the midst of it. You know, you have to think about it; I had equipment, and I'm a woman. So those things are always going to be at the forefront of my mind. My safety is always going to be a priority. Now, you know, I'll let the brave souls who want to be in situations like that do it. But I'm not afraid to say that I went home because I wanted to be 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 Protesters walk in front of a mural painted by Yehimi Cambrón that shows portraits of immigrants who live in Atlanta. “I feel like it is important to walk past that as an honor to black and brown folks who are still experiencing racism and trying to make things right in the world,” says Weatherspoon. Photograph: Lynsey Weatherspoon Related Stories privacy Andy Greenberg and Lily Hay Newman Protests Jason Parham No-Go Zone Aarian Marshall In the midst of Covid-19 and being surrounded by so many people, did you have any reservations initially about protesting? And if not, why? I didn't have any reservation, because we all needed to be there. I do understand that we all should have still been at home, because we're still in the midst of a global pandemic. Yet this instance felt extremely different. You had George Floyd. You had Ahmaud Arbery , you had Tony McDade, you had Breonna Taylor. All of those folks within the range of time that we've been at home, and to be out there protesting, you know, in such anger and such fervor, it meant more than staying at home from a disease. I know that sounds odd, but I feel like most people felt the same way, like there was no need to stay at home and sit down, when we saw what happened. So, I didn't have any apprehension. You know, I tried to protect myself as much as I could. There's only so much we can do at this point, but it was definitely much more important to stand up than to stay 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 Did you get any pushback from friends or roommates or relatives? I didn't tell anybody I was going. Well, I only told one person and that was just to let them know I’m going to be as safe as possible and I want to make sure I call you when I'm going home. So, I didn't stay long enough once I saw the police cars on fire and once people started throwing rocks and other objects into windows and at people. As I said, this is my first time photographing a protest, so I went in very green, yet I understand that my safety is important. So I left when I felt uncomfortable. This was your first protest? My very first time photographing a protest. Wow, I thought you did this on a regular basis. Oh, no. I've never done this. Not only have I never done this, I did not expect this response. It's been very overwhelming, because now so many people are following me, especially on Instagram. I went up from 3,700 or 3,800 followers to 14.4 thousand followers. All of this happened in the span of this week. So I'm overwhelmed. I'm thankful that the world is seeing what we've already seen and known. The world is definitely watching. I've received messages from Germany, Tokyo, parts of Mexico. I want to say Scotland, Barcelona. Everywhere. Everywhere. Can you describe the atmosphere of the protests in Atlanta? It's changed a bit from Friday until the last time I went, which was [last] Monday. I think Friday was much more like it was the beginning of the Atlanta protest, and we’re also trying to get a feel for what we can do in the midst of this. On Sunday, it was similar to that of Friday, May 29, but it was a bit subdued. Monday, I feel like since most people were probably at work, and couldn't make it, there was a smaller crowd but it was still effective. Still, they marched from Centennial up to the capitol. That was the first time I saw the capitol as armed as it was. So that's when I started feeling a bit nerved by it, just seeing police, seeing sheriffs, seeing people in riot gear, you got a crowd who's definitely emotional and vocal about how they feel. Being mindful that they could throw teargas or pepper spray at any time, I'm usually in the back just so I won't experience it. I did experience some teargas on Sunday, and it's not fun. So I just try to be as safe as possible. But the environment—people are still vocal. People are still going out there. I'm sure they went out yesterday in the rain. People are just tired, and people are upset. 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 DeKalb County’s Southern Christian Leadership Conference president, Nathan Knight, speaks to a crowd in front of the Henry Grady statue. In an editorial published by the school’s newspaper in 2019, Georgia State University students demanded Mayor Keisha Lance Bottoms remove the statue because of Grady’s support for white supremacy. Photograph: Lynsey Weatherspoon Can you describe your experience being teargassed? So, on Sunday, when the protesters started taking items out of a construction site to build a wall to keep the police from them, it was around curfew, and the police threw teargas at us, and when you start seeing people run you automatically do the same thing, so while I'm running, you have to stop running because it's so much stress on your eyes. It hits you like nothing I've ever felt before in my life, and you just have to stand there and take it. They had people out there, some of whom were protesters, who were carrying bottles of water to help you flush your eyes out, but it takes so long for it and it just stings; it stings your eyes, it stings your skin. Thankfully, I know enough people who are helpful in how to clean your skin up after those things, but if you didn't know, you're going to hurt yourself. For one, you shouldn't wear contacts to a protest because of the teargas or pepper spray, you can burn your eyes. But, knowing that I needed some fresh water to pour on my eyes and to not wipe my skin to alleviate the burn, that was helpful. For anybody else who was green out there, it was probably worse for them. Definitely not fun, but that's why I tell people, look, you don't have to go to a protest if you don't want to, especially not knowing what could happen. I don't want anybody to experience pain like 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 As a black photographer, can you talk more about the importance of being able to be in the position to cover a protest that deals with injustices against black people? If we aren't covering our own folks, we could possibly get a skewed vision from the predominantly white photographers we already see. Also, knowing that the power of the photograph and the power of being on the ground is just as important, because I'm pretty sure those who are photographing, those white, male photographers who are photographing, they're just probably getting their shot and they're gone. Where the rest of us will probably stay there all night just so we can get the full story. So that is, it is important to not only be a photojournalist, but, you know, equal and equitable in what you actually photograph, you know, give the facts because we see several sides of the story. I think with that, having social media is powerful because so many things happen in real time. If we didn't have that we would still have that skewed view of black people. Flowers placed in a fence on Marietta Street in Atlanta form #BLM, which references the Black Lives Matter movement that began in 2013 after George Zimmerman was acquitted in the shooting death of Trayvon Martin. Photograph: Lynsey Weatherspoon 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 Something WIRED has been reporting on is surveillance and security around these protests. What, if any, steps have you taken to address these problems of surveillance on protesters? That is a really good question and one that has been going around in the photojournalism community as well. Being in the editorial space, it's pretty much an open call to be able to photograph people on the ground. I don't agree with facial recognition, and I feel like it's mostly used when you have instances of people who are throwing objects at people or buildings. So that's why I have a problem when that occurs, because why just use it on people who are in the midst of the protest rather than using facial recognition on police as well? It can be one-sided. I usually try to get the side or the back of people and if someone asks me to take their photo, I will. Also, if someone was to come up to me and say, "Hey, don't take my photo," I most certainly would not do it because I respect that person's decision not to be in a photo. Were there any instances in your life that were triggered by the recent brutal killings of black people. Are you comfortable telling me any of these instances? Yeah, I have one instance that always sticks in my mind. I want to say this happened around maybe 2014, 2015. I went to volunteer at a Christmas event to photograph families, and there were two white, male photographers there. So I introduced myself. They asked me what I did, and I said that my goal was to be a prominent photographer. Basically, the microaggressions were worse than anything else, because [one of them] assumed that I was not capable of doing any of it. So not only just racism, but the microaggression against being a woman. So we can't ever forget that, and being a black woman, that part right there is already, you know, a hill to the climb daily. So when that happened, you know, that only made me want to do it more. Though I've never, you know, I've never been called out my name by a white person. Maybe they have and I just didn't hear it. But that particular situation right there always sticks out to me, because not only women but black women are pretty much told we can't do anything. And it's sad that we have to prove folks wrong time and time again. 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 Where are you finding the energy to continue to put yourself out there to shoot? I'm finding it through rest. I don't go out there on consecutive days on purpose because I am physically, mentally drained after each one. I don't think it's healthy for anybody to keep returning to that trauma daily. You know, weekly is already pushing it, but daily I, I mentally can't take it. So I've made a decision that if I'm not hired to cover it, then I pick and choose when and which ones I actually want to go to. Los Angeles Alexis Hunley is a self-taught portrait photographer based in Los Angeles. When she was 1 year old, the city saw an uprising fueled by anger from the police beating of Rodney King, a moment her neighborhood still remembers well. Hunley’s thoughtful approach to protest photography exemplifies an answer to a question raised in the photo community: “How do we cover protests?” A woman raises her fist at a protest organized by Build Power and Black Lives Matter. Photograph: Alexis Hunley Lauryn Hill: When you first heard about the death of George Floyd, can you describe where you were and what you were doing at that moment, if you can recall? 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 Alexis Hunley: I honestly have no idea. I barely remember what I did two days ago. But, I do know that within that day, I definitely heard about it through Twitter. I know the overwhelming feeling for the day was just exhaustion at a physical and spiritual and emotional level. When the protests against police brutality started in LA, can you walk me through your approach for photographing it? What were your intentions when you were headed out to these protests to shoot? When I went to the first one downtown on the 27th of May, I wasn't 100 percent sure what to expect. There was a Black Lives Matter-slash-Build Power protest, and it was important to me to be there because I felt like I needed to do something. I needed to show my support. I needed to be a part of documenting something that is happening to black people, specifically as a black person, because too many times we are being documented by voyeurs. It felt like going to photograph was my contribution and my way of supporting, and that was kind of the mindset that I went into it with: of being honest and being respectful and creating images that aren’t that sort of gross, voyeuristic, just focused solely on things like our pain and our trauma. So in your last statement, just so I can clarify, you were trying to make sure you weren't taking voyeuristic images that were just showing black people's pain and trauma? You were trying to get a more fuller picture, is that what you were saying? Let me rephrase. I am trying to say this as delicately as possible. I get frustrated seeing images only created by non-black people that concern black stories, particularly around black suffering. I think too often they can be callous, and they can be too centered on our pain and our trauma. Like, showing the whole story is important, but there is more to us than just us being killed and harassed and beaten and murdered, and I'm tired of only seeing images like that. I bring my own understanding and sensitivity as a black woman with me when I'm shooting in a way that a non-black person can't. Police officers stationed in downtown LA near City Hall. Photograph: Alexis Hunley 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 in the midst of Covid-19, did anyone push back on you going? Yeah and it wasn't even about me. It was my mom being a mom. She was upset, and I was getting ready to head out. She was like, “You get on me and your dad every day about going to the store, leaving the house because of this pandemic, but you're gonna go to a protest?” We had some words back and forth. I was like, “You going to the store to get fresh fruit every other day is not the same as me going to protest and/or take photos. These are historical moments. I understand it's risky, but I'm still going to go do it.” They've come to terms with it. My father will drive me and drop me off and be ready to pick me up at any point. They still support me, even though it worries them a lot. My mom is the most concerned about me being detained or injured or killed. Which makes sense. My cousin was detained. It's all of these simple fears, but I still feel like it's something that I need to do. So, I'm here and I'm doing it. A woman wearing gloves holds the hand of a young boy, who is also wearing a mask as protection from Covid-19. Photograph: Alexis Hunley 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 was the demographic of the photographers? Were most of them black? Were they mostly non-black photographers? It is overwhelmingly non-black photographers, and it's a little difficult to tell sometimes, because so many people have DSLR cameras or little mirrorless cameras, and I'm not 100 percent sure if they're photojournalists. But the protests in general, it's been overwhelmingly non-black photographers shooting. I noticed, even when I went yesterday, the crowd was overwhelmingly not black, which I thought was very, very interesting. I am always very good at picking out brown faces, black faces in any crowd. But, I had to search a little bit, which I thought was strange, but also encouraging. It still made me uneasy. It was a weird experience, but I noticed that on Fairfax and Third, specifically, there were a lot of white, male photographers who were not wearing masks, smoking cigarettes. I have a photo of some guy smoking a cigarette without a mask on, and it infuriated me because I know that you're not there to support and protest for black lives. You're there for your own voyeuristic needs and wants and desires. You're going to throw this up on your Instagram or your YouTube channel or whatever you're going to do. It enraged me that, like, you're willing to put more people's lives at risk by not—you can't even wear a mask? You are most likely creating images that are exploitative in some fashion and then you also won't wear a mask. It's just a double slap in the face. Were there any more physical obstacles that you ran into while you were out there during the protest? One thing I noticed was that there were far too many people bringing dogs, and not even big dogs, little dogs. I watched a French bulldog almost get trampled because the cops … a white man threw a bottle of Ciroc into the air at the police from behind. So in front of the line it was mostly black people, and he was back in the middle somewhere and he tossed it at the police. So, you know, instantly everybody's ready. They're ready to just start beating people, and so I don't remember 100 percent if they started spraying pepper spray, but everybody started running and I almost ran over somebody's dog and then witnessed another dog almost get trampled, which was a very unexpected physical obstacle. I must say, I expected police to show up and I expected to be boxed in, but I didn't expect that to become a thing. I saw people running with kids and like, it was odd. 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 Yeah, I bet. Especially because I can't imagine how big it was in LA. I've never seen that, like the energy that was coming out of these hundreds of people walking from the Beverly Center to Fairfax and Third was indescribable. They just kept coming and kept coming at one intersection. There were two protesters who stopped to direct traffic so that the cross street wasn’t impeded. There were a lot of moments where I felt very hopeful, but also very emotional, seeing people handing out water bottles. I saw a woman yesterday giving out squirts of hand sanitizer throughout the crowd. People with extra masks. I saw a wagon filled with bottles of teargas neutralizer and a lot of those folks are not black. A lot of black folks were distributing supplies as well, a lot were just protesting. But it was really, really, I don't want to say powerful—I'm trying to think of the right word here—encouraging almost, to see so many people stop what they were doing to provide direct aid and support to people who were protesting was really amazing. A spray-painted wall in Los Angeles. Photograph: Alexis Hunley 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 about any mental obstacles? I know that without the anxiety and the fear that comes around contracting Covid, around being shot at and injured, blinded, killed, being teargassed, I would have some different images. Those factors make it difficult for me to approach certain situations to get shots that I want. They make it difficult for me to stay longer than a certain amount of time. Even outside of the shooting, they make it difficult to come back after and crank photos out and edit and answer emails and even just interact, not normally, but interact outside of everything that's going on. It's hard to just have different or normal or non-death-related conversations. When you were out there, were there any moments that you saw with your eyes but refused to capture them with your camera or you just couldn't emotionally take? Were there any moments like that? I can think of one specifically downtown. There were families of victims who've been killed by LAPD and other LA law enforcement agencies. And this one woman was speaking, and she was crying, and after the crowd started to move and disperse to a new location, I noticed another woman, I don't know if they were family or not, walked up and they were hugging and crying in the street together. I think it would have been a powerful image. I can still see it in my head. But it felt more important to let them just have that moment, if that makes sense. It felt wrong to try to take that moment with me. It wasn't for me. Why did you ultimately decide to blur or exclude faces? I'm sure there are probably maybe other outlets who wanted to show the faces? There were, and I had to turn some of them down. It's not something I'm willing to compromise on. I was explaining to a friend after learning about all of the deaths of different Ferguson activists and protesters that I wasn't willing to be complicit in the demise of another black person because of a photograph for a couple hundred bucks, for some likes or some follows, for an assignment. It was a nonnegotiable for me, period. Like, I don't ever want to knowingly have a hand in the death or the murder, the beating, the harassment of other black people. I won't ever budge on 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 Protesters walk from the Beverly Center to Fairfax Avenue and Third Street in Los Angeles on August 30. Photograph: Alexis Hunley And did you use an app? What did you use to blur the faces? I used Photoshop, and then within a few days I started learning different techniques, so I just kept adding layers of different ways to obscure. Removed all my metadata. Actually, that was one of the things I needed to do. There's a new video about how to do it, because I'm not super technical. I taught myself how to shoot and edit and do a lot, and I know that there are gaps in my knowledge, but that's part of what I'll be doing today is just going online and looking at other ways to remove metadata and secure the identities of protesters, specifically black protesters, as well as I can. That's very, very important to me. Do you think the way you blur out these images and the way you shoot should become a standard as to how photographers start to cover these protests? I do. We live in a surveillance state, and the government has shown that it will do whatever they deem necessary in any situation. I got really upset when I saw that the DEA had been authorized to do covert surveillance on protesters. It's completely wrong, and it's terrifying. I do believe that we should be obscuring the identities of protesters, specifically black protesters, during these protests happening right now. You know, I am not opposed to blurring the identity of protesters at any protest in the future, because our government has shown that they will find you and they will do whatever they deem necessary to quell your protests or your grievances. So it just makes me feel safer. London Known for his fashion work, Darrel Hunter is an international photographer who calls London his home. Hunter’s style of shooting fashion is seen in how he also documents events. Each of his subjects are uniquely composed to help translate the story he is trying to portray. 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 woman wearing gloves lowers her hand after participating in a chant. “You can see it's really crowded, we're in the middle of a pandemic, and she has gloves on, but she's still here. She's had enough,” says Hunter. Photograph: Darrel Hunter Lauryn Hill: Do you see any similarities between the way the US is struggling with its criminal justice system and things going on in the UK? Darrel Hunter: I would say it's similar. It's not an issue to the extremity that we're seeing. It's not being played out in front of us, but there are still several instances where black boys will be more likely to be stopped and searched. There have been people that have been arrested for no reason. People who have been victims of police brutality, have been killed by police. It's still something that we have to deal with. We're not exempt at all. There's definitely distrust out there in the criminal justice system within the black community. I don't think we’re exempt. It’s just maybe different measures or different ways that it's played out and addressed in the US as opposed to the UK. When the news broke of George Floyd’s death, where were you at that time and what was your reaction to it? I remember I was at home and I had just come back in, and someone sent me a video, and they prefaced to me,“You don’t want to watch that.” I read and understood what had happened, and, unfortunately, it's not the first time that I've seen or we've seen something like that, but I did finally watch the video. It was heartbreaking, like I was, for most of that week afterward, I was completely unproductive. I couldn't think about anything else. It was emotionally draining, it felt that that had happened to someone close to me. It was seeing someone that looked like me being murdered before my eyes in such a cold and inhumane way, I just, yeah, I was, I wouldn't say broken, but it really affected me and just brought back memories of other things that I'd seen. Even recently, with like Ahmaud Aubery and Breonna Taylor, like so many other things that had happened. Then, on top of that, the fact that we were all dealing with the pandemic and everything and then to see this in the midst of that happening was just really upsetting. 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 Protesters surround Star Wars actor John Boyega at a rally on racial injustice in Hyde Park on June 3. Photograph: Darrel Hunter Can you describe to me the atmosphere that you experienced when you were at the protest in London? First of all, it was overwhelming. It was very emotional but also very powerful. When you first arrive, you're not sure what to expect. You don't know whether it's going to be, from our side, if it's going to be met with hostility, or if it's going to be peaceful. Like what is happening? Being there, seeing people of all races, all ages coming together for a common cause, or people that are agreeing that not just this, but the whole system is broken and they don't want to be a part of it, hearing people speak and rally together, it just feels, for me, different from other protests that I've been to. It was so different. There were so many people. It was powerful, and it was also very emotional. After I finished, I came home, and I needed to take some time just to decompress. Being a part of it and just wanting change or having the whole thing of I'm literally fed up and I'm going to use my voice; I'm going to use anything I can to act in change or to educate people or to push for this rather than just sitting back. It was an air of strength and solidarity throughout the whole protest. 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 Can you talk about a personal experience you've had dealing with racism? If so, how have these recent events triggered that? There are several. I'd fully be here all day trying to think of all the times. And I'm not saying that I, personally, am the only person that's been oppressed by my personal experiences with comments that people have made. It's a lot. Even just recently, I had a nephew who is now 19, and earlier last year he was with his friends, they were just outside of their friend's house, and a police van came and basically just searched them all and said that they had reports of somebody with a knife fitting his description or one of their friends’ descriptions. Of course there was no such thing. Handcuffed them all. Told them to get on the ground. When they refused, they basically threatened them with batons and basically put them on the ground, and one of the police officers was actually kneeling on my nephew's neck and he was struggling and saying, “Look, I can't breathe.” Like, this was uncomfortable. I mean, fortunately, thank God, it didn't end the same way , but for me it was like how different that story could have been. How many times has this happened? How many times have I been driving and been stopped for no reason? "Oh, someone fits your description" or "Well, we heard about cars like this being stolen." It's frustrating, because you know that they're only doing it because of the color of your skin. You have that anger and you want to react but then you basically don't want to end up, unfortunately, like George Floyd. But then you have a situation where things turn into death and it makes you think yes, I'm grateful that my situation didn't turn out that way, but why do we have this where they can just treat you like you don't matter, like you have no importance, and can just kill you? And you feel so powerless. You think about all of the other instances where people have made even comments which they think are fine about the color of your skin or about your hair. I remember when I was quite young out of school using house phones at one time and I was speaking to this girl. I think we went to school together or something, but it was a friend and she was a white girl, and one day I called her house and her mom answered the phone and asked me if I was a black man. And I’m like, yeah, I'm black. And her response was, well, basically, “We don't want any blacks in the UK so you should go back where you come from” and then hung up the phone. Just things like that, even as a kid. All of these things start to come back to you when situations like this happen. 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 Police officers barricade a street leading to the Ministry of Defense as protesters march from London's Hyde Park to the prime minister’s office. Photograph: Darrel Hunter When you were out in the protest, you had a camera, so people probably could have easily regarded you as a person of the media—and you're also black. If there were police officers out there monitoring, did the protests ever get dangerous? And if they did get dangerous, did you find yourself in a dangerous position because of who you were or how you looked? You know, I mean, there was a police presence out there, but I didn't feel in any danger at any point. I didn't see anyone being violent. There were a lot of people out there, and they did cover a large area, but I didn't see any form of vandalism or abuse or anyone clashing with the police or anything like that. It was basically controlled for the most part. Were there any moments that you saw before taking the photo that you actually didn't proceed on taking the photo because it seemed too sensitive or too invasive? Were there any moments like that where you refrained from taking a particular photo? 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 think there was probably one moment. I don't know if the news reached the US, but there was also recently a transport worker. She works for the railways, named Belly Mujinga, and she died after someone who had coronavirus spat on her while she was at work, and then the courts came back and ruled that they weren't able to charge the person. The person got away, whereas before that, there was somebody who had done a similar act with a police officer and they ended up with 12 months in jail. So, one of her relatives was there, and while the protest was going on a lot of people were also holding signs of her while [the relative] was sitting down, and she was really distraught, crying and looking really broken. I saw other people taking pictures, but I didn't feel comfortable in that moment, like pressing a camera in her face, so I waited until later, until there was a different time to try and capture a picture of her. But to me, it's not also about “Hey, I want to get a great photo, this is an opportunity,” it's also respecting the space that people are in, because different people, you have no idea what they've been through. As a black photographer, can you talk more about the importance of being in the position to cover protests like these that revolve around black people? I think it's extremely important. And, I mean, I'm not saying that other photographers can't cover it, but I feel that as a black photographer, you can then control the narrative and show a different side. Like I said, most of the black photographers that I know who are covering it, even if they weren't photographers, they would be at the protest, they would be involved. If it’s a subject that is close to their heart. It will give you a different perspective on it. If you're just there as a job, as an assignment, and you have no connection, you will photograph it in a different way, and you would help to spread a different narrative. So whereas a black photographer may be looking at pictures of solidarity, of people marching or shouting out, holding signs, trying to document moments where the police have been over-forceful, someone else may just be looking at, Oh, hey, look! This person was doing graffiti or they threw something at the police. It creates a completely different narrative. For example, there was a picture that I took, and I know a few other black photographers took, of the man who had a white van which he had spray-painted with Black Lives Matter on it, drove it to the protest, and was standing in the middle and allowing other people to climb up his van. And he was part of the protest, and we took that picture and then someone else took that picture, and the tagline for the article was “Violence and Vandalism at the March” and how protesters vandalized this van. The guy was like, “What are you talking about? That's not even true. That's not what happened.” This guy did it to his own van. I do feel like as a black photographer, it's very important for black photographers to be the ones telling this story and to document this so that they can control the narrative and present a real image of what is happening. 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 Four protesters station themselves on top of a building next the prime minister’s office. Photograph: Darrel Hunter I'm from Birmingham, Alabama, so we often talk about the 16th Street Baptist Church bombing that killed four girls and how that event has been passed down through generations and it still shudders through our soul. Is there any moment in history like that that you grew up learning and has been triggered because of these events? I mean, again, there were so many, but even over here, we had when I was younger, there was a young black boy by the name of Stephen Lawrence who was killed by these four or five racist guys. The parents were fighting for years for justice. There were marches, there were campaigns and so many people that tried to fight to this day for justice for Stephen Lawrence. There's another black boy, Mark Duggan. Basically, he was in a car and the police stopped him and literally just opened fire on him and killed him. Things that you've seen with like the civil rights movement during like church bombings, people walking into church and shooting people. All of these instances make you feel that we haven't gotten anywhere. That we're now still dealing with this, and not only dealing with it, having to explain to people why it's an issue and how it affects us. It's traumatic. Growing up, we're watching it or it happens in our area, but imagine being one of these people actually videoing it or who were on the street when it happened. That is literally going to cause so much trauma within the community that is not dealt with, and we are kind of just expected to be strong and continue and just go on until something else happens. I feel like, for me, and I'm sure for the majority of black people, all of these things are so traumatic in a way that it touches all of us in some way. 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 Here in the US, there's been a big conversation in the photo community about surveillance, and it's something that WIRED has been reporting on throughout the protests. I don't know if surveillance is a big issue in London, but does the issue of surveillance affect how you shoot or how you manage your photographs after you shoot them in terms of erasing metadata? With the majority of my images, especially if somebody is doing something that was deemed illegal or something that was controversial, I wouldn't capture it. If it was something that I did capture, I would never put that out there. So for me, the majority of the images that I captured, it was people that had face coverings. The people that you can see their face, I would ask for their permission. The whole point of me capturing images is not to put people out there or to get them in trouble. The minute I arrived at the protest, I did put my phone straight on airplane mode. I turned off my Face ID, turned off my location services. I feel that it's a duty. Because I feel like the protests here have been slightly different. I haven't had to worry about people being incriminated or people being investigated afterward for being at a protest. But, yes, definitely, I do think it is a duty of all photographers, should they be capturing something in an area where people are, say, jumping a barrier that they shouldn't or they are breaking down the security camera. If you're capturing that moment, yes definitely scrub your metadata and take a screenshot of the image after you've taken it so that it's now a fresh image, or make sure their faces are blurred out. It's not about incriminating anyone just for a sake of a photo. A protester wears a black beret and turtleneck, an attire Hunter says is reminiscent of “revolution.” Photograph: Darrel Hunter 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 Throughout all of this, coronavirus is still considered a global pandemic, and I was just wondering, did you have any reservations about catching coronavirus before going out to the protest? Honestly, I didn't. I spoke to friends and family. And I said I'm going to the protest. I just let them know, since obviously I may interact with them in the future. I said I'm going to take every precaution. I'm going to wear a mask while I'm out there. I had hand sanitizer with me. The minute I got back home, I took off all of my clothes, showered immediately, put everything in the wash. So my thing was I was going to take precautions. I don't think I could let that hinder me from going to the protest. Yes, it is serious. Yes, it has affected many people. However, this issue is also very serious, and this predates coronavirus. We could make several excuses, say coronavirus wasn't around and it was raining. People could say, “I'm not going to protest today because it was raining.” I feel that if they only did it because it was convenient or because it felt safe, there would be no point in doing it. The whole point of a protest is to go against the grain. So, yes, I wasn't worried. I took all the precautions I could and made up my mind that I was still going to go. Was there anything that you felt that I should have asked you that I didn't or anything else you want to say? The thing that I did like about this was the majority of the people protesting were black. However, people that were there from other nationalities, it was supportive. Sometimes I've been to or seen protests where it becomes an issue and it's been led by someone else. The thing I liked was that it was being led by black people. It'd be black people speaking, and then people from other nationalities were there supporting. So whether they were Asian, whether they were white, whether they were Arab, they were there, and it was more of “we're here to support you, not try to make this about us … we're here to support.” That's how I feel it should be. It's just like if it's a cause that's for women, I can't be the one leading it. I can support and I can speak out, and I can help in any way I can, but I can't be the one standing at the forefront telling women what to do or telling people what to do for women. Updated 6/11/2020 3:15 pm ET: This story has been updated to correct that Hunley said "documented by voyuers," not lawyers, as previously stated. What happened when I switched from Mac to Windows How Kickstarter employees formed a union 5 simple ways to make your Gmail inbox safer Quarantine has transformed not-TV into essential TV Let's rebuild the broken meat industry— without animals 👁 What is intelligence, anyway ? Plus: Get the latest AI news ✨ Optimize your home life with our Gear team’s best picks, from robot vacuums to affordable mattresses to smart speakers Photo editor Topics protests Photography Angela Watercutter Jason Parham Marah Eakin Angela Watercutter Alex Miller Kate Knibbs Amit Katwala Elizabeth Minkel 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 Human Cell Atlas Is Biologists' Latest Grand Project | WIRED"

"https://www.wired.com/story/the-human-cell-atlas-is-biologists-latest-grand-project"

"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 Megan Molteni Science The Human Cell Atlas Is Biologists' Latest Grand Project Casey Atkins Save this story Save Save this story Save Aviv Regev speaks with the urgent velocity of someone who has seen the world with an extraordinary new acuity, and can’t wait for you to hurry up and see it too. At a meeting of 460 international scientists gathered last week in San Francisco, the computational biologist bombarded her audience with a torrent of results from her lab at the Broad Institute of MIT and Harvard, where she is pioneering powerful new tools for understanding what we humans are really made of—and what makes us fall apart. “Where do disease risk genes act?” she fired into the crowd. “Which molecular communications are being disrupted? Which cell programs are being changed? These are the next generation of questions we can now ask.” For centuries, scientists like Regev have known that clues to our elemental humanity were hiding in the basic unit of life: the cell. The cell has captivated scientists ever since Robert Hooke stuck a sliver of cork under his microscope in the 17th century and observed an “infinite company of small boxes,” drawing a parallel between the structures he saw through his instrument’s eyepiece and a monastery’s spare rooms. But only in the last few years has the technology existed to investigate the internal workings of individual cells at scale. Using these methods, scientists are now embarking on one of the most ambitious efforts in the history of biology. Dubbed the Human Cell Atlas, the project intends to catalog all of the estimated 37 trillion cells that make up a human body. Led by Regev and Sarah Teichmann, the head of cellular genetics at the UK’s Wellcome Trust Sanger Institute, the international consortium aims to assemble much more than a laundry list of cell types. By decoding the genes active in single cells, pegging different cell types to a specific address in the body, and tracing the molecular circuits between them, participating researchers plan to create a more comprehensive map of human biology than has ever existed before. If successful, this map will knit together information about how cells organize into tissues, how they communicate, and how things go wrong. Such a resource could one day have huge implications for understanding and treating human disease. Just how huge? Last week’s meeting offered a brief, but dazzling glimpse. It was sponsored by the Chan Zuckerberg Biohub , a two-year-old biomedical research center backed by Facebook founder Mark Zuckerberg’s philanthropic investment group, CZI. The Biohub’s co-president, Stephen Quake , also a Human Cell Atlas organizer, welcomed a parade of the project’s founding members to the stage to share their latest work. Ed Lein, a neuroscientist at the Allen Institute explained how he’s spent the last two years building a taxonomy of all the cells found in one tiny patch of the human brain. By sequencing the active genes in those cells, his team has already identified 80 different kinds, including a totally novel neuron found only in humans. “We see that basically everything is rare,” said Lein. And that’s just in one corner of the brain. Understanding how those neurons network across the rest of the organ will require the work of many other labs. “This problem is so enormous that it necessarily has to be a community effort,” Lein told WIRED in an interview last year about his role as a member of the Human Cell Atlas’s brain working group. 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 Some Atlas participants, like Lein, are deep-divers. Sten Linnarsson at the Karolinska Institute in Sweden takes a broader, more shallow approach. His lab is using gene expression measured across time to observe how quickly cells take on new identities in developing tissues. By capturing snapshots of cells every few hours, and seeing how their gene patterns change, it’s possible to predict what they’ll be doing in the future. A lot of Linnarsson’s work to this point has been done in mice, but as scientists like Lein add more and more human brain data, Linnarsson can start applying his ideas to humans. “We expect to be able to make large branching trees tracing the developments paths of cells in the human brain,” said Linnarsson. These findings are already transforming biology as we know it. But it’s results from Regev’s work that perhaps offer the best example of how the Human Cell Atlas might revolutionize medicine as well. In a recent pair of studies published in Nature , Regev and her collaborators at Massachusetts General Hospital discovered a new, rare type of lung cell, with similarities to salt-balancing cells found in the gills of freshwater fish and frog skin. Concentrated in this unique cell was activity of the CTFR gene, mutations to which cause cystic fibrosis. Regev now believes it probably plays a key role in the disease, breaking the widely held view that a much more ubiquitous cell type was responsible for expressing the disease-causing gene. Imagine you wanted to design a drug or a gene therapy to target such a gene. Knowing where it’s doling out damage is essential to making a medicine that’s effective with the fewest side effects. Cystic fibrosis is fairly straightforward—one gene causing chaos in one organ, the lungs. But other diseases are much more complicated. A reference map of what all the healthy cells in the body look like would be invaluable for comparing with diseased tissues to see where things went wrong. This is one way the Human Cell Atlas could lead to medical breakthroughs. Another is matching cancer patients to the right treatments. A promising new class of drugs, called checkpoint inhibitors , gives the immune system free reign to attack tumor cells. But it doesn’t work for everyone; some people appear to develop resistance. By looking at gene expression in melanoma cells taken from patients before and after treatment, Regev’s team discovered that some people’s tumors were impervious from the get-go. Despite having a mutation that should have made the drug effective, some tumor cells had flipped on a set of resistance genes. And wherever they appeared in the tumor, they blocked immune cells from getting 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 With this knowledge in hand, Regev’s team tested whether you could reverse that resistance, by combining the checkpoint inhibitor with drugs that are known to manipulate those genes. In mice, they saw a dramatic effect. The unpublished work is forthcoming in the journal Cell , and her collaborators at the Dana Farber Cancer Institute are now pursuing clinical trials to assess the efficacy of the combined therapy approach in humans. The Human Cell Atlas will be a place to collect all these genetic programs that can disrupt treatment. The oncology space is moving quickly to adopt routine sequencing to match patients’ unique tumor mutations to targeted medicines. The next step is screening for how a patient’s cancer cells toggle genes on and off in ways that interact with various medicines. “I like moving fast,” says Regev, who launched her own company, Celsius Therapeutics, in May, to help advance her findings more quickly into medicines for cancer and autoimmune disease (it is not involved in the clinical trial mentioned above). But she’s cautious to separate that business from her academic work and role at the Human Cell Atlas, where her job is to convince people to share their hard-earned data, in which important biomedical discoveries might be lurking. “From the beginning we have designed this as a public good and an open resource to enable science around the world,” says Aviv. It’s meant to be a generally useful reference for how healthy tissue behaves, like the human genome was for DNA. When it comes to medicine, the real power will come from combining that reference atlas with data from diseased populations, she says: “That’s where the interesting translational discoveries will be, much of which we cannot yet even imagine.” In some ways the Human Cell Atlas is Regev’s way of encouraging the world, “Come on, hurry up, imagine them already.” Kelly Slater's artificial surf pool is really making waves The hearing aid firm taking a page out of Apple's playbook Bump-canceling beds promise super smooth bus rides PHOTO ESSAY: Giant family portraits with Vladimir Putin How to use Twitter: critical tips for new users Hungry for even more deep dives on your next favorite topic? Sign up for the Backchannel newsletter X Topics Biology genetics medicine Genomics biotech gene therapy cells Max G. Levy Emily Mullin Erica Kasper Emily Mullin Emily Mullin Celia Ford Elizabeth Finkel Maryn McKenna 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 "

"Coronavirus and the Future of Telemedicine | WIRED"

"https://www.wired.com/story/coronavirus-future-telemedicine"

"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 WIRED Staff Business Coronavirus and the Future of Telemedicine Photograph: Peter Dazeley/Getty Images Save this story Save Save this story Save On Friday, WIRED’s editor in chief, Nicholas Thompson, hosted a Facebook Live with ER doctor turned cofounder Caesar Djavaherian, who now serves as the chief medical officer of his telehealth company, Carbon Health. This was the first in a series of four conversations presented by Salesforce in which WIRED will explore what the coronavirus pandemic means for the future of business, education, technology, and health. Hundreds of readers tuned in, and we took questions from viewers in real time. The conversation has been lightly edited for clarity. Nicholas Thompson: Hello, I'm Nicholas Thompson, and I'm the editor in chief of WIRED. Today we're going to be talking about the future of telemedicine with Caesar Djavaherian. Caesar is an emergency room physician, has been for many, many years. He's also one of the founders of Carbon Health, which is building one of the first at-home coronavirus tests. He's been at the front lines of combating the coronavirus since the very beginning in the Bay Area. He's on the front lines of helping to build the technology to fight it. He's on the front lines of figuring out the future of telemedicine. So, Caesar, good morning. Caesar Djavaherian: Good morning. Thanks for having me. NT: Let's start with a little bit about you. You started as an emergency room physician. And at some point a couple years ago, you made the decision that the most important thing you could do is try to make medicine more efficient, particularly through telemedicine. Tell me about that choice and a little bit about that transition. CD: I started out as an ER doctor. I actually trained in New York City, where the pandemic is hitting hardest. And just like many doctors who practice medicine, I became a little bit disenchanted with all of the administrative burdens that physicians have to deal with in their everyday lives. And I wasn't satisfied with the answers to my questions about why we do things this way. I was told, “Well, we always do it this way,” or “This is the way we've traditionally approached X type of health care.” And I thought, you know, in 2013, 2014, 2015, with incredible technology developing in every other industry, why couldn't we take a step back on how health care was being delivered? And really ask ourselves, if we were to create a brand-new health care system today, what would that look like? 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 part of it is that you can do so much in person. But there's a lot you can do actually online, outside of the clinics. And being able to take a step back from it, and asking that question, and really trying to strip down health care to its bare bones, almost like, you know, how Elon Musk talks about first principles. So what are the first principles in health care? It's really a provider and a patient and some work that has to happen around that interaction. And once you can break it down to those bare bones, you can then start to build technology that can enable that experience to be much better from the patient perspective, and, frankly, much better from the doctor perspective. NT: So, you're trying to beat Elon Musk without the tweet storms, right? CD: Well, I’m not very good at tweeting. NT: We have a quick first question, which is ‘What is telemedicine?’ Got a coronavirus-related news tip? Send it to us at [email protected]. CD: Ah. So, you know, the definition of telemedicine is fairly broad. It's anything from taking care of a patient's needs through the telephone—so just the old fashioned way—to having video interactions with your patients, to actually having video interactions with your patients assisted with devices. So whether it's loading information from your Apple Watch, or using a remote stethoscope like Eko Health has built or some of the at-home products like blood pressure cuffs, connected scales, that sort of thing. And there are lots of companies that have gone into this field under the umbrella of telemedicine. But frankly, it means different things to different people. NT: Ever since the internet was invented, I've been hearing stories about how the internet will allow doctors in rural communities to treat many people. But it hasn't taken off, really, maybe until now. And the differences are, as I understand it, we have much better bandwidth, we have better computers, we’ve got better cameras, we have Zoom, we have wearable devices, which give us more data. What else do we have? What else do we need? CD: Oh, it's a good question. So first of all, big shout-out to Zoom, because the video quality has gotten much better under the Zoom platform for telemedicine providers. I think without trying it, most patients didn't think they’d be able to get their questions answered. So they've maybe tried telemedicine as an early adopter, tried to onboard, connect with their providers. And what I've heard from patients, actually, is that that was an incredibly frustrating experience for them. They'd much rather just go to a place where they know they can get care. And unfortunately for a lot of them, that meant the emergency department, and that's where I would see them. So patients were showing up with presentations that really could be taken care of at home through telemedicine or, frankly, wait till the next day to see their primary care doctors. And so, one thing that's in place, to your question, is that patients need to try it. And I think this pandemic has really forced a lot of us to try telemedicine for the first time. 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 what we need more of is to have a broader list of actual ailments that we can take care of virtually. So today, if you're a young woman with urinary tract infection symptoms, that's a perfect case for telemedicine. Now, if you have back pain and fever and vomiting, that's probably not the right case for telemedicine. It might be in the future, depending on the connected devices that patients have in their homes. NT: And so then, with Covid-19, there are a whole bunch of interesting steps where telemedicine can play a role and a bunch of steps where it can't. So the initial question of: Should I go see a doctor? Should I get a test? That not only can be done via telemedicine, it should be done on telemedicine. Lots of people who weren't positive have gotten infected by going into a hospital to see whether they should get tested. So consultations, definitely. Testing you can't do via telemedicine, but you are working on an at-home test, which I want to talk about for a second. And then there are other stages like treatments—you can't have a ventilator run in your home. So is it the right framework, that with every kind of illness, there are steps where telemedicine can be appropriate and steps where it's not? CD: Yeah, well, I think we shouldn't try to fit a clinical scenario into the telemedicine box and just try to use telemedicine because it's there or because we want to. The health care system is incredibly complex, and the number of different patient presentations is incredibly diverse. We should use telemedicine in areas where telemedicine works and is effective and can resolve a patient's problems with the same clinical standards as an in-person visit. But then there are instances where having a patient come into the clinic or into the hospital is more appropriate. And frankly, that's really the angle that Carbon Health has taken, which is that, yes, we do have telemedicine video visits. We can do a lot through that, but we can then connect them into our own clinics, or into a partner hospital, so that from the patient perspective, they're getting the best care possible for every instance. You’re absolutely right, there are telemedicine companies that do monitoring of patients in the intensive care unit so that one doctor can actually see multiple patients at the same time through their monitors. They can look at the vital signs, make recommendations to the nurses, but they can’t perform procedures, they can't put a patient on a ventilator when they need it. So there are limitations out there. And I think, again, going back to some first principles, we know that this is a tool in the toolbox, but we can't have it siloed off from the rest of the health care ecosystem, because we know that there are too many things that need to happen for a patient to be well cared for. And this pandemic has highlighted all of those. Read all of our coronavirus coverage here. So in this pandemic, you have a disease that is deadly in certain populations. If you're male, 70 to 80 years old, with diabetes and heart condition, this is a very deadly disease. If you're a younger woman, you might just have very mild symptoms, like not being able to taste or smell. And the reason that telemedicine kind of rose to prominence within this pandemic is that we needed to very efficiently risk-stratify a huge percentage of the population, not just in the US but around the world. And so you can see that for some people, having information about coronavirus was sufficient. For other people, being on a ventilator was the care that they needed. So how do you organize all that? Well, we think through technology you can inform those who need the information and keep them away from the health care system. For a subset of those people, you can provide some care, whether it's symptom control, or guide them to the right testing facility or the right clinics. And then for a subset of those people, they'll need more advanced care and you want them to go to the emergency department or the hospital, but you want them to get there having informed the staff before they arrive so that they can be protected when the patient hits the door. 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 Now, I know in New York the assumption is that nearly everyone has coronavirus, and that's clearly an unfortunate event. In the rest of the country, the frontline providers mostly assume that patients don't have coronavirus. And so when the patient hits the door, if they're given the heads-up that this patient is at risk for it, they can better protect themselves, they can be more on guard and prevent transmission further, not just to the health care workers but then to their families and the rest of the community. NT: An amazing question came in that is so dark and cynical that I wish I had thought of it myself. The question is about the business model of telemedicine. Clearly, one business model is: I call Caesar and health insurance pays Caesar. Or I pay Caesar directly, if you give me a consultation or some treatment. Somebody asked: Is there a business model where pharmaceutical companies can insert ads during a telemedicine consultation? Is that something that has come up or that you have seen? CD: You know, Practice Fusion was a health tech startup that created an electronic health record that doctors could use for free. But in exchange for that free software, they would show advertisements for pharmaceutical products. And that company, unfortunately, I think blurred the lines of ethics and clearly has gotten in trouble with what they've done. There's a recent penalty that the company ended up having to pay. I haven't seen that same model in telemedicine, and I hope I never do. The idea that you can monetize and profit from a doctor-patient relationship is, frankly, disconcerting. And clearly it's not at all within our business model, nor in any of the current telemedicine companies’ business models that I've seen. I think that the industry hopefully has learned a big lesson from the rise and fall of Practice Fusion. NT: So let's talk about a product that you have, which is the at-home coronavirus test. You prepared it, you had some interesting scientific way of doing it that wasn't being done by others. The FDA said, “Wait, you can't do this right now.” You're in the process of negotiating with the FDA. I won't ask you to talk about that. But tell me how your test worked, what was different, and why it was optimized for personal at-home testing. 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 CD: So we had our first coronavirus patient come into our clinics, or a highly suspicious coronavirus patient, on January 23, before all of this started to happen. And from day one, we mobilized our company to try to address the needs. We also realized that effective testing wasn't available even to public health officials. So in retrospect, now that I'm reading more reports about it, we were unfortunately not prepared for this pandemic, even though we had seen other countries go through it. So the idea was: OK, we have a disease that's highly transmissible, that's putting not just our health care workers at risk but also using up all of our resources when it comes to personal protective equipment, and also has put a lot of strain on the supply chain for just the basic testing components. We also realized that the test itself is frankly old. You know, when I was in college, I used the RT-PCR technique in my research endeavors, and that was 25 years ago. So, again, going back to the first principles, what is it that we need to get accomplished? And what are the different ways we can accomplish it? The at-home test doesn't rely on the typical supply chain. It uses a different type of swab. And the idea of being able to administer the test within the patient's house, where they're not at risk of infecting others, was incredibly compelling to us. So we worked with our lab partner to identify a workflow where patients who are at risk for coronavirus infection would be evaluated by one of our doctors at scale. We can look at hundreds, if not thousands, if not tens of thousands of patients’ symptoms at the same time. And just like you’re analyzing something in a dashboard, you can identify who would benefit from an at-home test. And the doctor can go through those patient responses, order the tests appropriately, have the test delivered to the house. The patient then self-swabs—and the swab that we're using is actually a buccal mucosa, so it takes saliva from the inside of the cheeks and the gums, and the patient would put it back into this tube and ship it back through the US Postal Service to our lab partner for analysis. We would get those results in 24 to 72 hours, and then communicate to them again, and then initiate further video visits with the patients who are positive. We can focus on communities that are being hit hardest, without having to put our health care workers at risk. 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 we were working within FDA guidelines when we launched the test. We immediately stopped when the FDA updated its guidelines around the testing, and we are continuing to work with the FDA to obtain approval, because the officials have said publicly that they support the idea of home testing. They want more data around it. And frankly, we're hoping that between the FDA and the local governments in each state, that we can get this test approved, because we know that it performs incredibly well compared to the standard that's out there. NT: How do you know that? I mean, you know that the test is effective because you've tested it. But you haven't tested the process where people actually have to put it in the tube and put it in the mail, and they forget to put stamps in it, or their kid puts a peanut butter and jelly sandwich on it, right? Like all the things that happen at home. CD: That’s a great point. And frankly, that clinical study hasn't been done with the at-home test. But it hasn't been done with any of the existing tests in this pandemic. So when you ask your doctor, you're going to run a nasopharyngeal—so you're going to put a swab through my nose into the back of my throat—and you're going to send it off to Labcorp or Quest, what's the sensitivity? How do I know how accurate this is? You won't get a straight answer. And the reason is that clinical data don't exist for any of these tests. So the real-world data doesn't exist, whether it's for the at-home test or for the commercially available testing. We do know that, to your point, that the process of extracting the DNA and getting an appropriate sample for the RT-PCR machine is highly effective and replicable. But how good are people at swabbing their own mouths and noses and putting it in the mail? We do have data that we've shared with the FDA. And so we're optimistic that it is an effective way of doing it. NT: We have a good question here. What do you view as the biggest bottleneck in telemedicine that needs to be urgently resolved? 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 CD: So my concern, not just with telemedicine, but with health care in general, is that the regulatory network is an old one. If you're a doctor and you graduated from a medical school in the US, and you've gone to residency in the US, and New York state gives you a license to practice medicine—and then you need to practice medicine in Pennsylvania or Connecticut or New Jersey, you actually have to go through the same six-, eight-, or nine-month process to get approval to practice medicine in that other state. It makes zero sense. When you get on Metro North in Manhattan and you come out in Greenwich, your DNA doesn't change, your body doesn't change at all. You're still a human being, but the doctor that could treat you in New York can't treat you in Connecticut. And that's a problem. And telemedicine faces the exact same problem, where a provider who is licensed in California can't provide services in Idaho. And I know there's a concern about, for example, treating patients in underserved communities or rural communities where health care providers don't necessarily live, because there isn't a population density that's large enough. Well, we need to take a step back and ask ourselves, “What are these regulations good for?” Is New York state that much better at figuring out whether I'm a good doctor than California is? Let's identify the state in the country that's the hardest to get acceptance in, and let's say that if you get accepted in North Carolina, then you can be a doctor anywhere in the country. That's what we're looking for. And having parity with the telemedicine visit, meaning if you're seen via telemedicine or in-clinic, insurance companies should pay roughly the same amount. I would say that is also an important barrier, because, currently, if you look at incentives for providers, it's to ask the patient to come into the office, because they won't get paid otherwise. NT: They get paid zero for a telemedicine consultation? Or they get paid half, they get paid a quarter? CD: Yeah, it's state by state, and it's insurance company by insurance company. So you have to read your plan to find out what your benefits are. 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 NT: But what's the range? On average, it's 10 percent, or on average it's 92 percent? CD: I would say that, on average, it's zero. Unless you have a specific kind of telemedicine clause in your benefits. And, well, this is why what Trump said, you know, early on, which was, there's now parity. You can see a Medicare patient who you've never seen before, so you haven't established with that patient, you can see them and you can get paid for it. That was novel. But what does it do? Again, what are we trying to achieve here? What we're trying to achieve is that a patient gets care. If it's appropriate for telemedicine, it's appropriate for telemedicine. If it's inappropriate for telemedicine, the doctor shouldn't be providing that care through telemedicine. The payment should be secondary. And yet, we've gated it with these regulations and with these insurance contracts, and states started to, in 2018, say, “Well, we want parity between telemedicine and in-clinic visits.” However, there's no stick to that. So the caveats were if you had an established patient, you can then, next time, see them via telemedicine. You needed to do a video visit versus just an asynchronous visit where the patient fills out their information, the provider looks at it later on. There were all these nuances to it, where in the practical world, it didn't make telemedicine a viable option for many. And it incentivized doctors to say, “Oh, you want that prescription refill for the blood pressure medicine that you've been on for years? You have to come into the clinic for me to see you.” If you've been on the receiving end of that comment, you now know why. It's because your provider is not incentivized to take care of you remotely and say, “I understand that it's hard for you to come in to get that prescription refill. I know you need it. I'd like you to send me your latest blood pressure from the home blood pressure monitor that you took the other day. And as long as it's in range, I'm going to refill your medicine.” NT: Ok, so I'm just going to restate for everyone in the audience that this is absolutely insane. If there are any congressmen, governors, legislative aides listening: If doctors do telemedicine consultations, they should be paid. And I agree with Caesar, if I go to see you and you give me good advice about something that can be handled via telemedicine, you should be paid. If you try to instruct me on performing my own surgery with a saw, that's inappropriate, you should not be paid. So I think that's where we should be going. 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 have a whole slew of really great questions. So one of them is: What about telemedicine in prisons? I’d like to broaden that out a little bit, but that's an excellent question. Where are the populations, or surprising areas, where telemedicine is particularly appropriate? CD: The prison population is one that’s ripe for telemedicine. I work in an emergency department that's very close to a state prison as well as the county jail. I think also rural communities that may not have access to a dermatologist or a specialist—telemedicine is perfect for those fields, especially when it comes to things like stroke care. Most of the decisions made around stroke care can be done remotely. And it's a service that can really change someone's life. So the prison population is a great example. The local jails will contract with medical groups that just do jail care. And that's a very limited amount of payment for mostly chronic issues, and they'll send out to the local emergency departments for the more acute issues. If you know of local uses for telemedicine, and you're wondering, why haven't they been adopted, I would say look at the payment scheme, and look at the incentives for that system and how money is allocated. And I guarantee you that there's waste there. It's one of the frustrating parts of being in the field; you see a ton of waste. You see an incredible amount of press around the cost of health care, and yet very few people are doing anything innovative about it, to change it. There's just too much money on the other side of that equation. NT: I'm going to read something from a viewer. This is something I think you're going to agree with, because it maps closely to something you just said. This is what Rich says: “I have been using telemedicine for 10 years. Regulations and lack of parity from payers are what's been holding it back, not the technology. Can't be used for everything, no. But patients love it and are not going to tolerate it going away after Covid-19. Payers need to pay for it ongoing, and restrictions across state lines need to go away. My patients live in two states and travel all over. I should be able to help all of them via telemedicine, not just the state where I'm licensed.” Godspeed, Rich. Thank you for that excellent comment. 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 Now I want to go back to something you said. You were talking about telemedicine in rural areas, which brings me to a question from three viewers on a similar topic. And that is basically: In rural areas, there's a need for telemedicine, but sometimes there isn't broadband. What can you do? CD: Well, I'm hoping 5G and the additional capabilities will be there eventually. I know that the T-Mobile/Sprint merger happened partially on the basis of providing broadband to these rural communities. I've been able to do telemedicine consultations through my cell phone on a soccer field when there's been an urgent condition that a patient needed to be seen for. So I think we're less reliant on broadband issues than we were a few years ago. I would say also that there's a subset of telemedicine called asynchronous telemedicine, where a patient can input some information about what they're going through. So, for instance: My age is 25, I'm female, no other medical problems, and I'm having burning when I urinate. What should I do? So you input that information as the patient, and your doctor at some nonsynchronous time later on reads that information and says, “Sounds like you have a urinary tract infection. You should have an antibiotic sent to your pharmacy.” And does so. And that allows you to not have the best broadband service but some sort of access to the internet. It allows your provider to see many patients at the same time. And it's evidence based. It turns out that in the clinical scenario I just gave you, having a urine test and a urine culture doesn't affect your treatment of the patient, as we once thought it did. And so it's better for the patient, because it gets them treatment before the infection gets to their kidneys, and it's better for the provider because now they can see more patients at the same time and do so efficiently. And then spend their time following up and instructing the patient on their condition, rather than the administration of the health care. NT: Okay, we have a question from Facebook: With Carbon Health telemedicine and Covid-19 testing, how much would it cost to get at-home tested once it's approved by the FDA? 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 CD: That’s an awesome question. So I think I mentioned that on January 23, we had our first patient in our clinics with what was suspected to be coronavirus. We had two patients, from Wuhan city, tachycardic and with fever. From that moment on, we rallied the entire company, and part of rallying the company was: What can we contribute to this pandemic? And part of what we're contributing is our doctor services for free, for the at-home test. So the only cost to patients will be the cost of the test itself and the shipping. We've gotten the payments down to around $167 for the at-home test. The idea is that if our politicians are being straightforward with us, and that these tests, which should be covered by insurance, will be free to patients, the doctor visit which Carbon Health provides, we won't charge for. And so we're trying to do everything we can to get widespread testing to patients to follow the same trajectory as, you know, South Korea and Germany have done. We understand that payment is a problem. So we've made our contribution to the cause. NT: Let's look at your crystal ball about the future of telemedicine. As with many other things in the world, coronavirus has accelerated trends that existed before, like working from home and communicating via video conference. Look into the future five years from now, I would imagine it'll be much more telemedicine for certain kinds of treatment. I would imagine you would then need differently designed hospitals, because you need less space for consultations and maybe a higher percentage of space for invasive treatments. So you need to redesign hospitals. I would imagine that there will be different kinds of doctors who succeed—you know, a person who's very good at telemedicine, is very good at communicating through Zoom and has good lighting, as you do Caesar, will have an advantage versus some of the soft skills you have for in-person consultations. I would imagine that the number of times people go to the hospital for no consequence will go down. What else is going to happen because of telemedicine? By Meghan Herbst CD: Well, you know, my prediction is that costs will go down as well. At Carbon Health we've been hyper-focused on access plus cost. So if you create a better patient experience and a better doctor experience and use technology to make that experience more seamless, and then take away the administrative burden, what that does is it reduces the cost of care. And we've seen that in our company, in our clinics. For example, we now have mental health services, we have pediatric services, we do primary care through our virtual platform. And so exactly what you said is what I believe too. And the reason that you've come to that conclusion, I've come to that conclusion, is that it just seems like it makes sense that whatever we can take care of through great technology, and remotely, we should. And those things that you can't do through telemedicine or technology should happen in-person. And that's kind of what clinics will look like. And that's what hospitals will look like—they’ll be for procedures and more acutely ill patients, and then we'll reduce cost. 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 would say one caveat, though, is that it's not in your hands or mine what that future looks like. It's really going to end up being how much your employer demands that type of care to the insurance companies who decide which providers get paid for the care that they provide. So I think that one of the caveats in health care that's not obvious is that even if you create the most amazing product in the world, patients don't necessarily come unless that product is approved by a gatekeeper (the insurance company or the government). So that's the one caveat that's frustrating. But I think there is an opportunity in this pandemic, where if you're an insurance executive or an employer who does self-insurance or the government, it's hard to argue that, “Oh, technology is not useful in health care.” NT: And then, digital disruption often sounds, in theory, fantastic and wonderful. And there are huge benefits. You can look at different industries: the music industry, where we had digital disruption and Spotify is a great way to listen to music, but it drove a lot of record labels out of business, drove some bands out of business, made more people tour. We all know those effects. Digital disruption has been great for journalism. Look at what we’re doing. We have Facebook distributing the conversation that WIRED is having. That’s so cool. But it’s also changed the advertising market, which is complicated. Journalism has changed dramatically. So one of the things we know about digital disruption is that it turns things upside down, in ways that are very hard to predict. So with that premise, give me some more predictions about what it does to hospitals, insurers, doctors. CD: I think digital disruption has already happened in health care, but in the exact opposite way as it has in other industries. When you look at time spent, the doctor’s time, and how we spend it during the day, frankly most of it is in front of the computer. The numbers are staggering. It’s up to 150 percent of the time that you spend with your patient; you actually spend 150 percent of that time documenting the visit. And of course that depends on what specialty you’re in, but the point is that doctors have become really attached to, burdened by the administrative needs of documenting the visit. So typing out: Nick Thompson, male, came in for XYZ reasons. That takes time and effort, so now you’re spending one of the highest-paid profession’s time on documentation. So the digital disruption has happened, and it’s led to this terrible, expensive health care system that you see today. 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 Now, for version 2.0 or 3.0, whatever it is in this life cycle, I think that can change by having smarter technology in play. So at Carbon Health, we look at how much time the doctors spend documenting, how much time they spend with patients, how much time they spend after their shift is over documenting. Typically, if you look at Epic Systems, which is a very well run company, it has software in many of the hospitals across the country, if not the world. What happens is that typically there’s a peak in log-ins during hospital hours, and then there’s a lull around dinner time, and then there’s another peak late at night. And what’s happening is that the doctors are spending time with their families, then logging back in and finishing up their work that they started during the daytime. That is incredibly disruptive to the doctor-patient relationship, to job satisfaction for providers, etc. When we look at our own numbers at Carbon Health, we see that typically there’s about a 15-30 minute period of time after the shift is over, where the provider finishes up all their charts, and then there's no more log-in until the next day. And that to us is success. And hopefully there are more and more companies like ours who can use technology in a smart fashion—to disrupt the disruption, frankly—and get us back to why people always wanted to go into medicine in the first place, which is: I love spending time with my patients, I love getting to know people, understanding what they need and trying to meet those needs. Rather than: I spent some time with my patients and then I spent a lot of time with my computer to document everything. NT: Ok, we’re going to wrap it up here. Thank you so much for everybody who joined in. Thank you for all those fantastic questions that came in through Zoom, Facebook, other channels. Thank you to our audience and to Caesar. We’ll see you at the next one. What if it returns every year, like the common cold ? “Here in spirit”: an oral history of faith amid the pandemic We need a vaccine—let’s get it right the first time Un-miracle drugs could help tame the pandemic WIRED Q&A: We are in the midst of the outbreak. Now what ? Read all of our coronavirus coverage here Topics coronavirus COVID-19 Susan D'Agostino Dhruv Mehrotra Dell Cameron Vittoria Elliott Reece Rogers Will Knight Amanda Hoover 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 "

"Why Tech Employees Are Rebelling Against Their Bosses | WIRED"

"https://www.wired.com/story/why-tech-worker-dissent-is-going-viral"

"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 Nitasha Tiku Business Why Tech Worker Dissent Is Going Viral Microsoft CEO Satya Nadella, left, and Amazon CEO Jeff Bezos are targets of employee petitions against certain company contracts. Chip Somodevilla/Getty Images Save this story Save Save this story Save Silicon Valley has a long and secretive history of building hardware and software for the military and law enforcement. In contrast, a recent wave of employee protests against some of those government contracts has been short, fast, and surprisingly public---tearing through corporate campuses, mailing lists, and message boards inside some of the world’s most powerful companies. The revolt is part of a growing political awakening among some tech employees about the uses of the products they build. What began as concern inside Google about a Pentagon contract to tap the company’s artificial-intelligence smarts was catalyzed by outrage over Trump administration immigration policies. Now, it seems to be spreading quickly. Within a few days in late June, employees from Microsoft , Amazon, and Salesforce publicized petitions urging their CEOs to cancel or rethink lucrative contracts with US Customs and Border Protection, Immigration and Customs Enforcement, and local police departments. Airing a company’s dirty laundry is new. Historically, tech workers have rarely peeked out from under the industry’s cone of silence---a cultural norm often invoked as a sign of trust in leadership but enforced by a layer of nondisclosure agreements and investigations into leaks. At Google in particular, managers have encouraged internal debate---and employees have bought into the system. But earlier this year, internal efforts broke down over Google’s role in Project Maven, which applies AI to interpret camera footage from drones. Employees adopted other tactics when they felt executives were downplaying the size and scope of the Pentagon contract. Thousands, including senior engineers, signed a petition asking CEO Sundar Pichai to cancel the contract. Some workers claimed to quit over the relationship. A group of engineers refused to build a security tool necessary for Maven. “We believe that Google should not be in the business of war,” the petition said, warning Pichai that the company’s involvement in Maven would “irreparably damage Google’s brand and its ability to compete for talent.” Earlier this month, Google said it would not renew the Pentagon contract when it expires next year. A few days later, Pichai released a code of ethics to govern Google’s use of AI, which said Google would not develop the technology for use in weapons, but will continue “our work with governments and the military in many other areas.” 'People who signed up to be tech heroes don’t want to be implicated in human rights abuses.' The changes emboldened workers at other companies. A petition that started with seven Microsoft employees has gained 457 signers asking the company to drop its contract with ICE. “We are part of a growing movement, comprised of many across the industry who recognize the grave responsibility that those creating powerful technology have to ensure what they build is used for good, and not for harm,” the petition says. Two days later, Amazon workers publicized a letter that seeks to halt sales of the company’s facial-recognition services to law enforcement; that has 400 signers. More than 650 Salesforce workers want the company to rethink its relationship with the Customs agency, because “our core value of Equality is at stake.” Each of the companies employs tens of thousands of workers across the globe, so it’s hard to measure the level of internal support for their efforts. But the protests also drew support from influential academics and researchers, who drafted their own petitions around government contracts at Google and Microsoft, which became a touchstone for anxious employees. The fledgling movement marks an evolution in the consciousness of tech employees; last year, employees at several companies asked their CEOs to drop out of President Trump’s advisory council and oppose a ban on visitors from predominantly Muslim countries. But asking a company to forgo the revenue of a government contract is a different kind of tradeoff. “One is about the politics, the other is about the core business, what is this company in the business of doing or not in the business of doing,” says Liz Fong-Jones, a site reliability engineer at Google known for her advocacy work. 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 Such stands against a company’s financial interests are unusual inside private firms, but not unheard of, says Forrest Briscoe, a professor at Penn State’s business school, who has studied internal and external corporate activists. He cites efforts beginning in the late 1980s by environmental scientists employed by Dupont and General Motors to alter those companies’ positions on climate change. Silicon Valley’s recruiting pitch has long been: Work with us to change the world. Employees are encouraged to make their work life synonymous with their social identity, and many internalize those utopian ideals. “People who signed up to be tech heroes don’t want to be implicated in human rights abuses,” says a senior Google employee involved in the protest against Project Maven. Tech workers may feel freer to challenge their employers in part because they have marketable skills at a time of great demand, says Nelson Lichtenstein, a history professor and director of the Center for the Study of Work, Labor, and Democracy at UC Santa Barbara. “Why don’t you find this among the people wiring the circuit boards together in China? Because there they are much more vulnerable,” he says. 'I’m pretty sure that no one who took a job at Google thought, "I’m going to work for a defense contractor." Lockheed Martin is down the road, they could have gone to work there.' Lichtenstein compares the tech workers to recent activism by teachers in several states seeking better funding for schools. “The teacher strikes of the last few months were about re-funding public education in austerity states, a political as well as financial shift,” he says. “That has very large consequences for public policy as well as corporate policy.” One Google employee says tech workers benefited from the momentum of the teacher strikes. But why now? Employees say their companies have grown so big that workers weren’t aware of the extent of their employers’ government contracts. The shift caught companies accustomed to controlling the narrative flat-footed. They scrambled to downplay blog posts from sales teams just months earlier crowing about contracts with government agencies that are now in the spotlight for harsh treatment of immigrants or invading people’s privacy. But Stephanie Parker, a policy specialist at YouTube, says the changes have been building. “From the outside, it looks like there’s been an 180-degree change from last month to this month,” she says. In reality, she says, the 2016 election and internal disputes over diversity at Google have awakened employees to “the connections between the technology we’re building, issues in the workplace, and what impact that has had on our communities and on our world.” One reason for the unrest is that the projects involved have very real consequences, says Erica Joy Baker, a former Google engineer and well-known activist within the industry who’s now an engineering manager at Patreon. “Now we’re talking about life and death decisions for a lot of folks,” Baker says. “I’m pretty sure that no one who took a job at Google thought, ‘I’m going to work for a defense contractor.’ Lockheed Martin is down the road, they could have gone to work there.” 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 disputed projects span a range, from building facial-recognition technology that could be deployed on unsuspecting people in public to providing computer services that a few years ago would have been run on a machine inside the Pentagon. Moreover, in each case, there may be ethical considerations on the other side. Matt Zeiler, CEO of Clarifai, an artificial-intelligence company also working on Project Maven, said in a recent blog post that deploying the technology could save lives. Microsoft policy managers told employees in an internal online discussion that the company was in contact with immigration advocacy groups, who said canceling Microsoft’s contract could harm kids and families. Still, some workers see a common thread through projects with the Pentagon, the immigration services, and the more tenuous connection between the software company Palantir, which works with ICE and uses Amazon’s AWS service. “This is not a hair we can split and say 'actually we didn’t built the jails, we just allowed them to more quickly itemize the invoices for the jails,'” says the senior Google employee involved in the effort to shut down Maven. “This is an ethical question and it’s a question lot of people are asking.” For now, the movement’s message is not a finely drawn policy position on what kind of government work is acceptable but rather a plea for transparency and a seat at the table, so that employees have a say in where such technology is used. Some tech workers involved in the protests invoke IBM’s work for Nazi Germany in the years leading up to World War II. Edwin Black, author of IBM and the Holocaust , says the current wave of dissidents is atypical for the tech industry. “You wouldn’t have even asked me this question a year ago. Now we have to ask, is it a political revolt, or is a revolt of consciousness about the capabilities of the technologies being implemented?” In a statement, an IBM spokesperson said, “As with other foreign-owned companies that did business in Germany at that time, IBM's German operations came under the control of Nazi authorities prior to and during World War II.” Employees are aware this will be a long slog and have been skeptical of the lawyered-up, press-friendly but vague responses. In Google's new AI principles, Pichai said the company will not pursue “technologies whose purpose contravenes widely accepted principles of international law and human rights,” according to the blog post. “Who says that?” another Google employee involved in the Maven protest asked WIRED. “Either you support human rights or you don’t.” The reason you use closed captions for everything now The stock market loophole that screws the little guy Inside Palmer Luckey’s bid to build a border wall The bike-share war is shaking up Seattle like nowhere else Here are the best Mac alternatives for Windows users Looking for more? Sign up for our daily newsletter and never miss our latest and greatest stories Senior Writer X Facebook LinkedIn Topics Google Microsoft Amazon Salesforce Pentagon employees Gregory Barber Caitlin Harrington Kari McMahon Steven Levy David Gilbert Jacopo Prisco Will Knight 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 "

"'Uncanny Valley' and the Meaninglessness of Writing About Tech | WIRED"

"https://www.wired.com/story/book-review-uncanny-valley-anna-wiener"

"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 Kehe Culture The Millennial Meaninglessness of Writing About Tech For more than four years, Wiener toiled and lounged in customer support roles, first at a data analytics company and then at GitHub. Photograph: Michael Short/Bloomberg/Getty Images Save this story Save Save this story Save Throughout her career, Rebecca Solnit has been dogged by comparisons to Joan Didion. Never mind that the writers have peanuts in common beyond a geography—California—in which Didion didn’t even remain. As a woman writing semi-journalistic sentences of quality, Solnit is doomed to her Didion descent. (They all are. Virginia Heffernan, Anna Quindlen, Meghan Daum, Katie Roiphe, Rebecca Traister, Susan Orlean, Rachel Cusk, Michelle Orange, Maureen Dowd, Roxane Gay, Leslie Jamison, Sarah Nicole Prickett, Jia Tolentino—Didion’d, every last one.) So what’s a Solnit to do when given the opportunity to sum up the virtues of a new memoir , Uncanny Valley , by a young woman writing semi-journalistic sentences of quality? Follow tradition, of course, and enforce the homology down the generations. “Like Joan Didion at a startup,” Solnit declares. It’s right there, indelible on the book jacket. The victim of the quasi-praise is Anna Wiener, who moved to San Francisco at age 25 for a job in tech and lived to write about it. For more than four years, between 2013 and 2018, she toiled and lounged in customer support roles, first at a data analytics company and then at GitHub. Uncanny Valley is her chronicle of that period, written with the kind of piquant ambivalence that triggers a salivary response, followed by spitting cries of Didion’s umpteenth coming, in so many modern readers. Wiener is a rock-solid writer, which Solnit’s miscalibrated, publicity-oriented blurb doesn’t change. What it does do, unfortunately, is expose the book’s foundational wobble. Didion prized her vantage as a social observer, the neurotically perceptive outsider. Wiener, who lived within yet strains to see from without, is never sure where she stands—an irresolution that’s less Didion at a startup and more the ditherings of an upstart. Wiener recognizes the problem, or fragments of it. She makes mention of identity crises; she frets about her stance and status. Early on, as she’s packing up her Brooklyn apartment, leaving behind a nascent career in publishing for something as anti-literary as mobile analytics, a close friend wonders if she’s making the right decision. Wiener takes the moment to reflect on her split consciousness: There had always been two sides to my personality. One side was sensible and organized, good at math; appreciative of order, achievement, authority, rules. The other side did everything it could to undermine the first. I behaved as if the first side dominated, but it did not. I wished it did: practicality, I thought, was a safe hedge against failure. Wiener is constantly at odds with herself, consumed by warring impulses that her time in tech only comes to exacerbate. She feels like a “babysitter” or “concubine” on the job; she feels “indescribably lucky” on the job. She hates EDM (“decadent and cheaply made”); she loves EDM (“like I just railed cocaine, except happy”). She takes pleasure in learning a bit of coding; she realizes “there was nothing I needed or desired from software.” She does it in the same sentence: “I hated the success metrics,” she writes, “but I liked being the one who monitored them.” Elsewhere, on biohacking: “I wanted to be above it, but I wasn’t above it.” Like/dislike, love/hate, inside/outside: Wiener’s formulations reach for rigor, for some deep truth about knowability, but end up wimping out. She starts arguments she can’t finish, not only with herself but with her new colleagues. She’s surprised whenever one-on-one interactions admit of nuances disallowed by her standard-issue assumptions. Billionaires are bad, except the one who befriends her. Tech bros think the same way, except her roboticist boyfriend. Perhaps these conflicts are meant to echo the Bay Area itself, a land so riven by self-contradiction it’s on the verge of spiritual collapse, but the conclusion is still unenlightening. Was Didion ever so flimsy or indulgent? Her moralities were nonnegotiable. Wiener, perfecting that New York–nourished millennial mode, can’t find new meaning, only evidence, everywhere, of meaninglessness. To stay sane as everyone around her drinks the Kool-Aid (or butter coffee), Wiener never relinquishes her outsider status. Instead, she tells herself she’s making good on her college degree and doing sociology—tech as her laboratory. Here may be the source of the struggle. Though she lives inside the glass cage, she walks around it as though from the other side, mistaking reflections for embodied reality. She's ruled by appearances, by looking and seeing. Observing the ruggedly dressed workforce: “They looked ready to gather kindling and build a lean-to … They looked in costume to LARP their weekend selves.” Observing commuters: “They looked tired, resigned, sheepish. Mostly, they looked at their phones.” Observing businessfolk in the Financial District: “They looked so much older than we did … They looked straight out of another era, like the nineties.” No amount of looking at something, alas, makes it come alive. (Unless you’re on drugs. Which Wiener is, at one point. You’re happy for her.) Uncanny Valley by Anna Wiener | Buy on Amazon Courtesy of FSG What makes this all the more frustrating is that Wiener can write an immaculate sentence. Like the very first one, an instant classic: “Depending on whom you ask, it was either the apex, the inflection point, or the beginning of the end for Silicon Valley’s startup scene—what cynics called a bubble, optimists called the future, and my future coworkers, high on the fumes of world-historical potential, breathlessly called the ecosystem.” Rhythmical, urbane, and look at that beautiful “whom”! (High on her own fumes, though, she lets the challenging pronoun define her, using it in the book at least 15 times.) In sections on the ephemerality of software, the exigencies of telecommuting, and thought-trends in tech—rationalism, city-building, UBI—Wiener's well-honed words pierce through the conventional chatter. She’s also a master of the descriptive arts. A hot tub at a spa-themed party becomes “a sous vide bath of genitalia.” Trendy shoes she buys but never wears are a “monument to the end of sensuousness.” Jeff Bezos is a “chelonian ex–hedge funder.” She never actually names Bezos. In fact, she uses very few proper nouns. Aside from the occasional first name of a friend, every character or company, the ones she's worked for as well as the ones everybody knows, is glossed with a pithy phrase. The coy ploy, in subversive deference to NDA culture, ranges from effective (“the social network everybody hated”—Facebook) to distracting (“a computer-animation studio famous for its high-end children’s entertainment”—Pixar?). 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 Sentence-level flourishes never add up to text-level sophistication, though. Nor do they make this memoir literary , a descriptor Wiener is clearly chasing. Beyond Didion, Wiener’s other major influence seems to be Ellen Ullman. Ullman, who fell into programming in the late ’70s and stayed at it for 20 years, wrote a masterpiece of a memoir called Close to the Machine. Just because they’re both women in tech doesn’t validate the comparison, of course, but Wiener actively invites it. She profiled Ullman for The New Republic in 2016, saying that she read Close to the Machine for the first time at 25, the same year she moved to San Francisco. Here is one of Ullman's more startling passages, talking about a guy she dated: His lovemaking was tantric, algorithmic. I once thought that love could not be programmed, but now I wondered. This sex was formulaic, had steps and positions and durations, all tried and perfected, like a martial arts kata or a well-debugged program. My own role in it was like a user-exit subroutine, an odd branch where anything might happen but from which we must return, tracing back to the mainline procedure. I felt again as if I'd come in on a private process, something that Brian had worked out all on his own and which, in some weird expression of trust, he had decided to show me. I should have felt dissatisfied. I should have called it off. For a time, I even looked fondly at the neat monogram on my pajama pocket where it lay on the dresser top. But again I gave in to curiosity and tenderness. He has been with himself too long, I thought. 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 Wiener lacks this technoliterary lyricism. Perhaps because she never cracked coding, never got close to the machine, was only adjacent to it, more looker or lurker than full-bore liver, she can’t find connections, these novel ways of seeing. Instead, she produces a dishy, readable account, full of fashionable doubt and just-so anecdotes, that mostly reiterates the well-established buffooneries and blindspots of Valley culture. Late in the book, Wiener turns to contemporary literature for some solace, to pull herself out of the internet-fueled spiralings of her filter bubble. It offers no respite, and she dismisses it all as “beautiful descriptions of little substance, arranged in elegant vignettes.” It’s such a tidy summation of her own memoir one wonders if she’s including herself in the critique. Uncanny Valley indeed began life as a series of vignettes in the pages of n+1 , with the same canny title and a clearer sense of purpose. There’s a lot more to the full-length book. There’s also, true to its core ambivalence, a lot less. Read it. Don’t read it. Love it. Hate it. Lurking by Joanne McNeil Though it never quite sustains the momentum of its knockout first chapter about Google, this personal history of the internet, forthcoming in February, manages a sensitive sharpness to which more tech critics should aspire. How to Disappear by Akiko Busch If you're tempted, as many seem to be, by Jenny Odell's How To Do Nothing —a book-length non-argument for stopping to smell literal roses—pick this up instead. It's stranger and more radical, a reminder that invisibility is what keeps us alive. Close to the Machine by Ellen Ullman Has tech ever been written about so lyrically, before or since? A programmer, a memoirist, an essayist, a novelist, Ullman's a poet at a computer, whatever the medium. Magic and Loss by Virginia Heffernan She's been called the Didion of tech writing, which is ridiculous. Heffernan (a WIRED contributor) is entirely her own. Loopy and hyperliterary, she can write circles around anyone and anything. Political Fictions by Joan Didion Overshadowed by the flashy early work and her more somber late phase, this middle-period collection of essays may be Didion's truest triumph. She never tells you what she thinks—yet by the end you believe exactly what she does. When you buy something using the retail links in our stories, we may earn a small affiliate commission. Read more about how this works. Features Editor X Topics Wired Book of the Month Book reviews memoir Angela Watercutter Jason Parham Gregory Barber Jason Parham Elizabeth Minkel Kate Knibbs Jason Parham Kate Knibbs 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 "

"Defying Company Policy, Over 300 Amazon Employees Speak Out | WIRED"

"https://www.wired.com/story/amazon-employees-protest-communications-policy"

"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 Louise Matsakis Business Defying Company Policy, Over 300 Amazon Employees Speak Out Amazon Employees for Climate Justice, which led a widespread walkout over company policies last fall, organized the protest this weekend. Photograph: Jason Redmond/Getty Images Save this story Save Save this story Save While Amazon CEO Jeff Bezos was throwing a lavish party at his $23 million mansion in Washington, DC, this weekend—attended by celebrities like Ivanka Trump and Bill Gates—hundreds of his employees were gearing up to revolt. At issue was the company’s external communications policy and reports earlier this month that it threatened to fire employees for speaking out about climate change without proper authorization. In protest, more than 350 Amazon workers published statements under their own names in a Medium post on Sunday, intentionally violating the policy en masse. The protest was organized by Amazon Employees for Climate Justice, a coalition of activist workers that has pushed for the company to adopt more environmentally friendly policies over the past year. The group organized a climate change walkout last fall that was attended by thousands of Amazon and other tech workers around the globe. “Corporations cannot own the conversation that threatens our very existence,” wrote Maren Costa, a principal user experience designer at Amazon. “We can’t be silent about issues that harm our children, communities, and planet.” Costa is one of several employees who were told they could be fired if they continued speaking publicly about Amazon without getting advanced approval. In the fall, Costa spoke with several news outlets, including WIRED , about what she said was the company’s inadequate response to the climate crisis. Amazon has long required employees to get approval before speaking publicly, but the policy wasn’t strictly enforced, according to The Washington Post. In September, right before the walkout, Amazon created a new internal portal for workers to request permission to speak with the press; employees are now required to have a “business justification” for doing so. None of the workers who contributed to Sunday’s Medium post appear to have used that formal channel. “The idea is to intentionally break the communications policy so prolifically that it is unenforceable,” Amazon Employees for Climate Justice wrote in an email sent internally last week to collect statements and signatures; it later made the message public. Many large companies have policies about external communications, and AECJ acknowledged that Amazon’s policy makes sense in some cases, such as confidential projects. “But allowing a corporation to silence us on its contribution to the climate crisis is a clear overreach of comms policy, and effectively demands we give up our basic humanity and integrity in order to be employees,” the group wrote in its message. 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 all employees are welcome to engage constructively with any of the many teams inside Amazon that work on sustainability and other topics, we do enforce our external communications policy and will not allow employees to publicly disparage or misrepresent the company or the hard work of their colleagues who are developing solutions to these hard problems,” an Amazon spokesperson said in a statement. The spokesperson did not comment on whether Amazon would take action in response to Sunday’s post. The statements the group published Sunday addressed a range of issues beyond Amazon’s impact on the environment. The Medium post is a laundry list of controversies the company has weathered in recent years, including labor issues, safety and privacy, and political influence, among others. Not all of the statements were critical of Amazon’s outside communications policy. One worker said it prohibited her from sharing positive opinions with the press. “I want to be able to speak to the media about all the innovative things we ARE doing to protect Alexa customer privacy,” wrote Emily Greene, a software engineer. “I work every day to improve our protections of customer data, and it’s disappointing when the media spins the truth because the people who speak up are the ones with nothing to lose.” 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 A number of Amazon employees who participated in Sunday’s Medium post commended the company’s recent environmental efforts. Ahead of the walkout in September, Bezos unveiled a new “ Climate Pledge ,” where businesses promise to regularly disclose greenhouse gas emissions and reach carbon neutrality by 2040. Amazon was the first company to join. “I am proud to work at Amazon and to be working on such an important topic. I feel supported by our company and by our leadership to make this our top priority,” wrote Kimberly Pousman, an engagement manager working on the Climate Pledge. But many other workers believe Amazon has not gone far enough to protect the planet. “Amazon should end our contracts with oil and gas companies,” read a statement signed by dozens of employees “Our AI and machine learning are being used for ‘finding oil,’ ‘producing oil,’ and ‘optimizing production.” Gizmodo reported in April that over the past several years, Amazon Web Services, Amazon’s cloud computing arm, had aggressively courted the business of energy companies. Despite protest from employees, Bezos has said that AWS would not stop working with the fossil fuel industry. Many criticized the treatment of warehouse associates and delivery drivers. “Amazon’s supply chain should not be built at the expense of warehouse workers who work at a pace that causes higher-than-industry-average injury rates,” read one statement signed by dozens of workers. “It’s not humane to have people scared to go to the bathroom.” Michael Berman, a senior software development engineer, condemned Amazon’s network of delivery contractors , who have been implicated in a number of lethal accidents. “Today’s system incentivizes unsafe driving, and appears to be designed to insulate Amazon from liability, rather than to promote ownership and accountability,” Berman wrote. Max Eliaser, a software development engineer, was the sole employee to denounce Ring , the home security company Amazon acquired in 2018. Civil liberties groups and privacy advocates have criticized the secretive partnerships Ring has made with police departments around the country, which amount to a private, nationwide surveillance network. “The deployment of connected home security cameras that allow footage to be queried centrally are simply not compatible with a free society,” Eliaser wrote. “The privacy issues are not fixable with regulation, and there is no balance that can be struck. Ring should be shut down immediately and not brought back.” 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 systems engineer named Bob Danek decried Amazon’s political influence in Seattle, where its headquarters is located. “Seattle residents have the exclusive right to vote for their council members, and to influence those elections with massive amounts of money is shameful,” Danek wrote. In the fall, Amazon poured $1.5 million into local races in the city, in the hopes of electing business-friendly representatives. While the collection of statements spans a broad array of topics, the central point is that the hundreds of employees who added their names are choosing to speak out, with or without Amazon’s approval. “I think it is dangerous for any company of any size to silence the words of the employees who are looking for the welfare of everyone,” wrote Vivek Koppuru, a software development engineer. It’s not clear what, if any, repercussions these workers may face. Google similarly confronted a wave of employee activism, and was widely condemned after it terminated several employees involved in organizing efforts. The employees alleged they were fired unlawfully, and the National Labor Relations Board is investigating the matter. The bird “snarge” menacing air travel Chris Evans goes to Washington The display of the future might be in your contact lens Scientists fight back against toxic “forever” chemicals All the ways Facebook tracks you— and how to limit it 👁 The secret history of facial recognition. Plus, 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 Contributor X Topics Amazon Vittoria Elliott Amanda Hoover Niamh Rowe Amanda Hoover Amanda Hoover Dell Cameron David Gilbert Caitlin Harrington 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 "

"TikTok, Under Scrutiny, Distances Itself From China | WIRED"

"https://www.wired.com/story/tiktok-under-scrutiny-china"

"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 Louise Matsakis Security TikTok, Under Scrutiny, Distances Itself From China TikTok has been downloaded more than 110 million times in the United States since 2017. Now lawmakers are questioning the app's policies—and its ties to China. Photograph: Getty Images Save this story Save Save this story Save TikTok, the app that revolves around sharing short video clips, is in a unique position. It’s arguably the first international social media platform to have built a massive audience in the United States, where it’s been downloaded more than 110 million times since its founding in 2017. TikTok has offices in California near competitors like Snapchat, Instagram, and YouTube, but it’s owned by ByteDance , a Chinese tech giant. As tensions between the US and China continue to escalate , that fact has become a headache for TikTok. Now the company is taking steps to distance itself publicly from its counterparts in Beijing. This week, Senators Chuck Schumer (D-New York) and Tom Cotton (R-Arkansas) sent a letter to US intelligence officials asking them to investigate whether TikTok poses “national security risks.” In their letter, sent to Joseph Maguire, the acting director of national intelligence, the senators expressed concern about the data TikTok collects on US users and whether that information could potentially be shared with the Chinese Communist Party. They also questioned whether Tiktok censors content on its platform and said the app is a “potential counterintelligence threat we cannot ignore.” It wasn’t the first time this month that lawmakers have questioned the security and content moderation practices of TikTok. Two weeks ago, Senator Marco Rubio (R-Florida) called for the Committee on Foreign Investment to investigate ByteDance’s 2017 acquisition of Musical.ly , a lip-syncing app popular in the US that was later merged with TikTok. On Twitter, Rubio said he was concerned TikTok is “censoring content in line with #China’s communist government directives.” TikTok responded to the questions raised by all three senators in an unsigned blog post published Thursday. The company asserts data on US users is stored in the United States, and that it isn’t subject to Chinese law. It also said that it doesn’t remove content “based on sensitivities to China.” “We have never been asked by the Chinese government to remove any content and we would not do so if asked. Period,” the post reads. “Our US moderation team, which is led out of California, reviews content for adherence to our US policies—just like other US companies in our space.” In its statement, TikTok also said it “doesn’t operate in China,” and doesn’t intend to do so in the future. But it doesn’t need to. The company didn’t mention that ByteDance already owns the extremely popular Chinese version of TikTok, called Douyin. TikTok now appears sensitive about ensuring the two apps aren’t conflated with one another. On Thursday night, a TikTok spokesperson emailed this reporter about a story WIRED published in July about China’s social credit system. The story had one line about the app partnering with local officials in a Chinese city, and the spokesperson requested that the original reference to TikTok be changed to Douyin. (The story has been updated accordingly.) But the timing of the message, and how much distance the company seemed to want from its counterpart, seemed striking. “They're separate apps, markets, users, content, teams, policies, etc.,” the TikTok representative wrote. Is there something about TikTok you think we should know? Contact the author at [email protected] or via Signal at 347-966-3806. WIRED protects the confidentiality of its sources, but if you wish to conceal your identity, here are the instructions for using SecureDrop. You can also mail us materials at 520 Third Street, Suite 350, San Francisco, CA 94107. Despite TikTok’s efforts, the company’s ties to China will almost certainly continue to be viewed with suspicion, not only by regulators but also by users. After The Washington Post reported about the lack of content on TikTok concerning the ongoing pro-democracy protests in Hong Kong, some users began experimenting to see whether their videos about the demonstrations would be removed. Buzzfeed News , whose reporters also uploaded footage themselves, found that the clips weren’t censored. Concerns about censorship seem to arise whenever a tech company from China is involved. Reddit users performed similar experiments after news broke earlier this year that Tencent would invest in the platform. Tencent also has a stake in Activision Blizzard, which has come under fire for punishing an esports player who spoke out in support of the Hong Kong protests. 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 Some of this distrust in TikTok may also stem from how little is known about its content moderation policies and practices. TikTok’s rules are relatively short and don’t go into too much detail. Compare that to Facebook, whose Community Standards were developed over more than a decade and now read almost like a full governmental constitution. Like many platforms, TikTok also hasn’t released much information about how the company’s staff are told to interpret its policies. According to guidelines recently obtained by The Guardian , TikTok previously instructed moderators to censor topics deemed sensitive by the Chinese government, as well as LGBT content in some markets. ByteDance has said the documents are outdated. It’s possible that TikTok itself hasn’t yet figured out how it plans to govern its platform, which has ballooned into an enormous global powerhouse only a few years after it launched. Like other social media companies, TikTok may initially have put more emphasis on growth than detecting problematic videos; the company reportedly spent nearly $1 billion on advertising last year alone. But it’s now facing many of the same controversies that other platforms have struggled with. This week, The Wall Street Journal reported that Storyful, a social media intelligence company, had identified around two dozen accounts on TikTok connected to ISIS. And in February, TikTok was fined by the Federal Trade Commission over allegations that Musical.ly illegally collected information on users under 13. There are signs TikTok is looking to mature its approach to policing its app. Earlier this month, Vanessa Pappas, TikTok’s US general manager, announced the company was bringing in the law firm K&L Gates LLP to create a committee of outside experts to review and advise on its rules for “child safety, hate speech, misinformation, bullying, and other potential issues.” The firm is also tasked with finding ways for TikTok to be more transparent about its policies and practices. And according to online job listings, TikTok is hiring more senior staff to work on moderation and security issues, including a trust and safety manager , a privacy lawyer , and an ethics and compliance manager. Even if TikTok opens up about its moderation practices, US concerns over its Chinese owner likely aren’t going away, especially because of China’s long track record of compelling tech companies to censor the internet within its borders. It’s a fear Facebook CEO Mark Zuckerberg, whose company has tried to compete with TikTok, appears more than happy to capitalize on. “Until recently, the internet in almost every country outside China has been defined by American platforms with strong free expression values,” Zuckerberg said during a speech at Georgetown University earlier this month. “There’s no guarantee these values will win out.” TikTok may be the biggest test yet. 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. Contributor X Topics Social Media China National Affairs censorship ByteDance Andrew Couts David Gilbert Reece Rogers Dhruv Mehrotra Lily Hay Newman Matt Burgess Dell Cameron Lily Hay Newman 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 "

"TikTok Is Having a Tough Time in Washington | WIRED"

"https://www.wired.com/story/tiktok-rough-time-washington"

"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 Louise Matsakis Business TikTok Is Having a Tough Time in Washington It’s not year clear whether mounting scrutiny from lawmakers will meaningfully impact TikTok’s operations in the US, where it has been downloaded over 100 million times. Photograph: Costfoto/Getty Images Save this story Save Save this story Save In some ways, the social media app TikTok could not have risen to prominence at a worse moment. The platform for sharing short-form video clips is owned by the Chinese startup Bytedance , and surged in popularity just as the United States’ relations with China are turning icier than they have been in years. At the same time, US regulators are more closely scrutinizing the data privacy practices of social media companies than ever before, after scandals like Facebook’s Cambridge Analytica debacle erupted last year. Republican lawmakers routinely accuse the likes of Facebook, Twitter, and YouTube of censoring conservative voices. Now TikTok is coming under fire for many of the same issues. On top of that, it has to find a way to explain its relationship with Beijing. Oh, and the app is particularly popular with teenagers and young people. Put it all together, and it’s like catnip for politicians with an agenda to push. During a hearing on Capitol Hill Tuesday, lawmakers and national security experts questioned whether TikTok really operates independently from China as the company has claimed. “Parents, if you don’t know what TikTok is, you should,” senator Josh Hawley (R-Missouri), one of tech’s loudest critics in Congress, said at the Senate Subcommittee on Crime and Terrorism. “A company compromised by the Chinese Communist Party knows where your children are, knows what they look like, what their voices sound like, what they’re watching, and what they share with each other.” TikTok declined to send an executive to attend the hearing. (Apple also was a no-show.) Instead, Vanessa Pappas, the company’s general US manager, released a lengthy statement on its website. “Every day, our US team makes decisions that we see as best for the US market, and we are given the independence to do so,” she wrote. Pappas also said that TikTok stores data on US users within the country, and that its content moderation team for the US market is similarly based in California. Is there something you think we should know about TikTok? Email the writer at [email protected]. Signal: 347-966-3806. WIRED protects the confidentiality of its sources, but if you wish to conceal your identity, here are the instructions for using SecureDrop. You can also mail us materials at 520 Third Street, Suite 350, San Francisco, CA 94107. The hearing took place just hours after The Washington Post published an article in which former TikTok staff said they were instructed by managers in China to censor videos on the platform, validating lawmakers’ existing fears about the company. Last month, senators Chuck Schumer (D-NY) and Tom Cotton (R-Arkansas) sent a letter to US intelligence officials asking them to investigate national security risks posed by TikTok, including “the potential for censorship or manipulation of certain content.” TikTok told The Washington Post that it initially wanted to moderate its platform according to a centralized set of rules, but later rethought the “one size fits all” approach. It now has different policies for each region it operates in. Also on Tuesday, senator Marsha Blackburn (R-Tennessee) sent a letter to Alex Zhu, the head of TikTok, asking the company to answer a series of questions related to children’s privacy by November 26. Earlier this year, TikTok reached a more than $5 million settlement with the Federal Trade Commission over claims that it illegally gathered personal information on children younger than 13. The settlement concerned the practices of Musical.ly, an American karaoke app Bytedance purchased in 2017 and later absorbed into TikTok. “It is crucial that Chinese-linked efforts to collect data from American children ends,” Blackburn wrote. “Because TikTok is owned by ByteDance, the app is subject to foreign laws that allow China’s government to seize information and 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 It’s not yet clear whether mounting scrutiny from lawmakers will meaningfully impact TikTok’s operations in the US. Last week, Reuters first reported that the Committee on Foreign Investment in the United States (CFIUS) had opened an investigation into Bytedance’s $1 billion acquisition of Musical.ly two years ago. The worst case result of the investigation would be that CFIUS tries to compel TikTok to divest its assets related to Musical.ly. Earlier this year, the Chinese gaming company Beijing Kunlun Tech Co. said it would sell the US dating app Grindr after CFIUS raised national security concerns. The extra attention TikTok has received from regulators and journalists has filtered down to users, some of whom have questioned whether they’re being censored by China. After The Washington Post reported about the lack of content on TikTok concerning the ongoing pro-democracy protests in Hong Kong, some users began experimenting to see whether their videos about the demonstrations would be removed, for instance. Similar stunts were carried out earlier this year when the Chinese tech giant Tencent announced it would invest in Reddit. No matter how TikTok’s time in the Washington spotlight pans out, its reputation has undoubtedly changed. Unlike competitors like Facebook and Twitter, TikTok has sought to evade controversy by branding itself merely as a platform for lighthearted content. In her statement today, Pappas stressed that the platform is “a place for users to express their creativity in a lighthearted and fun way.” But now, with regulators concerned about everything from children’s privacy to censorship dictated by the Chinese Communist Party, TikTok will have to get serious. That means finding a way to earn the trust of not only elected officials, but also users—and their parents. The super-optimized dirt that helps keep racehorses safe What's blockchain actually good for, anyway? For now, not much How to free up space in Gmail Trying to plant a trillion trees won't solve anything The untold story of Olympic Destroyer, the most deceptive hack in history 👁 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. Contributor X Topics congress Social Media ByteDance TikTok Reece Rogers Will Knight Peter Guest Matt Laslo Paresh Dave Steven Levy Deidre Olsen 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 "

"In Hong Kong, Which Side Is Technology On? | WIRED"

"https://www.wired.com/story/hong-kong-protests-digital-technology"

"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 Zeynep Tufekci Security In Hong Kong, Which Side Is Technology On? Illustration: Simoul Alva Save this story Save Save this story Save It was a sweltering August Saturday in Hong Kong, and the authorities had just shut down one of the most important technologies in the city: the MTR, Hong Kong's uber-efficient subway system. So the protesters walked. The demonstrators were in their 12th week of continuous action ; they'd been marching, singing, occupying streets, forming human chains, confronting police. They started when the city's chief executive, Carrie Lam—a leader essentially handpicked by Beijing—introduced a bill that would allow Hong Kong's government to extradite suspects to mainland China for prosecution. Hong Kong is a “special administrative region” of China, with an independent judiciary and much wider freedoms than those found on the mainland. Fearing that the extradition law would lead to the further erosion of those freedoms, large numbers of protesters took to the streets starting in early June. Related Stories Do Less Zeynep Tufekci Ideas Rose Eveleth Eyes on You Tom Simonite Now, nearly three months later, the bill had been suspended but not yet withdrawn. (That would come, but later.) And the protesters were feeling their strength, demanding an independent inquiry into police misconduct and universal suffrage. But on that Saturday, as we all ended up walking in the blazing sun, the protesters had a new target in their sights: “ smart ” lampposts equipped with sensors, cameras, and internet connections. Fifty had been installed in the city, a first batch of an expected 400, and the protesters were determined to take one down. The government had said the smart lampposts would be used only for benign purposes—that they'd take air quality measurements and assist with traffic control, and would not collect facial or other personal data. The protesters feared otherwise. When I spoke to them, many brought up what was happening to the Uyghurs in the Xinjiang region of China. Trapped in a massive surveillance net that hacks their phones and collects biometric data (including DNA samples from practically the whole population), the Uyghurs live under constant scrutiny and worse—Big Data along with traditional surveillance techniques have sent as many as a million people off to internment camps. Citizens of Hong Kong feared similar technologies would be used against them. Many wore face masks. They carried umbrellas, not just to shelter from the sun but also to block the view of CCTV cameras or the helicopters that flew overhead—or to huddle under as they assembled barricades. At the same time, this stream of young people carrying umbrellas and traveling on foot were anything but Luddites (at least as people usually use the term). They were quite attached to their tech. Like other decentralized movements before them—the protesters who amassed in the Arab Spring, under the banner of Occupy, in Istanbul's Gezi Park, and under the name Indignados in Spain—the demonstrators in Hong Kong were forever on their phones. They pulled them out to learn where the movement was making its next stand; they pulled them out to learn where to retreat after being teargassed; then they pulled them out to learn where everyone was regrouping for the next advance. They scrolled through Telegram, beaming with myriad protest groups—big ones conveying information about the whole movement and small ones that organized one neighborhood or another. They voted on LIHKG (a homegrown Reddit) to decide their next steps. I watched it all happen: The protesters would amass and the police would meet them in force. Then, in a blink, the demonstrators would move somewhere else, using the subway—when they could—to outrun the authorities. They would decide where to go next through online discussions and polls. It felt like magic. The Hong Kong protesters managed to form human chain 30 miles long, surprising even themselves. One day, inspired by a single post on LIHKG, the protesters decided to form a human chain. They would do it on the anniversary of the historic 1989 chain across the three Baltic states that demanded freedom from the Soviet Union. The Hong Kong protesters ran with the idea and managed to form a line of activists 30 miles long, surprising even themselves. They used apps to coordinate in real time, getting people to move from overly populated sections of the chain to ones that were more sparse. They held hands and sang in unison. In the middle of the event, someone had the idea that they should end with everyone covering one eye, in honor of a medic who had been shot in the eye just a few days earlier. At precisely 9 pm, I watched them all obscure one eye, perfectly coordinated. Move, countermove. The next day, authorities shut down the subway. And all throughout my time in Hong Kong, it was painfully clear how ubiquitous the surveillance was. Telegram includes a feature that allows you to see if a contact is a member of a group; that feature may well have exposed everyone's phone number to the authorities. (Telegram says it's fixing this.) Phones constantly pinged nearby cell phone towers, revealing locations. At one point, LIHKG was down due to a denial of service attack. It's unknown whether Beijing was behind the attack, but China's state-sponsored hackers certainly have the motive and the means (and then some) for such an exploit. Hong Kong Protests Memes Emma Grey Ellis Depth of Field Jason Parham Info Wars Louise Matsakis Realpolitik Peter Rubin and Will Knight This techno-evolutionary arms race between authorities and protesters isn't new—and it's not just playing out in authoritarian countries. Those smart lampposts are already sprouting up in many democracies or are being planned as part of smart-city initiatives. Those governments, too, promise they will be put to benign use. But once a surveillance infrastructure exists, governments and corporations will certainly be tempted to run with it. Facial recognition is being deployed all over the world. Biometric databases are expanding. Personal, financial, health, social, and other data is being collected by entities ranging from social media giants and apps to websites and retailers—anyone and everyone, it appears. And this data is being churned through to identify and target people individually—to sell things, yes, but also to spread misinformation. 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 Later that Saturday, the protesters used a couple of basic technologies, a handheld saw and a rope, to set upon a smart lamppost. As the post fell, cheers rose from the crowd. A jubilant moment isn't decisive, though. There will be more smart lampposts and more abuse. But the pessimism that abounds these days—as authoritarians have turned new technologies to their advantage—is likewise not decisive. It's still early. We can't predict who will win and how. That story is still to be written, by us. Zeynep Tufekci (@zeynep) is a WIRED contributor and a professor at the University of North Carolina at Chapel Hill. This article appears in the November issue. Subscribe now. The first smartphone war 7 cybersecurity threats that can sneak up on you “Forever chemicals” are in your popcorn— and your blood EVs fire up pyroswitches to cut risk of shock after a crash The spellbinding allure of Seoul's fake urban mountains 👁 Prepare for the deepfake era of video ; plus, check out the latest news on AI ✨ Optimize your home life with our Gear team’s best picks, from robot vacuums to affordable mattresses to smart speakers. Topics magazine-27.11 protests disinformation Vas Panagiotopoulos David Gilbert Dhruv Mehrotra Andy Greenberg Andrew Couts Dell Cameron Dell Cameron Lily Hay Newman 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 "

"Ex-Google Executive Opens a School for AI, With China's Help | WIRED"

"https://www.wired.com/story/ex-google-executive-opens-a-school-for-ai-with-chinas-help"

"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 Tom Simonite Business Ex-Google Executive Opens a School for AI, With China's Help Kai-Fu Lee, founder of Sinovation Ventures, says tension between the US and China around artificial intelligence "is not a weapons race, AI is more an enabler.” Giulia Marchi/Bloomberg/Getty Images Save this story Save Save this story Save Application Regulation Sector IT Research Technology Machine learning When China’s government said last summer it intends to surpass the US and lead the world in artificial intelligence by 2030, skeptics pointed to a major problem. Despite gobs of data from the world’s largest online population, lightweight privacy rules, and 8 million fresh college graduates in 2017, the country doesn’t have enough people skilled in AI to overtake America. This week Kai-Fu Lee, onetime head of Google’s operations in China, launched a new project to help close the country’s AI talent gap. His helpers include the Chinese government and some of North America’s leading computer scientists. The project is an example of how US and Chinese efforts to progress in AI are entangled, despite recent rhetoric about superpower technology rivalry. Lee was born in Taiwan, studied in the US, and began his career in AI research before stints as an executive at Silicon Graphics, Apple, and Microsoft. He led Google’s expansion in China until 2009, when he left to found an AI-centric investment firm now called Sinovation Ventures. The firm invests in both China and the US, and has its own AI research institute. At Peking University in Beijing Tuesday, Lee addressed 100 professors from Chinese science and engineering schools. Over the next four months the group will learn how to teach machine learning and other AI techniques, in a new annual program supported by Sinovation’s AI Institute, the University of Peking, and China’s Ministry of Education. Some of the newly trained professors will help with a second phase of the program this summer, in which 300 top students will get special training in AI from Lee and other experts. Cornell professor John Hopcroft, second from left, lectured at the opening day of a new AI training program backed by China's government at Peking University. Sinovation Ventures Artificial Intelligence Institute 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 Despite the program’s connection to China’s government, some of the experts helping Lee work for American institutions. Cornell Professor John Hopcroft joined Lee to teach on opening day this week. He received the Turing Award, considered the Nobel of computing in 1986 , and now does research on machine learning. Google’s leading AI researcher Geoff Hinton is slated to give a class via videolink this summer. In his four-hour lecture Tuesday, Hopcroft summarized for the assembled professors the contents of a machine learning course at a top US university. He’s made frequent trips to China over the past decade trying to help the country improve the quality of its university education, which he describes as a humanitarian project. “The opportunity in China is to make the world better for millions of people,” he says. Lee says his program will quickly expand the nation’s supply of programmers with AI experience. “If these professors each teach a class of 400 students in fall and spring, that would graduate thousands of students for employment in 2019,” he says. That could help Chinese companies competing to hire AI engineers—including startups in Lee’s investment portfolio. It also aligns with a key strand of China’s Next Generation Artificial Intelligence Development Plan announced last July. The plan envisions China’s economy, military, and society invigorated and empowered by artificial intelligence. The government is seeking to build on a recent surge in AI investments from China’s internet companies and others, which has created several startups worth over $1 billion in areas including facial recognition and new types of computer chips. Government support for AI in China includes new funding, government contracts, and access to some state data troves. Growing China’s AI talent base has also become a major theme, with the government supporting new programs from colleges and companies. Given that background, and recent friction between the US and China over technology and trade , Sinovation’s project might add fuel to concerns in Washington about an “ AI arms race ” between the countries. The US Trade Representative’s report justifying this week’s sanctions on $50 billion of Chinese imports said that one part of China’s AI plan is to use venture investments and other engagements with the US to draw technology back home. One hundred college professors from around China joined the program to improve how they teach AI skills to their students. Sinovation Ventures Artificial Intelligence Institute 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 Lee calls that framing “narrow minded.” He says companies and academics in both China and the US openly publish AI research papers and software. Google opened an AI research lab in China in December, saying it wants to collaborate more with the Chinese AI community. “This is not a weapons race, AI is more an enabler,” says Lee. That argument is somewhat shared by some in Washington. Bob Work, previously deputy secretary of defense in both the Obama and Trump administrations, chairs a new task force on AI at think tank the Center for a New American Security. At the launch event last month, he pushed back on use of the term “arms race” and said America’s greatest priority should be backing commercial development of AI. Elsa Kania, a researcher on the CNAS task force, says that could include taking pointers from Sinovation’s government-sponsored program in Beijing. “I would argue the United States should be doing the same,” she says. In 2016, the Obama White House produced a pair of reports on the potential of artificial intelligence that recommended investment in AI education and research. Nvidia, Intel, and several academics made similar pleas at congressional hearings on AI in February and March. So far, the Trump administration has shown little interest in the technology. Despite protests from some American officials, it's too late to stop China from becoming a power in artificial intelligence. The victory by an artificial-intelligence program from Chinese tech giant Tencent over a Go champion shows the country's gains in AI. As part of a national strategy, China is challenging Nvidia's dominance in chips used for artificial intelligence. Senior Editor X Topics China artificial intelligence Will Knight WIRED Staff Aarian Marshall Khari Johnson Paresh Dave Will Knight Gregory Barber 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 "

"Melinda Gates and Fei-Fei Li Want to Liberate AI from “Guys With Hoodies” | WIRED"

"https://www.wired.com/2017/05/melinda-gates-and-fei-fei-li-want-to-liberate-ai-from-guys-with-hoodies"

"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 Melinda Gates and Fei-Fei Li Want to Liberate AI from “Guys With Hoodies” Courtesy of Pivotal Save this story Save Save this story Save Artificial intelligence has a diversity problem. Too many of the people creating it share a similar background. To renowned researcher Fei-Fei Li , this paucity of viewpoints constitutes a crisis: “As an educator, as a woman, as a woman of color, as a mother, I’m increasingly worried,” she says. “AI is about to make the biggest changes to humanity, and we’re missing a whole generation of diverse technologists and leaders.” From the chair next to her, Melinda Gates affirms this, adding, “If we don’t get women and people of color at the table — real technologists doing the real work — we will bias systems. Trying to reverse that a decade or two from now will be so much more difficult, if not close to impossible.” Both women are powerful technologists. As chief scientist of artificial intelligence and machine learning for Google Cloud, Li is currently on sabbatical from Stanford, where she directs the Stanford Artificial Intelligence Lab. Gates studied artificial intelligence in the early days of the 1980s when when she was learning to code at Duke University. She spent a decade at Microsoft before leaving and later pursuing philanthropy. Now Gates is putting her mind and her money behind a national nonprofit that Li is helping launch: AI4All. The name says it all. AI4All will support educational programs designed to expose underrepresented high school students to artificial intelligence. I sat down with Gates and Li last week at Stanford University to talk about how to make AI research more appealing to women, why hoodies shouldn’t be tech’s status symbol, and what it takes to work in AI. Jessi Hempel : How did you get to know each other? Melinda Gates : If you’re at all interested in artificial intelligence, you’re going to hear about Fei-Fei’s work. I wanted to meet her and understand what she was doing, in particular, with some of her PhD students, and what it was like for a group of females to be in the field of AI. We met. Then Fei-Fei pulled together a group of women [studying AI]. Fei-Fei Li shows Melinda Gates around the lab. Courtesy of Pivotal Fei-Fei Li : Melinda, when I heard that you were starting to pay attention to AI, I really had that moment of thinking, “Finally. Finally, a world leader whose voice can be heard is a woman technologist and she is now paying attention to AI!” I have been in this space for many, many, many years as an educator as well as a technologist, and I’ve been having this increasing worry. As a technologist, I see how AI and the fourth industrial revolution will impact every aspect of people’s lives. If you look at what AI is doing at amazing tech companies like Microsoft, Google, and other companies, it’s increasingly exciting. 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 in the meantime, as an educator, as a woman, as a woman of color, as a mother, I’m increasingly worried. AI is about to make the biggest changes to humanity and we’re missing a whole generation of diverse technologists and leaders. So when I heard Melinda was paying attention to this, and your people reached out to me…you don’t know this, Melinda, but they reached out to me when my daughter was about four months old and I was home nursing. Melinda Gates : So been there. Fei-Fei Li : I was just so happy. We immediately arranged your visit and wanted to have a candid conversation. And I told the students, “You guys are all extremely passionate technologists, but you are also still blazing the trail. Be candid with Melinda about your experiences.” Melinda Gates : And that was fantastic. I just want to echo one thing that Fei-Fei said: If we don’t get women and people of color at the table — real technologists doing the real work — we will bias systems. Trying to reverse that a decade or two from now will be so much more difficult, if not close to impossible. This is the time to get women and diverse voices in so that we build it properly, right? And it can be great. It’s going to be ubiquitous. It’s going to be awesome. But we have to have people at the table. Fei-Fei Li : Exactly, because AI is a technology that gets so close to everything we care about. It’s going to carry the values that matter to our lives, be it the ethics, the bias, the justice, or the access. If we don’t have the representative technologists of humanity sitting at the table, the technology is inevitably not going to represent all of us. Jessi Hempel : We have already seen some of the consequences of not including diverse voices in the beginning stages of development. Is it already too late? Melinda Gates : I wouldn’t say it’s too late but I would say that that car is speeding down the road very quickly. This is one of the reasons Fei-Fei and I are so interested in thinking about how you get female technologists into this field. 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 Jessi Hempel : What came of your conversations? Fei-Fei Li : When I was coming out of maternity leave, I was thinking deeply about what I could do to really help this generation. I see this as one of the most important efforts I can make. Three years ago, I had started a test program along with my former PhD student, Olga Russakovsky. It was a pilot program called SAILORS, Stanford Artificial Intelligence Lab Outreach Summer Program. We invited high school ninth graders in the Bay Area. It’s a non-residential program focusing on young women, and inviting them to spend two weeks within the AI lab. There are two pieces of SAILORS. One: We have a strong hypothesis that the pipeline issue is deeply affected by the way that technology is presented to young students. In Silicon Valley—I’ve lived here for 10 years. I love Silicon Valley, but there is a dominant voice of, “Tech is cool. Tech is geeky. Tech is a guy with a hoodie.” Melinda Gates : Yes! Fei-Fei Li : The guys with hoodies have changed our world. But they’re not the only technologists. That’s not the only way to motivate people, especially young women with many choices. [They’re thinking], “I can be a doctor at the bedside saving people’s lives. I can be a journalist in the most needed area of the world giving the people a voice. Why should I be in AI or CS if all I heard is you can have a hoodie and look cool?” We add a humanistic mission into the teaching of the technology that goes to the core of what these young people are longing for. So for example, as a research project, we’re doing self-running cars in the robotics team for SAILORS. We wrapped it in the context of aging society, because a self-driving car, of course, is cool technology, but one of the populations it’s going to help the most is our increasing aging society. Jessi Hempel: How did you decide to target ninth graders? Stanford students demo technology for Melinda Gates. Courtesy of Pivotal Fei-Fei Li : We spent a lot of time looking at past data. We realized that around early high school years is when students start to think about their college major. They’re questioning: Who am I; what impact can I make on the world? The program was very popular and successful. We have amazing young women. The only problem is, it’s not big enough. So then I started thinking, we really ought to start to spread it nationally. And this is when we started collaborating with Melinda. We started this organization called AI4All. It’s still, I would say, stealth-ish. 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 Melinda and Jensen Huang, the founder of NVIDIA, are putting in the seed money for us. AI4All is focusing on spreading a SAILORS model—the education of AI with humanistic mission to diverse students—to different campuses and companies. Jessi Hempel : Have you started rolling it out? Fei-Fei Li : We officially started in March. Five universities are partnering with us: Berkeley, Carnegie Mellon University, Princeton, Boston University, and Simon Fraser. They’re going to start their own chapters of SAILORS. They will tailor it to different local communities. For example, Berkeley will be more robotics focused, and will focus on low-income students. The Princeton program will be more about racial diversity, because New Jersey has a strong African-American community. Jessi Hempel : What are the major barriers to launching something like this? Fei-Fei Li : We have so few AI technical leaders who are diverse themselves. Also, they’re busy doing the things like building a startup or making money off publishing papers. This kind of education is longterm. Education is thankless for a long time. Jessi Hempel : Melinda, what insight do you have from funding other organizations that could help AI4All be successful? Melinda Gates : Fei-Fei is in the process of hiring an executive director, and she’s in a very fortunate situation. She’s got a couple of really strong candidates. But we’re talking about the skills you need in that executive director. Because sometimes, and [Bill and I] certainly made this mistake, both ourselves and with other organizations, you think you know what you want. You have this really shiny candidate, and they have all these other skills. But if they’re actually not good at hiring, recruiting, retention, and building an organization, you’re not going to succeed. Jessi Hempel : Melinda, when we spoke last fall , you put out a call out to figure out where to focus your resources as you turned your attention to helping women succeed in tech. Is this the first piece of that effort? Are we going to see more of it? Melinda Gates : This is one piece of it. You’ll see more of it. Definitely. Since you and I talked, we’re funding Girls Who Code more, because I think that’s another model, for sure, for getting the pipeline filled. 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 I’m also looking at workplace diversity. I’ll make some investments there. There’s a fantastic economist at Harvard, Iris Bohnet. She does behavioral economics and she’s looking at how you design diversity into a system. She’s the person who has talked about how in orchestras , women couldn’t get a first chair. Finally, when [audition judges] put a curtain down so that people on the other side of the curtain couldn’t see who was playing the violin on the other side, the numbers went up a little bit. But they didn’t go up as much as she thought they might. She realized that the person on the other side of the curtain interviewing could hear the footsteps of the person walking across the stage. Once they fixed that, the number of female first chairs went up significantly. So in coding, when a professor looks at a female’s code or a male’s code, we’ve seen the bias numbers. You just have an inherent bias. When it’s anonymized, guess what? The women do just as well as the men. I know a young man who’s working on a fantastic young startup where you submit your code with no name. There are seven great coders reviewing the code on the other side that was submitted anonymously. And the last thing I’ll just say, the other place that I’m investing is NCWIT [ National Center for Women and Information Technology ]. They’re doing a great job of designing things into that first computer science course a student takes that attract women. Jessi Hempel : There are already many women and people of color working in the field. How do we draw attention to their work? Fei-Fei Li : Oh boy. I just tell media, please find a list of AI technologists and give them a voice, because it’s so convenient to pick up the phone and call that guy that is always out there. There are women and other diverse technologists. And if you need help finding them, there are people like me. I’m happy to supply you with a list of AI technologists who have diverse backgrounds. I think that voice needs to be heard. Melinda Gates : And the other thing I would just say for readers is that this is an exciting field. AI is going to change so much. So we shouldn’t be afraid of it. We have to be smart about how it’s done. But you can learn AI. And you can learn how to be part of the industry. Go find somebody who can explain things to you. If you’re at all interested, lean in and find somebody who can teach you. Jessi Hempel : I’m so glad you said that, because I think sometimes we think, well, you’ve got to get the ninth grader interested because it’s too late for the rest of us who are mid-career. Melinda Gates : And I think sometimes when you hear a big technologist talking about AI, you think, “Oh, only he could do it.” No. Everybody can be part of it. Fei-Fei Li : Our culture has a tendency to call a few of them geniuses. And then mortals just think, “We’re not geniuses.” It’s not true. If someone has a fantastic biology background, he or she can contribute in AI and health care. AI has many aspects. AI is everywhere. It’s not that big, scary thing in the future. AI is here with us. Senior Writer Facebook X Topics Backchannel Steven Levy Vauhini Vara Christopher Beam Virginia Heffernan Amit Katwala Lexi Pandell Samanth Subramanian Lindsay Jones 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 "

"If We Want Humane AI, It Has to Understand All Humans | WIRED"

"https://www.wired.com/2015/10/if-we-want-humane-ai-it-has-to-understand-all-humans"

"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 Davey Alba Business If We Want Humane AI, It Has to Understand All Humans Kelsey Dake Save this story Save Save this story Save The first picture flashes on the screen. “A man is standing next to an elephant,” a robotic voice intones. Another picture appears. “A person sitting at a table with a cake.” Those descriptions are obvious enough to a person. What makes them remarkable is that a human is not supplying the descriptions at all. Instead, the tech behind this system is cutting-edge artificial intelligence: a computer that can “see” pictures. Fei-Fei Li, director of the Stanford Artificial Intelligence Lab, is standing on a lit stage in a dark auditorium showing off the advanced object-recognition system she and her fellow researchers built. But as impressive as the system is, Li grows more critical as her presentation unfolds. She says that even if the computer is technically accurate, it could do more. The computer may be able to describe in simple, literal terms what it "sees" in the pictures. But it can't describe the stories behind the pictures. The person sitting at the table, for instance, is actually a young boy—Li’s son, Leo. Li explains that he is wearing his favorite T-shirt. It’s Easter, and we non-computers can all see how happy he is. Blake Farrington “I think of Leo constantly and the future world he will live in,” Li tells the audience at TED in a video that's been viewed more than 1.2 million times. In Li’s ideal future, where machines can see, they won’t just be built for maximum efficiency. They’ll be built for empathetic purposes. Artificial eyes, for instance, could help doctors diagnose and take care of patients. If robot cars had empathy, they could run smarter and safer on roads. (Imagine if the builders of self-driving cars used algorithms that didn’t account for the safety of pedestrians and passengers.) Robots, Li says, could brave disaster zones to save victims. Li is one of the world’s foremost experts on computer vision. She was involved in building two seminal databases, Caltech 101 and ImageNet, that are still widely used by AI researchers to teach machines how to categorize different objects. Given her stature in the field, it’s hard to overstate the importance of her humanitarian take on artificial intelligence. That's because AI is finally entering the mainstream. In recent years, Internet giants like Google, Facebook, and Microsoft have doubled down on AI, using brain-like systems to automatically recognize faces in photos, instantly translate speech from one language to another, target ads and more. And simpler forms of AI are now pervasive. Amazon uses a form of AI in recommending products you might like on its popular retail site. Yet as AI becomes ever more popular, it’s also going through a crisis of sorts. Research from the Bureau of Labor Statistics shows that by 2020, the US economy will have 1 million more computer-science-related jobs available than graduating students qualified to fill them—a gap we’ll soon desperately need to fill. At the same time, notable figures like Elon Musk, Stephen Hawking, and Bill Gates have publicly worried that artificial intelligence could evolve to a point where humanity will not be able to control it. A kind of doomsday strain of thinking around AI might be a little exaggerated, according to Li. But it does point to the importance of being mindful about how AI technology develops going forward—and 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 In a tech industry—and research community—that is still largely white and male , the danger arises of a less-than-humane AI that doesn’t take everyone’s needs and perspectives into account. Even as more people join the conversation around diversity in tech, recent examples show what happens when products aren’t designed to serve the most diverse population possible. In 2014, Apple introduced HealthKit, which the company presented as a comprehensive tracking system for human health. But it seemed to have forgotten about humans who have periods , at least until it corrected the oversight with a software update a year later. The Apple incident wasn’t specifically AI going awry due to diversity problems, but this July, it did at Google: The search giant apologized profusely when its new Photos app, which automatically tags pictures using its own artificial intelligence software, identified an African-American couple as “gorillas.” (“This is 100 percent not OK,” said Google executive Yonatan Zunger after the company was made aware of the error.) “The diversity crisis is the same crisis we talk about as a society in asking, ‘Is technology soulless?’” Li says, speaking frankly about her disappointment in the AI community being less than welcoming to members of underrepresented minorities. Among 15 full-time faculty members in her department, she’s the only woman. Elsewhere within the industry, the 44-person Facebook AI research team includes just five women. At Baidu, the 42-person AI team includes three female researchers. In her own lab, Li says there are few students of color. These numbers aren’t just bad in themselves; they bode badly for the prospects of developing truly humane AI. “I think the combination of being a professor and becoming a mother got me thinking really deeply about these issues,” says Li, who was born in China and migrated to the US when she was 16. “You feel so much more responsible for the future generations.” Li holds Friday afternoon wine and cheese sessions for women in AI every other week at her office. Recently, she also greenlit and helped carry out a one-of-a-kind project: the Stanford Artificial Intelligence Laboratory’s Outreach Summer program (SAILORS), the country’s first AI summer camp for ninth-grade girls. “This is a field that’s producing technology that is so relevant to every aspect of human lives,” Li says. As such, it’s vital that people doing the work have the perspective to make such a crucial technology relevant to every human’s life. “To bring diversity into a highly innovative and impactful field fundamentally has good value.” Topics artificial intelligence diversity Women in tech Steven Levy David Gilbert Kari McMahon Nelson C.J. Peter Guest Andy Greenberg Joel Khalili 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 "

"Barack Obama on Artificial Intelligence, Autonomous Cars, and the Future of Humanity | WIRED"

"https://www.wired.com/2016/10/president-obama-mit-joi-ito-interview"

"WIRED Logo The President in Conversation With MIT’s Joi Ito and WIRED’s Scott Dadich Click to share this story on Facebook Click to share this story on Twitter Click to email this story Click to comment on this story. (will open new tab) Joi Ito, Scott Dadich, and President Barack Obama photographed in the Roosevelt Room of the White House on August 24, 2016. Photographs by Christopher Anderson/Magnum Photos for WIRED IT’S HARD TO think of a single technology that will shape our world more in the next 50 years than artificial intelligence. As machine learning enables our computers to teach themselves, a wealth of breakthroughs emerge, ranging from medical diagnostics to cars that drive themselves. A whole lot of worry emerges as well. Who controls this technology? Will it take over our jobs? Is it dangerous? President Obama was eager to address these concerns. The person he wanted to talk to most about them? Entrepreneur and MIT Media Lab director Joi Ito. So I sat down with them in the White House to sort through the hope, the hype, and the fear around AI. That and maybe just one quick question about Star Trek. — Scott Dadich Scott Dadich: Thank you both for being here. How’s your day been so far, Mr. President? Barack Obama: Busy. Productive. You know, a couple of international crises here and there. Dadich: I want to center our conversation on artificial intelligence, which has gone from science fiction to a reality that’s changing our lives. When was the moment you knew that the age of real AI was upon us? November 2016. Subscribe to WIRED. Obama: My general observation is that it has been seeping into our lives in all sorts of ways, and we just don’t notice; and part of the reason is because the way we think about AI is colored by popular culture. There’s a distinction, which is probably familiar to a lot of your readers, between generalized AI and specialized AI. In science fiction, what you hear about is generalized AI, right? Computers start getting smarter than we are and eventually conclude that we’re not all that useful, and then either they’re drugging us to keep us fat and happy or we’re in the Matrix. My impression, based on talking to my top science advisers, is that we’re still a reasonably long way away from that. It’s worth thinking about because it stretches our imaginations and gets us thinking about the issues of choice and free will that actually do have some significant applications for specialized AI, which is about using algorithms and computers to figure out increasingly complex tasks. We’ve been seeing specialized AI in every aspect of our lives, from medicine and transportation to how electricity is distributed, and it promises to create a vastly more productive and efficient economy. If properly harnessed, it can generate enormous prosperity and opportunity. But it also has some downsides that we’re gonna have to figure out in terms of not eliminating jobs. It could increase inequality. It could suppress wages. Joi Ito: This may upset some of my students at MIT, but one of my concerns is that it’s been a predominately male gang of kids, mostly white, who are building the core computer science around AI, and they’re more comfortable talking to computers than to human beings. A lot of them feel that if they could just make that science-fiction, generalized AI, we wouldn’t have to worry about all the messy stuff like politics and society. They think machines will just figure it all out for us. Obama: Right. Ito: But they underestimate the difficulties, and I feel like this is the year that artificial intelligence becomes more than just a computer science problem. Everybody needs to understand that how AI behaves is important. In the Media Lab we use the term extended intelligence 1. Because the question is, how do we build societal values into AI? 1 Extended intelligence is using machine learning to extend the abilities of human intelligence. Obama: When we had lunch a while back, Joi used the example of self-driving cars. The technology is essentially here. We have machines that can make a bunch of quick decisions that could drastically reduce traffic fatalities, drastically improve the efficiency of our transpor­tation grid, and help solve things like carbon emissions that are causing the warming of the planet. But Joi made a very elegant point, which is, what are the values that we’re going to embed in the cars? There are gonna be a bunch of choices that you have to make, the classic problem being: If the car is driving, you can swerve to avoid hitting a pedestrian, but then you might hit a wall and kill yourself. It’s a moral decision, and who’s setting up those rules? 2 The car trolley problem is a 2016 MIT Media Lab study in which respondents weighed certain lose-lose situations facing a driverless car. E.g., is it better for five passengers to die so that five pedestrians can live, or is it better for the passengers to live while the pedestrians die? Ito: When we did the car trolley problem 2 , we found that most people liked the idea that the driver and the passengers could be sacrificed to save many people. They also said they would never buy a self-driving car. [ Laugh s.] Dadich: As we start to get into these ethical questions, what is the role of government? Obama: The way I’ve been thinking about the regulatory structure as AI emerges is that, early in a technology, a thousand flowers should bloom. And the government should add a relatively light touch, investing heavily in research and making sure there’s a conversation between basic research and applied research. As technologies emerge and mature, then figuring out how they get incorporated into existing regulatory structures becomes a tougher problem, and the govern­ment needs to be involved a little bit more. Not always to force the new technology into the square peg that exists but to make sure the regulations reflect a broad base set of values. Otherwise, we may find that it’s disadvantaging certain people or certain groups. 3 Temple Grandin is a professor at Colorado State University who is autistic and often speaks on the subject. Ito: I don’t know if you’ve heard of the neurodiversity movement, but Temple Grandin 3 talks about this a lot. She says that Mozart and Einstein and Tesla would all be considered autistic if they were alive today. Obama: They might be on the spectrum. Ito: Right, on the spectrum. And if we were able to eliminate autism and make everyone neuro-­normal, I bet a whole slew of MIT kids would not be the way they are. One of the problems, whether we’re talking about autism or just diversity broadly, is when we allow the market to decide. Even though you probably wouldn’t want Einstein as your kid, saying “OK, I just want a normal kid” is not gonna lead to maximum societal benefit. Obama: That goes to the larger issue that we wrestle with all the time around AI. Part of what makes us human are the kinks. They’re the mutations, the outliers, the flaws that create art or the new invention, right? We have to assume that if a system is perfect, then it’s static. And part of what makes us who we are, and part of what makes us alive, is that we’re dynamic and we’re surprised. One of the challenges that we’ll have to think about is, where and when is it appropriate for us to have things work exactly the way they’re supposed to, without surprises? Dadich: When we’re talking about that extended intelligence as it applies to government, private industry, and academia, where should the center of that research live, if there even is a center? Ito: I think MIT would argue that it should be at MIT. [ Laughs. ] Historically it probably would have been a group of academics with help from a government. But right now, most of the billion-dollar labs are in business. Obama: We know the guys who are funding them, and if you talk to Larry Page or others, their general attitude, understandably, is, “The last thing we want is a bunch of bureaucrats slowing us down as we chase the unicorn out there.” Part of the problem that we’ve seen is that our general commitment as a society to basic research has diminished. Our confidence in collective action has been chipped away, partly because of ideology and rhetoric. The analogy that we still use when it comes to a great technology achievement, even 50 years later, is a moon shot. And somebody reminded me that the space program was half a percent of GDP. That doesn’t sound like a lot, but in today’s dollars that would be $80 billion that we would be spending annually … on AI. Right now we’re spending probably less than a billion. That undoubtedly will accelerate, but part of what we’re gonna have to understand is that if we want the values of a diverse community represented in these breakthrough technologies, then government funding has to be a part of it. And if government is not part of financing it, then all these issues that Joi has raised about the values embedded in these technologies end up being potentially lost or at least not properly debated. Dadich: You bring up a really interesting tension that Joi has written about: the difference between innovation that happens in the margins and the innovation that happens in something like the space program. How do we make sure the transmission of all these ideas can happen? SCROLL DOWN Obama: I’ve tried to emphasize that just because the government is financing it and helping to collect the data doesn’t mean that we hoard it or only the military has it. To give a very concrete example: Part of our project in precision medicine is to gather a big enough database of human genomes from a diverse enough set of Americans. But instead of giving money to Stanford or Harvard, where they’re hoarding their samples, we now have this entire genetic database that everybody has access to. There is a common set of values, a common architecture, to ensure that the research is shared and not monetized by one group. 4 Nick Bostrom is a renowned philosopher at the University of Oxford who has warned of the potential dangers of AI. Dadich: But there are certainly some risks. We’ve heard from folks like Elon Musk and Nick Bostrom 4 who are concerned about AI’s potential to outpace our ability to understand it. As we move forward, how do we think about those concerns as we try to protect not only ourselves but humanity at scale? Obama: Let me start with what I think is the more immediate concern—it’s a solvable problem in this category of specialized AI, and we have to be mindful of it. If you’ve got a computer that can play Go, a pretty complicated game with a lot of variations, then developing an algorithm that lets you maximize profits on the New York Stock Exchange is probably within sight. And if one person or organization got there first, they could bring down the stock market pretty quickly, or at least they could raise questions about the integrity of the financial markets. Then there could be an algorithm that said, “Go penetrate the nuclear codes and figure out how to launch some missiles.” If that’s its only job, if it’s self-teaching and it’s just a really effective algorithm, then you’ve got problems. I think my directive to my national security team is, don’t worry as much yet about machines taking over the world. Worry about the capacity of either nonstate actors or hostile actors to penetrate systems, and in that sense it is not conceptually different than a lot of the cybersecurity work we’re doing. It just means that we’re gonna have to be better, because those who might deploy these systems are going to be a lot better now. Ito: I generally agree. The only caveat is that there are a few people who believe that there is a fairly high-percentage chance that a generalized AI will happen in the next 10 years. But the way I look at it is that in order for that to happen, we’re going to need a dozen or two different breakthroughs. So you can monitor when you think these breakthroughs will happen. Obama: And you just have to have somebody close to the power cord. [ Laughs. ] Right when you see it about to happen, you gotta yank that electricity out of the wall, man. Ito: What’s important is to find the people who want to use AI for good—communities and leaders—and figure out how to help them use it. Obama: Traditionally, when we think about security and protecting ourselves, we think in terms of armor or walls. Increasingly, I find myself looking to medicine and thinking about viruses, antibodies. Part of the reason why cybersecurity continues to be so hard is because the threat is not a bunch of tanks rolling at you but a whole bunch of systems that may be vulnerable to a worm getting in there. It means that we’ve got to think differently about our security, make different investments that may not be as sexy but may actually end up being as important as anything. What I spend a lot of time worrying about are things like pandemics. You can’t build walls in order to prevent the next airborne lethal flu from landing on our shores. Instead, what we need to be able to do is set up systems to create public health systems in all parts of the world, click triggers that tell us when we see something emerging, and make sure we’ve got quick protocols and systems that allow us to make vaccines a lot smarter. So if you take a public health model, and you think about how we can deal with, you know, the problems of cybersecurity, a lot may end up being really helpful in thinking about the AI threats. Ito: And just one thing that I think is interesting is when we start to look at the microbiome. There’s a lot of evidence to show that introducing good bacteria to fight bad bacteria—to not sterilize—is a strategy. 5 The first pets. Portuguese water dogs. Very cute. Obama: Absolutely. I still don’t let Sunny and Bo 5 lick me, because when I walk them on the side lawn, some of the things I see them picking up and chewing on, I don’t want that, man. [ Laughs. ] Ito: We have to rethink what clean means, and it’s similar whether you’re talking about cybersecurity or national security. I think that the notion that you can make strict orders or that you can eliminate every possible pathogen is difficult. Dadich: Is there also a risk that this creates a new kind of arms race? Obama: I think there’s no doubt that developing international norms, protocols, and verification mechanisms around cybersecurity generally, and AI in particular, is in its infancy. Part of what makes this an interesting problem is that the line between offense and defense is pretty blurred. And at a time when there’s been a lot of mistrust built up about government, that makes it difficult. When you have countries around the world who see America as the preeminent cyberpower, now is the time for us to say, “We’re willing to restrain ourselves if you are willing to restrain yourselves.” The challenge is the most sophisticated state actors—Russia, China, Iran—don’t always embody the same values and norms that we do. But we’re gonna have to surface this as an international issue in order for us to be effective. Related Stories Building AI Is Hard—So Facebook Is Building AI That Builds AI By Cade Metz What the AI Behind AlphaGo Can Teach Us About Being Human By By Cade Metz To Make AI More Human, Teach It to Chitchat By Clive Thompson Ito: I think we’re in a golden period where people want to talk to each other. If we can make sure that the funding and the energy goes to support open sharing, there is a lot of upside. You can’t really get that good at it in a vacuum, and it’s still an international community for now. Obama: I think Joi is exactly right, and that’s why we’ve been convening a series of meetings with everybody who’s interested in this. One thing that we haven’t talked about too much, and I just want to go back to, is we really have to think through the economic implications. Because most people aren’t spending a lot of time right now worrying about singularity—they are worrying about “ Well, is my job going to be replaced by a machine ?” I tend to be on the optimistic side—historically we’ve absorbed new technologies, and people find that new jobs are created, they migrate, and our standards of living generally go up. I do think that we may be in a slightly different period now, simply because of the pervasive applicability of AI and other technologies. High-skill folks do very well in these systems. They can leverage their talents, they can interface with machines to extend their reach, their sales, their products and services. Low-wage, low-skill individuals become more and more redundant, and their jobs may not be replaced, but wages are suppressed. And if we are going to successfully manage this transition, we are going to have to have a societal conversation about how we manage this. How are we training and ensuring the economy is inclusive if, in fact, we are producing more than ever, but more and more of it is going to a small group at the top? How do we make sure that folks have a living income? And what does this mean in terms of us supporting things like the arts or culture or making sure our veterans are getting cared for? The social compact has to accommodate these new technologies, and our economic models have to accommodate them. SCROLL DOWN Ito: It’s actually nonintuitive which jobs get displaced, because I would bet if you had a computer that understood the medical system, was very good at diagnostics and such, the nurse or the pharmacist is less likely than the doctor to be replaced—they are less expensive. There are actually very high-level jobs, things like lawyers or auditors, that might disappear. Whereas a lot of the service businesses, the arts, and occupations that computers aren’t well suited for won’t be replaced. I don’t know what you think about universal basic income 6 , but as we start to see people getting displaced there’s also this idea that we can look at other models—like academia or the arts, where people have a purpose that isn’t tied directly to money. I think one of the problems is that there’s this general notion of, how can you be smart if you don’t have any money? In academia, I see a lot of smart people without money. 6 Universal basic income is a concept where all citizens receive at least a living wage, provided by the government as a form of social security. Obama: You’re exactly right, and that’s what I mean by redesigning the social compact. Now, whether a universal income is the right model—is it gonna be accepted by a broad base of people?—that’s a debate that we’ll be having over the next 10 or 20 years. You’re also right that the jobs that are going be displaced by AI are not just low-skill service jobs; they might be high-skill jobs but ones that are repeatable and that computers can do. What is indisputable, though, is that as AI gets further incorporated, and the society potentially gets wealthier, the link between production and distribution, how much you work and how much you make, gets further and further attenuated—the computers are doing a lot of the work. As a consequence, we have to make some tougher decisions. We underpay teachers, despite the fact that it’s a really hard job and a really hard thing for a computer to do well. So for us to reexamine what we value, what we are collectively willing to pay for—whether it’s teachers, nurses, caregivers, moms or dads who stay at home, artists, all the things that are incredibly valuable to us right now but don’t rank high on the pay totem pole—that’s a conversation we need to begin to have. Dadich: Mr. President, what technology are you looking at to solve the biggest challenges that you see in government? Obama: There is a whole bunch of work we have to do around getting government to be more customer friendly and making it at least as easy to file your taxes as it is to order a pizza or buy an airline ticket. Whether it’s encouraging people to vote or dislodging Big Data so that people can use it more easily or getting their forms processed online more simply—there’s a huge amount of work to drag the federal government and state governments and local governments into the 21st century. The gap between the talent in the federal government and the private sector is actually not wide at all. The technology gap, though, is massive. When I first got here I always imagined the Situation Room would be this supercool thing, like Tom Cruise in Minority Report , where he’d be moving around stuff. It’s not like that, at all. [ Laughs. ] Particularly when it comes to hunting down terrorists on the other side of the globe, the movies display this omniscience that we possess somehow, and it’s—it’s just not there yet, and it has been drastically underfunded and not properly designed. In terms of the broader questions around technology, I am a firm believer that if we get climate change right, if we’re able to tap the brakes and figure out how we avoid a 6-foot rise in the oceans, that humanity is gonna figure stuff out. I’m pretty optimistic. And we’ve done a lot of good work, but we’ve got a long way to go. Figuring out how we regulate connectivity on the Internet in a way that is accountable, transparent, and safe, that allows us to get at the bad guys but ensures that the government does not possess so much power in all of our lives that it becomes a tool for oppression—we’re still working on that. Some of this is a technological problem, with encryption being a good example. I’ve met with civil libertarians and national security people, over and over and over again. And it’s actually a nutty problem, because no one can give me a really good answer in terms of how we reconcile some of these issues. Since this is a frontiers issue, the last thing I should mention is that I’m still a big space guy, and figuring out how to move into the next generation of space travel is something that we’re significantly underfunding. There’s some good work being done by the private sector, because increasingly it has displaced government funding on some of the “What the heck, why not?” ventures, the crazy ideas. When we think about spaceflight, we’re still thinking about basically the same chemical reactions we were using back in the Apollo flights. Fifty years later and it seems like we should—I don’t know if dilithium crystals 7 are out there—but, you know, we should be getting some breakthroughs. 7 Dilithium crystals are the material powering faster-than-light warp drives in almost all Federation starships. Dadich: I understand you’re a Star Trek fan. That was a show inspired by a utopian view of technology—what about it shaped your vision of the future? Obama: I was a sucker for Star Trek when I was a kid. They were always fun to watch. What made the show lasting was it wasn’t actu­ally about technology. It was about values and relationships. Which is why it didn’t matter that the special effects were kind of cheesy and bad, right? They’d land on a planet and there are all these papier-mâché boulders. [ Laughs. ] But it didn’t matter because it was really talking about a notion of a common humanity and a confidence in our ability to solve problems. A recent movie captured the same spirit— The Martian. Not because it had a hugely complicated plot, but because it showed a bunch of different people trying to solve a problem. And employing creativity and grit and hard work, and having confidence that if it’s out there, we can figure it out. That is what I love most about America and why it continues to attract people from all around the world for all of the challenges that we face, that spirit of “ Oh, we can figure this out. ” And what I value most about science is this notion that we can figure this out. Well, we’re gonna try this—if it doesn’t work, we’re gonna figure out why it didn’t work and then we’re gonna try something else. And we will revel in our mistakes, because that is gonna teach us how to ultimately crack the code on the thing that we’re trying to solve. And if we ever lose that spirit, then we’re gonna lose what is essential about America and what I think is essential about being human. Ito: I totally agree—I love the optimism of Star Trek. But I also think the Federation is amazingly diverse, the crew is diverse, and the bad guys aren’t usually evil—they’re just misguided. Obama: Star Trek , like any good story, says that we’re all complicated, and we’ve all got a little bit of Spock and a little bit of Kirk [ laughs ] and a little bit of Scotty, maybe some Klingon in us, right? But that is what I mean about figuring it out. Part of figuring it out is being able to work across barriers and differences. There’s a certain faith in rationality, tempered by some humility. Which is true of the best art and true of the best science. The sense that we possess these incredible minds that we should use, and we’re still just scratching the surface, but we shouldn’t get too cocky. We should remind ourselves that there’s a lot of stuff we don’t know. 1 Extended intelligence is using machine learning to extend the abilities of human intelligence. 2 The car trolley problem is a 2016 MIT Media Lab study in which respondents weighed certain lose-lose situations facing a driverless car. E.g., is it better for five passengers to die so that five pedestrians can live, or is it better for the passengers to live while the pedestrians die? 3 Temple Grandin is a professor at Colorado State University who is autistic and often speaks on the subject. 4 Nick Bostrom is a renowned philosopher at the University of Oxford who has warned of the potential dangers of AI. 5 The first pets. Portuguese water dogs. Very cute. 6 Universal basic income is a concept where all citizens receive at least a living wage, provided by the government as a form of social security. 7 Dilithium crystals are the material powering faster-than-light warp drives in almost all Federation starships. Scott Dadich ( @sdadich ) is the editor in chief of WIRED. This article appears in the November 2016 issue. This interview has been edited and condensed. ILLUSTRATIONS BY JOE MCKENDRY. GROOMING BY JACKIE WALKER. Related Stories The Frontiers Issue, Guest-Edited by President Barack Obama Soon We Won’t Program Computers. We’ll Train Them Like Dogs We Take a Ride in the Self-Driving Uber Now Roaming Pittsburgh Meet Moxie Marlinspike, the Anarchist Bringing Encryption to All of Us What if Star Trek Had Never Existed? Wired Facebook Wired Twitter Wired Pinterest Wired Youtube Wired Tumblr Wired Instagram Login Subscribe Advertise Site Map Press Center FAQ Customer Care Contact Us T-Shirt Collection Newsletter Wired Staff Jobs RSS Use of this site constitutes acceptance of our user agreement (effective 3/21/12) and privacy policy (effective 3/21/12). Affiliate link policy. Your California privacy rights. The material on this site may not be reproduced, distributed, transmitted, cached or otherwise used, except with the prior written permission of Condé Nast. "

"Inside the Senate’s Private AI Meeting With Tech’s Billionaire Elites | WIRED"

"https://www.wired.com/story/senate-ai-forum-musk-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 Matt Laslo Khari Johnson Business Inside the Senate’s Private AI Meeting With Tech’s Billionaire Elites Photograph: Chip Somodevilla/Getty Images Save this story Save Save this story Save US senators are proving slow studies when it comes to the generative artificial intelligence tools that are poised to upend life as we know it. But they’ll be tested soon—and the rest of us through them—if their new private tutors are to be trusted. In a historic first , yesterday upwards of 60 senators sat like school children—not allowed to speak or even raise their hands—in a private briefing where some 20 Silicon Valley CEOs, ethicists, academics, and consumer advocates prophesied about AI’s potential to upend, heal, or even erase life as we knew it. “It’s important for us to have a referee,” Elon Musk, the CEO of Tesla, SpaceX, and X (formerly Twitter), told a throng of paparazzi-like press corps waiting on the sidewalk outside the briefing. “[It] may go down in history as very important to the future of civilization.” The weight of the moment is lost on no one, especially after Musk warned senators inside the room of the “civilizational risks” of generative AI. As many senators grapple with AI basics, there’s still time to influence the Senate’s collective thinking before lawmakers try to do what they’ve failed to do in recent years: regulate the emerging disruptive tech. Inside the briefing room there was consensus on the dais that the federal government’s regulatory might is needed. At one point, Senate Majority Leader Chuck Schumer, the New York Democrat who organized the briefing, asked his assembled guests, “Does the government need to play a role in regulating AI?” “Every single person raised their hand, even though they had diverse views,” Schumer continued. “So that gives us a message here: We have to try to act, as difficult as the process may be.” The raising of diverse hands felt revelatory to many. “I think people all agreed that this is something that we need the government’s leadership on,” said Sam Altman, CEO of OpenAI, the maker of ChatGPT. “Some disagreement about how it should happen, but unanimity [that] this is important and urgent.” The devilish details are haunting, though. Because generative AI is so all-encompassing, a debate over regulating it can quickly expand to include every divisive issue under the sun, something that was on display in the briefing right alongside the show of unity, according to attendees who spoke to WIRED. 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 the surprise of many, the session was replete with specifics. Some attendees brought up their need for more highly skilled workers, while Microsoft cofounder Bill Gates focused on feeding the globe’s hungry. Some envision a sweeping new AI agency, while others argue that existing entities—like the National Institute of Standards and Technology (NIST), which was mentioned by name—are better suited to regulate in real time (well, AI time). “It was a very good pairing. Better than I expected,” says Senator Cynthia Lummis, a Wyoming Republican who attended the briefing. “I kind of expected it to be a nothingburger, and I learned a lot. I thought it was extremely helpful, so I’m really glad I went. Really glad.” Like many in the room, Lummis’ ears perked when a speaker called out Section 230 of the 1996 Communications Decency Act —a legislative shield that protects tech firms from liability for content users publish on their social media platforms. “One of the speakers said, ‘Make users and creators of the technology accountable, not immune from liability,’” Lummis says, reading from her exhaustive hand-scribbled notes. “In other words, he specifically said, ‘Do not create a Section 230 for AI.’ Lummis adds that the speaker who proposed this—she didn’t identify him— “was sitting next to [Meta CEO Mark] Zuckerberg and he said it—one or two seats away, which I thought was fascinating.” Beyond the diverse opinions of lawmakers, there were also disagreements among the experts invited to speak at the private briefing. The forum’s attendees and other tech leaders are talking about building and expanding on gains from AI, but many Latinos still lack broadband internet access, says attendee Janet Murguía, president of Hispanic civil rights organization UnidosUS. That reality underscores how “existing infrastructure gaps keep us from being at the front door of AI,” she says. Murguía wants lawmakers to think about the needs of the Hispanic community to prioritize job training, fight job displacement, and guard against “surveillance that gets away from the values of our democracy.” In particular, she mentioned AI-driven tools like geolocation tracking and face recognition, pointing to a report released earlier this week that found federal law enforcement agencies that are using face recognition lack safeguards to protect people’s privacy and civil rights. 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 resounding message she heard from tech CEOs was a desire for US leadership in AI policy. “Whether it was Mark Zuckerberg or Elon Musk or Bill Gates or [Alphabet CEO] Sundar Pichai, there was a clear resonance that the US must take the lead in AI policy and regulation,” she says. Murguía was glad to see women like Maya Wiley from the Leadership Conference on Civil and Human Rights and union leaders at the forum, representation she called impressive and historic. But she wants to see people from more segments of society in the room at the next forum, saying, “We can’t have the same small circle of folks that aren’t diverse making these decisions.” In her remarks during yesterday’s briefing, American Federation of Teachers president Randi Weingarten highlighted WIRED reporting that $400 can bankroll a disinformation campaign. Later, Tristan Harris from the Center for Humane Technology talked about how $800 and a few hours of work stripped Meta’s Llama 2 language model of safety controls and made it share instructions on how to make a biological weapon. “It’s like we were having a debate about how little it costs to ruin the world,” Weingarten says, pointing to Musk’s comment about how AI could spell the end of civilization. Weingarten credits Schumer for bringing people together at a critical moment in history, when there’s tremendous potential for AI to do good for humanity and tremendous potential to undermine democracy and human decision-making. Teachers and students deserve protections from inequality, identity theft, disinformation, and other harms that AI can fuel, she says, and meaningful federal legislation should protect privacy and seek to resolve issues like job displacement. “We want the responsibility to keep up with the innovation and think that that is what makes the innovation sustainable, like commercial air and passenger airlines. The innovation would not have been sustainable without a real commitment to safety,” says Weingarten. Ahead of the forum, Inioluwa Deb Raji, a UC Berkeley researcher, argued that the most reliable experts on real-world harms caused by AI come from outside corporations. She told WIRED she was thankful she was in the room to reiterate her opinion. A few times, she heard people argue that the reason major AI companies and the Biden administration had agreed corporations could lead voluntary commitments to assess AI systems before deployment was because those companies had built the technology and therefore understand it best. 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 She said perhaps that’s true, but hearing from people impacted by AI systems and examining how they’re affected offers another form of valid and important expertise that can inform regulation of AI and help develop standards. She knows from experience auditing AI systems for years that these systems don’t always work very well and can fail in unexpected ways and endanger human lives. The work of independent auditors, she argued during the briefing, opens things up to more investigation by civil society. “I’m glad I could be there to bring up some noncorporate talking points, but I wish I had more backup,” Raji says. Some commonly known tensions came up, such as whether open- or closed-source AI is best , and the importance of addressing the ways AI models that exist today harm people, rather than only looking at existential risks that don’t exist yet. While Musk, who signed a letter in favor of a pause in AI development earlier this year, talked about the possibility of AI wiping out civilization, Raji criticized Tesla’s Autopilot AI, which has faced criticism following passenger deaths. “Maybe I should have cared a little more about the independent wealth of people sitting two steps away from me, but I feel like it wasn’t that intimidating because I knew that they were repeating points that I’ve heard before from corporate representatives at these companies about these exact same topics, so I had a sense of what to expect,” she says. Despite some disagreements, Raji says, some of the strongest and most surprising moments of the meeting occurred when consensus emerged that government regulation of AI is necessary. Those moments made it seem there may be a path to bipartisan legislation. “That was actually pretty educational for me, and probably for the senators,” she says. There’s still an aversion to new regulations among many Republicans, which is why Senate Commerce chair Maria Cantwell, a Democrat from Washington state, was struck by how Microsoft CEO Satya Nadella framed the challenge. “‘When it comes to AI, we shouldn’t be thinking about autopilot—like, you need to have copilots,'" Cantwell says, paraphrasing Nadella's comments. "So who’s going to be watching, you know, this activity and making sure that it’s done correctly?” 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 all the CEOs, union bosses, and civil rights advocates were asked to raise their hands at points, one flaw with muzzling senators, according to critics on both sides of the proverbial aisle, is that lawmakers weren’t easily able to game out where their allies are in the Senate. And coalitions are key to compromise. “There’s no feeling in the room,” says Senator Elizabeth Warren, a Massachusetts Democrat. “Closed-door [sessions] for tech giants to come in and talk to senators and answer no tough questions is a terrible precedent for trying to develop any kind of legislation.” While Warren sat in the front row—close enough so the assembled saw the whites of her fiery, consumer-focused eyes—other critics boycotted the affair, even as they sought out the throngs of reporters huddled in the halls. “My concern is that [Schumer’s] legislation is leading to nowhere. I mean, I haven’t seen any indication he’s actually going to put real legislation on the floor. It’s a little bit like with antitrust the last two years, he talks about it constantly and does nothing about it,” says Senator Josh Hawley, a Missouri Republican. “Part of what this is is a lot of song and dance that covers the fact that actually nothing is advancing. The whole fact that it’s not public, it’s just absurd.” Absurd or not, some inside were placated, in part, because senators were reminded that AI isn’t just our future, it’s been in our lives for years—from social media to Google searches to self-driving cars and video doorbells—without destroying the world. “I learned that we’re in good shape, that I’m not overly concerned about it,” says Senator Roger Marshall, a Kansas Republican. “I think artificial intelligence has been around for decades, most of it machine learning.” Marshall stands out as an outlier, though his laissez-faire thinking is becoming in vogue in the GOP , which critics say is due to all the lobbying from the very firms whose leaders were in yesterday’s briefing. “The good news is, the United States is leading the way on this issue. I think as long as we stay on the front lines, like we have the military weapons advancement, like we have in satellite investments, we’re gonna be just fine,” Marshall says. “I’m very confident we’re moving in the right direction.” Still, studious attendees left with a renewed sense of urgency, even if that involves first studying a technology few truly understand, including those on the dais. It seems the more senators learn about the sweeping scope of generative AI, the more they recognize there’s no end to the Senate’s new regulatory role. “Are we ready to go out and write legislation? Absolutely not,” says Senator Mike Rounds, a South Dakota Republican who helped Schumer run the bipartisan AI forums, the next of which will focus on innovation. “We’re not there.” In what was once heralded as the “world’s greatest deliberative body,” even the timeline for legislation is debatable. “Everyone’s nodding their head saying, ‘Yeah, this is something we need to act on,’ so now the question is, ‘How long does it take to get to a consensus?’” says Senator John Hickenlooper, a Colorado Democrat. “But in broad strokes, I think that it’s not unreasonable to expect to get something done next year.” 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 artificial intelligence government Regulation Policy politics congress Mark Zuckerberg Elon Musk Khari Johnson Peter Guest Khari Johnson Will Knight Will Bedingfield Will Knight Niamh Rowe Will Knight 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 "

"As Trump Squeezes China, Alipay’s Star Rises | WIRED"

"https://www.wired.com/story/trump-squeezes-china-alipay-star-rises"

"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 As Trump Squeezes China, Alipay’s Star Rises Ant Financial has become a model for US fintech startups. Photograph: Paul Yeung/Bloomberg/Getty Images Save this story Save Save this story Save Application Personal finance End User Big company Sector Finance Ecommerce Technology Machine learning Li Xian, who works at a publishing company in Shanghai, says the Chinese mobile-payments app Alipay is indispensable. Over the past week she’s used it to order and pay for dinner through a delivery service, buy movie tickets, pay her utility bills, and rent a bike. “It’s my lifeline,” Li says. “I can’t remember the last time I used cash.” She is far from an outlier. More than 711 million people and 80 million merchants use the Alipay app each month, generating RMB118 trillion ($17.4 trillion) in payments over the 12 months ending June 30. Alipay has helped make cash almost obsolete in big Chinese cities, with even the smallest shops, restaurants, and market stalls accepting payment via QR codes shown and scanned at the point of sale. Alipay also offers a bewildering number of features built around payments. In many restaurants, for instance, you can scan a QR code to bring up the menu, then order food from Alipay without ever seeing a server. You can hail a taxi, send packages, add minutes of service to a cell phone plan, even set up a video consultation with a doctor, without leaving the app. Alipay offers deals from Taotao, a sister ecommerce site, tailored to an individual’s tastes and habits. “I think Alipay tries to cover every bit of our lives,” Li says. Ant Group , the company behind Alipay, is now headed for perhaps the biggest initial public offering of 2020. The IPO will highlight China’s strides in combining money and technology, and efforts to export that approach across the world. Around 65 percent of all Chinese use digital wallets, more than anywhere else in the world; Alipay accounts for 55 percent of them. Western companies are following Ant’s lead. Apple Pay , Google Pay, PayPal, and others provide smartphone payments via near-field communications and QR codes. Startups such as Affirm and LendUp offer loans in the US based on social media and other personal information. Maximilian Friedrich, an analyst with ARK Invest who studies innovation in payments and finance, says Square ’s Cash App seems to borrow from Ant’s model, offering banking and investments as well as mobile payments. But nothing rivals Ant’s scale and reach, its integration with Chinese ecommerce giant Alibaba, or how it leverages artificial intelligence. 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 Ant also faces some big questions. In China, it is the subject of government scrutiny for its broad reach and competition with government-run banks. Its approach to mining personal data, and perceived ties to the Chinese government, may raise privacy concerns, especially as it expands overseas. And Ant’s success and footprint abroad could run into an increasingly hostile US policy toward China. Ant declined to comment for this article. Beneath Alipay’s convenience is a strategy that uses artificial intelligence and troves of personal information. When renting a bike or a car with Alipay, for instance, the app may assess whether you need to pay a deposit by analyzing both a conventional credit score and some unconventional signals, including your friends, what apps you’ve installed, even how often you recharge your battery. “AI technologies are everywhere in Ant's business,” says Hui Chen , a professor at MIT who has worked with the company on research projects. Chen points to MYbank, an Ant subsidiary that offers small business loans through Alipay. The unit uses a risk management model with over 3,000 variables, some of which are updated in real time, he says. The system uses computer vision, voice recognition, natural language processing, and financial forecasting, Chen says. “They can make loan decisions within minutes and with zero involvement of human bankers.” “AI technologies are everywhere in Ant's business.” Hui Chen, MIT professor Alipay was launched in 2004 by Alibaba , the Chinese ecommerce giant founded by Jack Ma, to hold funds until transactions are finalized. At a time when few people owned credit cards and cash was still commonplace, this helped encourage ecommerce to take off. Alipay also became a way to verify a seller’s trustworthiness. Alipay launched a digital wallet for smartphones in 2009. Thanks to a scarcity of credit cards but an abundance of smartphones, it grew rapidly; users grew to 150 million, from 100 million, in its first six months. In 2011, Alibaba made Alipay its own company, which was renamed Ant Financial in 2014, and then Ant Group this year. Since becoming independent, Ant has diversified its payment business into a vast and growing web of financial interests. Now, less than half of Ant’s revenue comes from digital payments and merchant services. The majority comes from lending and wealth management, through more than a dozen subsidiaries offering a range of financial services. As of January, Ant’s money market fund, Yu’e Bao, managed $157 billion in assets, making it the world’s third largest such fund after JPMorgan and Fidelity. 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 sheer scale of Ant’s business makes it a target for regulation in China. The People’s Bank of China, the central bank, confirmed this month that the company would be subject to new financial regulations first proposed in 2019. China’s central bank is also developing its own digital currency and new standards for QR codes that might affect its business in unexpected ways. William Kirby , a professor at Harvard who studies Chinese business, says Ant is far more innovative and more useful than China’s state-owned banks, allowing it to undercut them. “The limits to Ant’s expansion at home are the insecurities of Chinese state banks and the government generally,” he says So far, the company’s growth has not been checked. Ant says its profit in 2019 was $2.5 billion. It says it was affected by a drop in consumer spending due to the Covid-19 pandemic but it appears to have weathered the storm well enough, with revenue growing 38 percent in the first half of 2020. Ant plans to offer between 10 and 15 percent of its shares in a listing split between the Hong Kong Stock Exchange and Shanghai’s new tech-centric STAR market. It is expected to value the company at around $200 billion, placing it among the world’s largest financial services businesses. By comparison, PayPal is worth $206 billion and Mastercard is valued at $335 billion. Ant is listing in Hong Kong and Shanghai, unlike former parent Alibaba, whose shares trade in New York. The Hong Kong and Shanghai listings reflect unease over deteriorating relations between Washington and Beijing. When former parent Alibaba went public in 2014, it listed its shares on the New York Stock Exchange. Ant has also pursued an ambitious international expansion plan through investments and acquisitions. It has acquired businesses in Singapore, Hong Kong, the UK, and the US. In November 2019 Ant invested $1 billion in Paytm, a major payments company in India. In January 2018, however, the US government blocked Ant’s planned acquisition of MoneyGram, a US money transfer firm, on national security grounds. Ant had acquired EyeVerify, a Kansas-based maker of eye-verification technology in 2016. Since then, US-China relations have worsened, and recently the US government has gone after successful Chinese-owned apps operating within its borders. On Friday, the Trump administration said it would ban the popular video app, TikTok , as well as WeChat, a communications app that is used by many Chinese in the US. “The danger [for Ant] is that the US government could, in its wisdom, decide not to allow merchants all over the United States to take Alipay from Chinese customers,” Kirby 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 Ant’s growth overseas may be affected by concerns over its use of personal data, as well as perceived links to the Chinese government. The company’s technology has been tied to a Chinese government plan to track and evaluate citizens. But the ties, if any, remain unclear, as do the details of the government scheme. If Ant can navigate these challenges, it may be well placed to take advantage of the spread of AI-driven fintech worldwide. The company says in its filing that it plans to spend 40 percent of the proceeds from its IPO, potentially around $12 billion, on research and development. Ant “has its hands all around the world in different markets,” says Friedrich of ARK Invest. “Every country and market or economy around the world will see those digital wallets rise up sooner or later.” 📩 Want the latest on tech, science, and more? Sign up for our newsletters ! One data scientist’s quest to quash misinformation The 20-Year hunt for the man behind the Love Bug virus Inside the industry of managing video game stars Tips to fix the most annoying Bluetooth headphone problems Could a tree help find a decaying corpse nearby ? 🎧 Things not sounding right? Check out our favorite wireless headphones , soundbars , and Bluetooth speakers Senior Writer X Topics China Finance artificial intelligence payments Will Knight Peter Guest Will Knight Will Knight Khari Johnson Khari Johnson Steven Levy 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 "

"Stopping Nuclear Terrorism Is a Game of Odds, Not Certainty | WIRED"

"https://www.wired.com/2015/10/stopping-nuclear-terrorism-game-odds-not-certainty"

"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 Johnson Security Stopping Nuclear Terrorism Is a Game of Odds, Not Certainty AS&E Save this story Save Save this story Save Editor's note: An Associated Press investigation into weapons traffickers attempting to sell nuclear material to terrorists prompted us to republish a WIRED feature from 2003 about the difficulty of preventing nuclear terrorism. I'm standing near a row of deserted loading docks in Billerica, Massachusetts, and George Kinsella hands me a vial of cesium 137. "This," he says, "is the kind of radioactive material you might see in a dirty bomb." As radioactive substances go, cesium 137 leads a fairly innocuous existence as a component of industrial instruments such as moisture gauges. Mishandled, though, it can cause severe burns or genetic defects, as it did at Chernobyl. I hand the vial back, fighting the urge to wash my hands, and Kinsella places it inside the trunk of a Mercedes sedan. Then he shows me a black canister the size of a soup can: Wrapped in a shielding layer of tungsten, it contains cobalt 57. He climbs into a cargo container on the back of a flatbed truck and puts the canister down near the center. The whole exchange looks like the kind of transaction that keeps Tom Ridge awake at night. As it happens, the loading docks belong to American Science and Engineering, the company where Kinsella works as principal software engineer, and he's preparing to demonstrate its MobileSearch X-ray and radiation sensor technology. For the past decade, the 44-year-old firm has developed X-ray scanners that help customs officials detect contraband in the war on drugs; now it's one of a handful of companies racing to manufacture devices that detect nuclear and radiological weapons. Kinsella and AS&E chief technology officer Joseph Callerame usher me into an RV-like vehicle parked alongside the Mercedes and the truck. We climb into a small, air-conditioned space where two swivel chairs sit in front of a console outfitted with four monitors and a bank of flashing lights. It looks like the control room of a small TV station. Kinsella takes a seat, and Callerame and I stand behind him. "Should we start the scan?" Kinsella asks. He makes a few quick keystrokes, and a low rumbling sound begins. A robotic arm mounted on top of our vehicle hangs near the far side of the Mercedes, then begins to slowly creep alongside it. "We're almost starting to cross the cargo now," Kinsella says. "Here we go." A ghostly outline of the trunk scrolls into view on two of the screens. One image is an ordinary X ray, a blurred jumble of superimposed shapes with no apparent depth. The second image, using more advanced backscatter X-ray technology, has an unearthly quality, as though the side of the car was ripped off and a grainy black-and-white image was taken of the contents. 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'm so transfixed by the shot of the Mercedes, I don't notice the rainbow stripe that appears beneath the outline of the trunk, shifting from green to bright red as the scan continues. "It's already detected the radiation," Callerame says. "Green indicates something's there, red is more serious. Even this very small source reveals a potential danger. And you can see that the source is localized to the back of the vehicle." As Callerame talks, the scanner moves past the Mercedes on to the flatbed. Suddenly there's a steady beeping in the room. "When the threat is higher, that alarm goes off." Once we're outside again, I glance back at the MobileSearch truck, glaring white in the early afternoon sun. From 20 feet away, it looks like the kind of trailer you might see at a construction site. But it's also an early glimpse of a technology that could be seriously effective at reducing a certain kind of threat. Which would be a good thing, because as dangers go, this one is about as gruesome as it gets. AS&E Imagine a terrorist driving east toward Washington, DC, a few minutes outside the Beltway on River Road. In the back of his van, he has 100 curies worth of cesium — about a thousand times what Kinsella handed me — along with a traditional explosive nearly as powerful as what Timothy McVeigh detonated in Oklahoma City. He's 14 miles from the White House. If he makes it there, he could perpetrate an assault on the US more disruptive than the terror of September 11. A strategically placed explosion might kill hundreds and require thousands to be treated for radiation exposure. The cleanup would take months. If he were carrying a traditional nuke—the smallest of which is about the size of a large refrigerator—he could well execute the single most devastating strike in human history. An atomic blast near the Capitol would vaporize everything in downtown DC. A zone framed by Georgetown and southeast Washington would suffer casualty rates of 98 percent. Three or four miles away—out to upper-northwest Washington, out to Reagan Airport across the Potomac—the casualty rate would run 50 percent, with most buildings damaged beyond recognition. The fallout would leave a trail of radiation sickness and, eventually, birth defects. 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 dirty bomb set off on the Beltway, or on the outskirts of any city, would be a disaster. But depending on the traffic and the road, it's likely that casualties from the explosion would be minimal and no one would die from radiation poisoning. The cost in life, disruption, and dollars might be the equivalent of a minor earthquake or a bad flood. A catastrophe, to be sure, yet nothing compared with the chaos that would ensue if such a device exploded in a crowded urban center. In terms of an actual multi-kiloton nuke, the difference between a detonation on the Beltway and a detonation in front of the White House would be several orders of magnitude. In the Beltway blast, thousands would die and millions might suffer from the fallout effects. Park the bomb by the White House, however, and a million people could be killed in seconds. And much of the US government would be taken out in the process. Right now, the government is focusing its resources on preventing that terrorist from getting his hands on a weapon of this scale. But how realistic is that? There are 30,000 nuclear weapons in the world, plus countless supplies of radioactive material that could be made into a dirty bomb, which spreads its poison with a conventional explosion. We live in the age of the "super-empowered angry young man," in Thomas Friedman's phrase, and any disgruntled group on the planet is a potential radiological event waiting to happen. No matter how hard you try to assuage or attack such groups, the odds are against you. So it's prudent not only to keep potential bomb detonators away from bombs but also to keep bombs away from large groups of potential victims. We need to make sure that van stays 14 miles away from the Capitol. And the way to do this isn't with Star Wars technology—death rays beaming down from space. We need an older technology, as old as cities themselves. We're talking about a wall. AS&E Walls have protected cities as long as there have been cities to protect. To guard against invasion, Nebuchadnezzar built a network of brick walls so that "the evil and the wicked might not oppress Babylon." As weapons evolved, walls had to change with them. By the 16th century, artillery had advanced to the point that Vienna razed the scattered developments outside city walls so potential invaders would have nothing to hide behind. The battlements had become a broad detection zone. The width of the space created was 400 meters—the range of cannons at the time. The outline of that zone is still visible today in the avenues and parks that make up Vienna's fabled Ringstrasse. Airplanes and missiles rendered the city wall symbolic; these days, the important defensive barriers aren't physical fortifications. But the advent of small nuclear weapons and dirty bombs—deliverable not by missiles and planes but by trucks and vans—suggest a new kind of urban perimeter defense, an atomic wall. Set up not as an actual barrier but as a vast array of sensors, such a technology would exploit the fact that any radiological or nuclear weapon leaves a footprint. For example, a ring of radiation detection devices deployed along the Beltway could scan every road, alley, and rail line that brings people within 14 miles of the White House. If nuclear material crossed the line, sensors would alert emergency response teams, which would intercept the vehicle before it entered the city. As in Vienna, the wall would be less a barricade that couldn't be crossed than a zone under constant surveillance. 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 basic technology behind such a system already exists, and while senior law enforcement and intelligence officials wouldn't discuss the subject on the record, conversations with both government and private-sector experts indicate a high level of interest in such a system. This past August, the Department of Defense announced that bioweapons sensors would be deployed in certain cities. Three months before that, the House began discussing the Anti-Nuclear Terrorism Prevention Act of 2002, which authorizes $250 million for installing scanning devices in New York City ports and tollbooths. Really, that's just a first step. "The idea of a truck containing a nuclear device in the center of our city is terrifying, but not impossible,"says Senator Charles Schumer, the New York Democrat who proposed the bill. "It doesn't matter how good our airport security is if all it takes to bring a nuclear device right into midtown is putting it on a ship or bringing it in on a truck." When it comes to Manhattan, Schumer has it relatively easy: He has only four tunnels and 11 bridges to worry about. What about the cities that don't happen to be located on islands? Any terrorist group well organized enough to plot a hijacking could find dozens of back roads into Los Angeles. How much would it cost to scan all the entrances to a city of that size? "To track vehicles traveling along a highway, what you'd need is a sensor array, and probably a secondary array—along with some video technology to keep track of who you were scanning," says Jim Winso, vice president of the San Diego-based SAIC (Science Applications International Corporation). The company is developing a radiation detection array—SAIC calls it a nuclear portal—that could cost less than $100,000 when purchased in bulk. The device would scan for suspicious cargo without slowing down traffic; once law enforcement identified an undocumented radiation source, they'd shut off the flow of vehicles at that particular access point, which would require roadblocks that could be set up in a matter of seconds. Once the vehicles in question had been contained, they would be examined with a more elaborate device—something like AS&E's $2 million MobileSearch system, which combines gamma ray detectors with advanced X-ray technologies. So when the terrorist heading toward the center of DC drives up the Beltway entrance ramp, his van would travel under a passive scanning device mounted on an overpass. If you remember high school physics, you know that radioactive materials emit invisible particles, including alpha and beta particles, which can be easily shielded against traditional scanners; most also emit gamma rays, which penetrate most materials and are far more difficult to conceal. In the split second he was under the scanner, 500 gamma rays might collide with it. Someone monitoring incoming data would notice the spike in radiation, and a video camera—the kind already used to catch traffic violators—would record his vehicle and license plate. 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 Within seconds, an emergency management team puts up a roadblock, slowing traffic to a standstill. A rapid-response team locates the vehicle and either searches it by hand or brings in a mobile X-ray unit to survey the contents. Of course, if the signature had suggested a less lethal material, the authorities could have opted to discreetly pull over the vehicle, as though they were nabbing someone for speeding. An array for each of the 50 Beltway on-ramps, plus 400 more to cover the roads running under the Beltway, would cost $50 million. Twenty-five MobileSearch trucks that could be moved to a scanning zone in a matter of minutes would cost another $50 million. Throw in a final $50 million to build temporary barricades and reconfigure roadways for the system. Then assume that everything ends up costing four times as much: The final tab for a metropolitan atomic wall would be $600 million. That's a lot. But keep in mind that the Bush administration asked Congress for $8 billion for research into Star Wars-style technology, out of a proposed total military budget of $379 billion. In other words, for the portion of the 2003 budget allocated for missile shields, you could build atomic walls around the dozen biggest cities in the US. Brookhaven National Laboratory "Every year there are about 300 cases of radiological materials that are either lost, stolen, or abandoned," says Ralph James. In his office at Long Island's Brookhaven National Laboratory, where he serves as associate laboratory director for energy, environment, and national security, James is telling me how an atomic wall might work in practice. There's a measured, Mr. Rogers quality to his speech that, along with his defense industry euphemisms, creates a false sense of normality. He mentions "consequence management" a few times before I realize he's describing what needs to be done after a nuclear bomb goes 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 To James, the key technology behind an atomic wall is the ability to differentiate between types of radioactive materials. If a source is sending out enough gamma rays, an ordinary handheld Geiger counter will pick that up. But you won't be able to identify the substance without a more sensitive detector. "You can think of gamma ray energies as frequencies," James tells me, as we sit in his office decorated with plaques and honorary degrees accumulated over 30 years. "Just as you can tune your radio to go from one frequency to another, you can tune the sensors to different gamma ray energies." The gamma rays emitted by the terrorist driving toward Washington, for example, would register energies of 662 kiloelectronvolts. That energy profile would create a clear picture: cesium 137, and probably a lot of it. Definitely not the kind of material you'd normally see packed into the back of a van. In general, detecting radiation is easy. The hard part is separating it from all the other radiation out there. "We have very sensitive detectors available—we can fly airplanes over the ground and pick up small increases in natural radiation from uranium ore deposits," says William Miller, professor of nuclear engineering at the University of Missouri. "But there's considerable variability in natural radiation levels. The presence of radon gas in homes and basements was discovered because a nuclear power plant employee kept setting off alarms at work." Potassium decays in every human body, and anyone being treated with nuclear medicine would trigger a crude Geiger counter. Without more advanced sensors, an atomic wall would be a nightmare of nonstop false positives. You'd know there was something spitting out gamma rays—just not what it was. "It's like good and bad cholesterol," says SAIC's Winso. "You have 'good' radiation, and and you have undocumented radiation." James and Winso believe that, in addition to screening out background noise, the system would need to keep track of known radiation sources—hospitals, for example—in an evolving database. That same database would monitor information transmitted by mobile sensors. "We'd need a type of sensor network within the city—to disperse radiation detectors into a continuous monitoring set of stations," James explains. "We can make these things very low-cost. They're not going to be very smart sensors, but they could be no bigger than a wristwatch, distributed to police officers, firefighters, postal workers—enough people dispersed around the city so that it would be difficult to move radiological material around it. All these low-cost sensors could be connected to a network—if you saw a lot of them going off, that's when you'd need to respond." 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 its own, each of these sensors would not be very sophisticated. "If we're looking at a radioactive source that's in the building across the street," James says, gesturing at a one-story lab about 40 feet away, "and I have a detector that's the size of a pinhead, it's not going to have very many gamma rays impinging on it in the period of, say, 100 seconds." James believes you can get around those limitations by thinking of the sensors as small pieces, loosely joined—an atomic wall that functions as a web. "As you get farther away from a source, the sensors have to get bigger, because that radiation is spreading everywhere. So you want to be close. Now you reach a point where you don't win by making these sensors bigger and more expensive by tiling them together. You win by having smaller, less-expensive detectors that are connected to a network." Any given wristwatch sensor might fail to detect a radioactive source, but distribute enough of them in a detection zone, and you'll start seeing a pattern of gamma rays trailing across the city. James calls it a "radioactive plume." Think back to the terrorist driving toward Washington. In the five minutes before he approaches the Beltway on-ramp, he drives by two police cars, one postal vehicle, and one fire truck, all of which are outfitted with Ralph James' wireless microsensors. Gamma rays set off two of the sensors, and the signals produce a discernible plume headed along River Road. Even this small amount would likely register as cesium 137, though not whether it was enough for a bomb. But emergency-response teams would know to watch out for something emitting gamma radiation heading east on River Road, even before the terrorist hit the Beltway. SAIC An atomic wall naturally brings to mind the Star Wars missile shield proposed during the Reagan administration. But the widely held objection to the Strategic Defense Initiative—that it would threaten the deadlock of mutually assured destruction and thereby make one side more likely to pull the trigger—of course does not apply. As September 11 made all too clear, mutually assured destruction wouldn't be much of a deterrent to our man with the cesium 137. Game theory has always had trouble accounting for players with no rational self-interest, and nuclear deterrence is no exception. In fact, the irrelevance of MAD creates an opportunity. There's a potential cost and inconvenience to building perimeter defenses, but there's no longer any new danger posed by creating them. It really comes down to how much risk you think there is. There's quite a bit of inconvenience at airports already; if urban residents truly felt that radiation warfare was a legitimate threat in their hometowns, it's not hard to imagine them putting up with longer lines at the city limits. And cost? Spread over its 20-year lifetime, even the most advanced system would be a rounding error in the military budget. 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 there's the more pressing issue: How easy would it be to subvert the network? After the scanning demo in Massachusetts, I sit down in a conference room with Callerame, and he walks me through the physics of concealment. High atomic-weight materials like lead can block gamma radiation, but the large quantities of lead that would be needed would show up on other scanning devices. Callerame's solution is to combine radiation sensors with advanced X-ray technologies, like the backscatter system that produced the startling image of the Mercedes. "I still think you're going to have to X-ray these things," Callerame says. "If you run only a radiation detector and somebody shields their source well enough, you may not pick it up. On the other hand, if you're simultaneously doing X-ray imaging, you'll see this big blob in the middle of the cargo, which would be a dead giveaway of something being clandestinely brought in." He shows me printouts of scans done at a demo in Washington, where they concealed the radioactive material in a container of lead the size of a bowling ball. In the image, the lead container pops out immediately, a bright-white circular shape in the middle of translucent grays. "Now, I should mention, even though we wrapped the cesium in this lead casing, we still managed to pick up the gamma radiation. It's just easier when you do the two in combination." Experts agree that a mixed-sensor approach is the way to go. "Any remedy that a terrorist could employ [to conceal radioactive material] would automatically make him more vulnerable to detection," says Winso. "You can use large quantities of lead to shield gamma sources, but that creates an awful lot of weight." Also, the mixed-sensor approach would help alleviate civil liberty and health concerns. Passive detection systems like SAIC's nuclear portal or Ralph James' wristwatch sensors are noninvasive—in both medical and privacy terms. You're not probing someone's car, the way you would with an X-ray scan, you're just listening for gamma rays coming out of the car. Other than radioactive materials, you wouldn't be able to tell anything about the contents of a vehicle from a passive scan. Mark Wasyl THE WALL AT WORK An "atomic wall" may seem far-fetched, but experts believe a detection perimeter could stop radiological and nuclear weapons—or at least provide a much needed level of redundancy in the effort to police them. Here’s how it might work. 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 1. As a terrorist approaches the Beltway, a scanner above the on-ramp detects gamma rays emitted by the radioactive material in his vehicle. 2. A silent alarm alerts authorities. As the terrorist passes through the scanner, a video camera records his vehicle's make, model, and license plate. 3. Police set up roadblocks and locate the vehicle. To keep traffic flowing smoothly, false positives would need to be kept to a minimum. 4. An emergency response team searches each suspect vehicle by hand or with a MobileSearch detection unit. While the experts I spoke with seemed convinced that a dirty bomb attack was more likely than a nuclear weapon, there was also a consensus that nukes would be harder—but not impossible—to detect. Unlike a dirty bomb, which disperses radiation that's already there, a nuke creates the majority of its radiation in the fission process. "This kind of system would have great utility for detecting radiological material that could be used in dirty bombs," explains Philip Anderson, director of the Homeland Security Initiative at the Center for Strategic and International Studies. But if a nuke reaches US soil, it's already too late. "With nuclear weapons, we have to go to the point of origin." Because nuclear weapons are larger, we could offset this by routing bigger vehicles through fewer portals, which would be outfitted with both X-ray and gamma ray scanners. Officials could distribute the cheaper microsensors along the city's periphery, detecting suspicious radiation stored in smaller vehicles, while channeling all the trucks large enough to carry a real nuke past the more expensive probes. This would add some friction to the flow of commerce into a metropolis, but those roads are already teeming with tollbooths and weigh stations. Sure, building an atomic wall might involve rerouting some of the traffic coming into cities, but we've pulled off larger feats of urban engineering. And in those cases, the cost of doing nothing was far less. No strategy to reduce the risk of nuclear terror is bulletproof. Even if scanning technology improves, it's always possible that a van containing deadly material might slip through. Prevention is a game of odds, not certainty. But if you think the technology can reduce the chance of countless urban casualties, then at a certain price, it's worth doing. 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 Before I leave the Brookhaven campus, James pulls me over to his bookshelves, near the patent grants displayed on the wall. He grabs a small jewel box off a shelf and opens it to reveal a gray block the size of a sugar cube. "This is the microsensor I was telling you about," he says proudly, as though we're looking at photos of his children. "It's made of cadmium zinc telluride, which can detect gamma rays at room temperature. This is missing the electrodes and supporting circuitry you'd need for wireless transmission, but you can see how small it is." James hands me the sensor, and I imagine millions of them scanning trillions of invisible particles like an oversize urban immune system. I ask him if he thinks such a system will ever be built. He pauses for a second. "Let me just say that sensors have already been deployed in New York and Washington. I don't want to make a comment beyond that regarding the specific locations to give information to terrorists." His smile seems to say, We're working on it. To be sure, building an atomic wall wouldn't be reason to stop doing all the other things we already do to keep the world free from radiological terror: weapons inspections, military strikes, peace marches. But like the city walls of old, an atomic wall of networked sensors might have the single most profound impact on our perception of safety, particularly for those of us living within the obvious targets. It would give the current system of policing radioactive materials a new kind of redundancy, one reassuringly close to home. You'd pass by those sensors at the exit ramp or the tollbooth, and you'd know that something, somewhere, was counting the gamma rays. Mark Wasyl 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 HARBOR Tackling the First Choke Point: Ports On September 10, Coast Guard agents looking for stowaways on a cargo ship docked in Port Elizabeth, New Jersey, found something altogether worse: trace amounts of radiation. They ordered the Liberian-flagged freighter to move offshore and called the Pentagon, which dispatched special operations troops trained in detecting nuclear weapons. In the end, no weapons were found (the radiation came from ceramic tiles), and the crisis passed. But the scare was a reminder that ports are both the easiest way for terrorists to bring nukes into the US—and the best place to stop them. Container ports are the natural first brick in any "atomic wall" of radiation detection. They are choke points on a grand scale, relatively small in number, huge in volume, and at least partially automated. Although there are more than 360 maritime ports in the US, the vast majority of the 8 million containers that enter the country each year go through a handful of massive shipping hubs, led by Port Elizabeth and California's Long Beach. Unlike cars and delivery trucks, cargo containers are all the same size—ideal for automated scanning. They are handled by a machine at least once—lifted by a giant gantry crane off the ship they arrived on—and usually again when loaded on a train or truck to travel to points throughout the country. Most are also typically examined by an inspector at the port, if only to ensure documents are in order. This controlled dockside setting is emerging as the test bed for technologies that could eventually be deployed around cities and other transportation hubs. At Port Elizabeth, the protocol is clear: First, a customs agent equipped with a radiation pager—a handheld Geiger counter—walks around the container. Then the bin passes under the arm of a massive truck-mounted VACIS (vehicle and cargo inspection system) machine, which uses gamma radiation to image the contents in much the same way X-ray machines view luggage. Two inspectors in the VACIS cab examine an image of the truck's metal skeleton, the density of its payload mapped in splotches of color. If the scan reveals something that does not agree with the manifest, inspectors may search the container with a density-determining "blaster," a stud-finder on steroids, or even hand-inspect 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 The system is powerful—the VACIS can see through as many as 3 inches of steel, which should allow it to catch any shielding that would hide a nuclear weapon from radiation sensors—but expensive and time-consuming. The scanners cost about $1 million each, and Port Elizabeth's four Vacis machines can handle only about 700 containers a day (21 percent of the total). Likewise, the port's 270 uniformed customs officials have time to hand-inspect only about 2 percent of incoming cargo—and less than half of those inspectors are equipped with radiation pagers. "If we had more technology, we'd be able to inspect more containers," explains Richard O'Brien, the port's deputy chief inspector. "Basically, we're now in a situation where we gauge our success by what we don't find." He pauses. "We know we've done a good job if nothing blows up." Deploying a network of relatively cheap sensors would help. For instance, if each of Port Elizabeth's cargo cranes had radiation detectors—like those installed at Virginia's Hampton Roads port in the wake of September 11—they would check every arrival automatically. So would sensors in ocean buoys and beacons. Officially, such measures are under consideration; unofficially, government sources acknowledge that some may already be installed. The Coast Guard has asked for a 36 percent budget increase next year to expand these efforts. That's a good start. Topics national security nukes terrorism David Gilbert Dell Cameron David Gilbert Andy Greenberg Dell Cameron Lily Hay Newman Dell Cameron 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 "

"The Pearl of Lao Tzu’s Twisted History - The Atlantic"

"https://www.theatlantic.com/magazine/archive/2018/06/the-pearl-of-lao-tzu/559109"

"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 A Muslim among Israeli settlers, the pearl at the center of an 80-year-old hoax, Marti Noxon putting women’s rage on TV, and pop culture’s response to Trump. Plus, Kissinger on AI and the end of humanity, an interview with Seth Meyers, the search for life on Mars, NRATV, and more. The 9.9 Percent Is the New American Aristocracy Matthew Stewart Is Television Ready for Angry Women? Sophie Gilbert A Muslim Among Israeli Settlers Wajahat Ali Chasing the Pearl of Lao Tzu Michael LaPointe Can Protest Art Get Its Mojo Back? Spencer Kornhaber How the Enlightenment Ends Henry A. Kissinger A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. Chasing the Pearl of Lao Tzu A tale of ancient philosophers, alien abductions, murder-for-hire—and how the world’s largest pearl came to be the centerpiece of an 80-year-old hoax L egend says the diver drowned retrieving the pearl. Trapped in a giant Tridacna clam, his body was brought to the surface by his fellow tribesmen in Palawan, a province of the Philippines, in May 1934. When the clam was pried open, and the meat scraped out, the local chief beheld something marvelous: a massive pearl, its sheen like satin. In its surface, the chief discerned the face of the Prophet Muhammad. He named it the Pearl of Allah. At 14 pounds, one ounce, it was the largest pearl ever discovered. A Filipino American, Wilburn Dowell Cobb, was visiting the island at the time and offered to buy the jewel. In a 1939 article that appeared in Natural History magazine, he recounted the chief’s refusal to sell: “A pearl with the image of Mohammed, the Prophet of Allah, is earned by devotion, by sacrifice, not bought with money.” But when the chief’s son fell ill with malaria, Cobb used atabrine, a modern medicine, to heal him. “You have earned your reward,” the chief proclaimed. “Here, my friend, claim this, your pearl.” In 1939, Cobb brought the pearl to New York City, and exhibited it at Ripley’s Believe It or Not, on Broadway. There, a new legend emerged, eclipsing the first. Upon seeing the pearl, Cobb said, an elderly Chinese gentleman “of highest culture and significant wealth” named Mr. Lee “burst into an hysteria of trembling and weeping.” This wasn’t the Pearl of Allah; this was the long-lost Pearl of Lao Tzu. Around 600 b.c. , he told Cobb, Lao Tzu, the ancient Chinese philosopher and founder of Taoism, carved an amulet depicting the “three friends”—Buddha, Confucius, and himself—and inserted it into a clam so that a pearl would grow around it. As it developed, the pearl was transferred to ever-larger shells until only the giant Tridacna could hold it. In its sheen, Mr. Lee claimed, was not just one face, but three. On the spot, Mr. Lee offered Cobb half a million dollars, saying the pearl was actually worth $3.5 million. But like the principled chief before him, Cobb refused to sell. The mysterious Mr. Lee returned to China, never to be heard from again. But his spontaneous appraisal—$3.5 million—still forms the basis of a price that has steadily grown, from $40 million to $60 million to $75 million and beyond. And Mr. Lee’s recognition of Lao Tzu’s legendary pearl is at the heart of an 80-year-old hoax that has left a trail of wreckage across the United States—a satin mirage many try to grasp, before the jaws snap shut. Bits of the legend are true. The pearl really was discovered when a diver drowned; Cobb really did acquire it from the local chief; and gazing at the pearl, you really can discern the face of a turbaned man. The rest is a fantasy Cobb invented. In the dry hills of Union City, California, I met his daughter Ruth Cobb Hill. Born in the Philippines, she is now 85 years old, a retired clinical psychologist. Facing her wall of artifacts—pottery, bracelets, and necklaces dating back to the Song dynasty ( a.d. 960–1279)—she began excavating the pearl from its foundational myth. Wilburn Cobb was born in 1903 on Cuyo, an island in the western Philippines. His father was an American mining engineer, and Cobb grew up affluent, with a penchant for adventure. Ruth described him as a brilliant swimmer who would go diving in Palawan’s underwater caves and race with schools of sharks. As he traveled from island to island, he grew enamored of indigenous cultures, and began writing romantic stories about the people he encountered. “The storytelling part of him was always, always there,” Ruth told me. “He wanted to be a writer.” Cobb studied his pearl, sketched it from different angles, and finally saw the turbaned face, like a figure in a cloud. He called it the Pearl of Allah in heretical, if well-meaning, deference to the chief, who was Muslim—and then put the words in the chief’s mouth, in the pages of Natural History. With a childlike indifference to distinctions of fact and fiction, Cobb seemed to perceive the pleasure of a story as proof of its validity. By the time he acquired the pearl, Cobb was a husband and a father to eight children, but domestic life never suited him. He pictured himself taking the pearl to America. It wasn’t long before Ruth saw the jewel as a rival. No older than 5, she came upon the pearl one night and kicked it—surely the only time the world’s largest pearl has been treated with such disregard. Ruth was right to worry; Cobb left for America in 1939. He brought the pearl to Roy Waldo Miner, a curator at the Museum of Natural History in New York, who wrote a letter certifying it as a genuine Tridacna pearl, and “a record specimen.” The Miner letter was enough to land Cobb his contract at Ripley’s, until the novelty wore off. Cobb’s American adventure meant abandoning his family to the Japanese occupation, which came in 1941. At the age of 9, Ruth witnessed massacres, had her home razed, and lived as a fugitive. Her father’s wartime experience sounds jolly by comparison. He joined the Merchant Marines, working in a ship’s kitchen while in his suitcase the pearl made an unofficial world tour, all the way to India before the fighting got too heavy. “Psychologically, he really couldn’t separate from it,” Ruth said, even as his life grew increasingly austere. Upon returning from the war, he settled in San Francisco and got a job as a guard at San Quentin State Prison. Cobb cherished the pearl all the more in San Quentin’s spare confines. “A lot of money would be just another headache to me,” he told the San Francisco Chronicle in 1967. “The richest man in the world doesn’t have what I have.” But what was it worth? Such a singular object was hard to appraise. In a way, the pearl was worth only what someone would offer, and it was toward the end of Cobb’s life—when he flirted with putting the pearl on the market—that the story of Mr. Lee first circulated. In 1967, Lee Sparrow, who operated the San Francisco Gem Laboratory, helped make the story a reality. “If Cobb was offered $3.5 million,” he told the San Francisco Chronicle, “then that is what it is worth.” But in Sparrow’s estimation, $3.5 million would be the bargain of the century. His laboratory set out to prepare an authoritative appraisal. With a whopping 127,574 pearl grains, Sparrow said, the pearl should be valued at $40 million to $42 million. The Sparrow appraisal surely flattered Cobb’s fantasy, but though he sometimes considered selling the pearl, he never did. He’d be approached by men who wanted to broker a sale, and leave them vexed. Cobb’s refusal to sell complicates certain accusations recently leveled against him. In the Philippines today, descendants of the Palawan chief reportedly insist that Cobb was only ever given the pearl as a broker. He was meant to sell it and share the proceeds with the chief. The descendants believe that their family still has a viable claim to the pearl—a matter of symbolic as well as financial importance. In 1996, Filipino President Fidel Ramos declared the South Sea pearl the country’s national gem, and singled out the Pearl of Lao Tzu as the world’s premier specimen. When Cobb died, in 1979, Ruth was left to settle his estate. Once a rival for her father’s affection, the pearl now became a tax liability. Wanting a second opinion of its value, Ruth consulted a gemological expert at the IRS, and they arrived at a price of $200,000. That sounded fair. Soon after, a jeweler from Beverly Hills said he’d found a buyer. And so, 40 years after the Pearl of Lao Tzu had come to America, Ruth Cobb Hill met its buyer at a Wells Fargo in San Francisco. Under armed guard, she lifted the world’s largest pearl from its safe-deposit box, and handed it over to a man named Victor Barbish. I f Cobb wrote the pearl’s original gospel, Victor Barbish was its fundamentalist. He founded a holding company, the World’s Largest Pearl Co. Inc., and named himself president. Then he elaborated on Cobb’s story—“the factual history,” he called it. During the Sui dynasty ( a.d. 581–618), Barbish said, the pearl’s owner awoke to find a young boy desperate for food and shelter knocking on his front gate, and took him in. One night, the man dreamed that the Pearl of Lao Tzu spoke to him and prophesied that the boy would initiate a new dynasty, “a reign distinguished by a more humane attitude than has prevailed heretofore.” Sure enough, the boy grew up to become Li Shih-Min, a founder of the Tang dynasty. Barbish also resolved a key logistical hitch in Cobb’s story: how the pearl ended up off the coast of the Philippines, some 1,800 miles away from the seat of the Chinese empire. Still snug in its shell, he said, the pearl found its way onto a trading ship during the Ming dynasty ( a.d. 1368–1644), and was swept overboard in a typhoon. He claimed to have learned these facts from a member of Mr. Lee’s family in Pasadena in 1983. With the help of a former CIA agent named Lewis Maxwell, Barbish said, he planned to sell the pearl to the Lee family. Yet something always seemed to thwart the pearl’s sale. The problem wasn’t that Mr. Lee never existed—that he was only ever a Wilburn Cobb invention—it was a series of action-packed calamities of the sort Barbish seemed to attract. In Japan, Barbish said, Mr. Lee gave Maxwell a check for a $1 million down payment, but after returning home to Alaska, Maxwell bled to death during a botched bypass surgery. The check disappeared, and Barbish never heard from the Lees again. Lewis Maxwell is just one of many names that float through the pearl’s history with Victor Barbish. Doctors, generals, princesses—there usually was a real figure somewhere behind the name. Like Cobb, Barbish sensed that the story could be worth more than the actual object. And in Barbish’s telling, the story of the pearl always ended with you becoming rich. When I began looking into the Pearl of Lao Tzu, I heard about a woman in Florida who knew more than anyone else about Victor Barbish’s 25-year ownership. She’d even written a memoir about Barbish, I was told, but was sitting on it for fear of being sued, or worse. I met Laura Lintner-Horn in Bradenton, Florida, in October, and over the course of several days, she told me how she had lived with Barbish’s family, on and off, for 50 years—from when she was a little girl until she met her third husband—never questioning his claims or disobeying his orders. She’d held the Pearl of Lao Tzu in her hands, and thought Barbish was here to fulfill its ancient message of peace. Indeed, she’d have done anything for the man she believed to be her father. Laura became an unknowing accessory to Barbish’s schemes, all the while believing equally in the legends of the pearl and the man. By the time she learned she’d been living a lie, she’d endured unimaginable tragedy, and had nothing left. “Everybody ends up defending the pearl until they lose,” she said. “And they lose big.” The story she told, and what I discovered during my own yearlong pursuit of the pearl, braided fact and fiction into a theater of the American absurd. From contract killings to alien abductions, Chinese emperors to Osama bin Laden, the Pearl of Lao Tzu’s story kept getting weirder with every detail I uncovered. And, as I’d learn, this artifact has come back on the market, and is only waiting for the next set of hands to pry it loose. F or 10 years, Laura has been trying to piece together the life of Victor Barbish, yet even basic facts are difficult to recover. He was a man who praised America as a place where a citizen “could be anything he or she wants to be,” and took full advantage of the national tolerance for self-invention. He said he was a monk, a prizefighter, a CIA agent, an opera singer. He was the business partner of Sammy Davis Jr., the lover of Sophia Loren. He was poisoned, shot, imprisoned in war, possessed by demons. His family calls him a visionary; most others call him a con artist. Barbish claimed to be the son of Al Capone, and he dressed the part, wearing open jackets, his bare chest heaped with gold chains. Whenever he happened to be near Mount Carmel Cemetery in Hillside, Illinois, he’d place a Cuban cigar on Capone’s grave site, a tribute to “Dad.” In fact, his father was a butcher named Lester Barbish, who married Helen Ruben and had a boy, Lawry Barbish, in New Castle, Pennsylvania. The man we know as Victor Barbish makes a debut in the public record in 1970, in La Verne, California. The city council prohibited gambling, but Barbish was running a bridge parlor at Vic’s Steak House, his restaurant and nightclub. Reading about his decadelong fight to legalize his operation, one gains a kind of admiration for his tenacity. To stop the constant raids on his bridge parlor, Barbish threw everything at the city council. He switched from card games to bingo, and said the proceeds would go to youth sports: He’d fund the completion of a downtown minipark. But La Verne didn’t want his money, or him. “I certainly would not want the minipark known as ‘the park that Vic built,’ ” one city councilman said. When flattery failed, Barbish unsuccessfully sued the city, demanding to know “the price of becoming a respectable citizen.” He moved to San Bernardino and founded the Church of All Faiths in a former five-and-dime store, using religious exemptions to start a bingo game there. Now he was Reverend Vic Barbish, ordained by the Universal Life Church of Modesto, a mail-order service. He published apocalyptic sermons in the local newspaper, while his bingo games took in about $80,000 a month. The city government finally realized he’d been investigated before, and revoked his gambling license. No matter what Barbish tried, he couldn’t shake a scent of the illicit; the people of San Bernardino thought he had ties to the Mafia. He needed something to legitimize him, something solid. He found that something in 1979, when word came to him that Wilburn Cobb had died. The world’s largest pearl was for sale. The price of becoming a respectable citizen: $200,000. In 1985, Barbish moved to Colorado Springs and reinvented himself yet again. As president of the World’s Largest Pearl Co., his name in The Guinness Book of World Records , he fostered an image of prosperity. A driveway of luxury cars led up to an enormous house filled with jade dragons, stuffed lions, a photograph of Princess Diana and Prince Charles personally addressed to Barbish’s glamorous wife. He ingratiated himself with the city’s jewelers, real-estate agents, and car dealers. He invited the police for dinner. Barbish would dazzle you with gaudy opulence. Then he would ask for an investment, or perhaps a short-term loan— just a few hundred thousand, say—to finesse the final touches of a blockbuster deal. “Victor was constantly saying, ‘I’m working on a $20 million loan on the pearl, and it’s going to be coming any minute,’ ” one of his marks told me. Or he’d say he had a buyer: Ferdinand Marcos, Whoopi Goldberg. But at the last possible moment, the deal would fall through—if not from some calamity, then because Barbish was just too principled. In the mid-’80s, he said, an excommunicated Iranian princess had brokered a $40 million sale on behalf of a group in Europe. But when Barbish learned that the buyers were “all of a criminal, unscrupulous origin,” he called it off. At other times, fate would intervene to protect the sanctity of Lao Tzu’s pearl. In 2004, Barbish told Aaron Klein of WorldNetDaily that he’d received a $60 million offer on behalf of a foreign buyer named Osama bin Laden back in 1999. According to Barbish, bin Laden had intended to purchase the pearl as a gift for Saddam Hussein, “to unite the Arab cultures.” The deal was in place, but bin Laden’s representatives were stopped at the Canadian border. When Klein, now the Jerusalem chief of Breitbart News , wrote about the deal, Barbish suggested that it established a link between bin Laden and Hussein—a crucial missing piece of George W. Bush’s justification for invading Iraq. “I just couldn’t sit back and listen to these lies about our government and President Bush,” Barbish said. “Bin Laden tried to purchase my pearl as a gift to Saddam, and Saddam wanted to accept it.” (Klein wrote that he was provided faxes documenting this historic deal, but when I reached him for comment, he said he couldn’t find them.) Written down, such stories seem so artless, it’s hard to imagine how Barbish passed them off. After all, his targets were savvy, successful people. But they had one thing in common: a fatal thread of greed that Barbish masterfully teased out. S ome fought back. Through the 1980s and ’90s, hardly a month passed without one legal action or another, brought by a large cast of characters claiming a share—$250,000 here, $500,000 there—of the Pearl of Lao Tzu. A constant presence in the legal saga was Peter Hoffman, the Beverly Hills jeweler who’d brokered the purchase from Wilburn Cobb’s estate in 1979. When a Colorado judge, fed up with all the legal wrangling, ordered the pearl to be sold at auction by August 1990 to settle the debts, Hoffman went to work. The bidding would begin at $10 million. Hoffman still owns a one-third stake in the pearl, and he’s always seen himself as the pearl’s rightful guardian, the only one who could successfully market it. Wilburn Cobb, he once told a reporter, “saw me in a dream with the three sages, Buddha, Confucius, and Lao Tzu, who said I would be the next caretaker of the pearl.” In May 1990, Hoffman exhibited the pearl in a vault at Studio City, in Los Angeles, the last time it was seen in public. On black velvet and gold lamé, it elicited gasps from reporters at a press conference, where Hoffman said the pearl had been cultivated by Lao Tzu’s descendants. Indeed, “the pearl’s purported spiritual powers” were far more important to him than the money, which he pledged to use “to benefit mankind.” As for that money, he expected the pearl to sell for $25 million to $50 million. (Citing too much “fake news” about the pearl, Hoffman declined to comment for this story, but noted that it “should be properly referred to as a priceless famous historical artifact.”) Hoffman has claimed that he was close to a sale several times in the ’80s and ’90s. Ferdinand Marcos was supposed to buy it, but was deposed before a sale was finalized; a baroness briefly had the sultan of Brunei intrigued. But his efforts ultimately led nowhere. The deadline passed, and the pearl drifted back into limbo, sealed in a safe-deposit box—right where Victor Barbish wanted it. For more than 20 years, the Pearl of Lao Tzu has remained in Colorado Springs. There, its secret is kept safely out of sight: It isn’t worth what the owners claim. In fact, it isn’t even a real pearl—at least, not as you might think. If someone says he owns a 14-pound pearl, you’ll probably picture one of those familiar, very precious little gems, and multiply the value out of all proportion. Seemingly to generate such warped calculations, the appraisal prepared by Lee Sparrow in 1967—$40 million to $42 million—cherry-picked from the 1939 letter written by Roy Waldo Miner, the Museum of Natural History curator. Miner had asserted that the specimen “can truly be called a pearl.” With this established, Sparrow proceeded to calculate the object’s value as though it were one of those tiny round gems blown up to Guinness -record size. Explore the June 2018 Issue Check out more from this issue and find your next story to read. But elsewhere in the Miner letter, the curator terms the specimen a “pearlaceous growth,” and stresses that it ought not to be classified as a precious pearl. The gems we commonly know as pearls are formed within the organic tissue of saltwater oysters, whose inner shells possess nacre, or mother-of-pearl, which generates a pearl’s signature luminescent sheen. Compared with these gems, Tridacna -clam pearls are more like porcelain. Indeed, the Pearl of Lao Tzu cuts an ugly figure. Some might liken it to a lump of white clay; others might think it’s an alien egg. Under U.S. trade law, it’s perfectly legal to call such objects pearls; any shelled mollusk—even a snail—can make a pearl. But gemologists traffic in precious pearls, and discard the rest with a pejorative classification: calcium-carbonate concretions. What was Sparrow doing? I located a colleague of his, who worked with him for 20 years (Sparrow passed away in 1990), and she recalls him as credible, even admirable. But with the Pearl of Lao Tzu, he was pulling a stunt. “I laughed my way through that whole thing,” she told me. She described how Sparrow was egged on by excited colleagues to inflate the number, until, in a collective frenzy, they reached $40 million to $42 million. If the pearl could attract a buyer at that price, then surely Cobb wouldn’t refuse to sell (and Sparrow would get a handsome commission). “It’s not like you’re breaking the law,” she added. “It just makes you look silly.” The Sparrow appraisal left room for the pearl’s “historical significance” as well, claiming that the pearl had been “carbon dated to be ±600 years old.” But Michael Krzemnicki, who directs the Swiss Gemmological Institute and has written extensively on techniques for dating pearls, told me there’s no record of the pearl’s ever having been subjected to radiocarbon dating. None of these facts inconvenienced Victor Barbish. In 1992, he commissioned a fresh appraisal, something to replace that of the deceased Lee Sparrow. Michael “Buzz” Steenrod, a former video-equipment salesman who worked at All That Glitters, a jewelry store in Colorado Springs, prepared the document. While Sparrow only said the pearl could be about 600 years old, the slippage is complete in Steenrod’s work. “It has been carbon dated to 600 b.c. ,” his appraisal avers. All things considered, he estimated its worth at $52 million. (Steenrod declined to comment.) It’s hard to blame those who fell for such fabulous appraisals, when the media provided no bulwark against them. Time after time, journalists failed to apply even the slightest pressure to the story. The pearl is “an estimated 6,000 years old,” the Los Angeles Times reported. It has been valued at $42 million, Channel 5 News in L.A. said. An anchor at CNN asked her audience: “Could you imagine the oyster?” Victor Barbish knew where the real money was—not in actual clams, but imaginary oysters. On no one did the spell work so well, or last so long, as Laura Lintner-Horn. She was the perfect candidate for life in Barbish’s hall of mirrors. Born in 1953 in Maywood, Illinois, a suburb of Chicago, Laura was adopted by her grandparents at the age of 3. Her parents had divorced, and it was considered seemlier for Laura’s mother to give her up, the better to attract another husband in their conservative, Italian Catholic neighborhood. Rather than being candid about the arrangement, however, Laura’s grandparents presented themselves as her parents, while her biological mother and aunt became her older sisters. Laura never doubted these relations, even as her classmates taunted her: “Your mother has gray hair! Your mother’s an old woman!” Victor Barbish met Laura’s “sister”—actually her aunt—at the Paradise Ballroom in Chicago in 1957, and they married. With his usual creep toward fabrication, he began putting it out that he’d had a one-night stand with Laura’s biological mother and that Laura was his daughter. And so Barbish’s revelation that her parents were really her grandparents only gave way to another primal deception: that he was her father. Until his death, in 2008, she believed it. She wanted to believe it. “I wanted a normal family so bad,” she told me. “I worshipped the Barbishes.” But while Barbish absorbed her into his family, she was always second-class, always playing catch-up in his affections. Every time she cleaned his house or worked without pay, she said, “I did it out of my heart.” One gets the sense that Barbish enjoyed seeing how far he could stretch Laura’s faith. When she divorced her first husband, whom she’d impulsively married at the age of 18 and who’d turned out to be abusive, Barbish told her he’d had him killed, and Laura didn’t learn otherwise until she ran into the man in Colorado Springs some 30 years later. When asked what had really happened, Barbish told her: “Let’s not go there, Laura.” And so she didn’t. Barbish wielded such supreme authority, she didn’t even doubt his live performances of alien abduction. He’d be driving down the highway, and his head would suddenly wrench back and his eyes would roll: The aliens had snatched his body. Laura would grab the wheel and shake him—“Please, Vic, wake up, wake up!”—and in the nick of time, he’d come to his senses, with no memory of his latest close encounter. L aura made her career in loss prevention for a department store, stalking shoplifters in a trench coat like her role model, Columbo. She’d wrestle them to the ground; once she jumped through the window of a car to prevent an escape, only to have a gun put to her head. “I was such a bitch,” she recalled. “I prided myself on that.” But she had a blind spot for the thief in her life. Looking back, she’s astonished by her gullibility, which she credits to the atmosphere of the Barbish home, describing it as cultlike. “You asked permission for everything,” she recalled. Laura’s major losses began on August 30, 2000. Lisa, Laura’s daughter with her first husband, had herself survived a physically abusive marriage, and Barbish had directed her to move to the town of Stockton, Illinois, to put her life back together. In Stockton, Lisa struggled with depression, started drinking, and lost her driver’s license. But that didn’t stop her from driving; she just evaded police along back roads, where the corn grew high in summer. At an intersection that August morning, a fully loaded 18-wheel truck hit Lisa’s car, driving it 200 feet into the fields, and killing her instantly. “I remember going through the cornfields just looking for things,” Laura said. She still has the items she recovered that day: a hubcap, a shoe. At the time, Laura was married to Phillip Lintner, an Elvis Presley impersonator. He’d raised Lisa from the crib, and when she died, Laura said, he destroyed himself in grief. He drank cheap liquor, smoked cigars, and stopped singing. Thirty days after receiving a diagnosis of stomach cancer, Phillip died, on Christmas Eve 2001. Laura retired early, and drew closer to Barbish. In addition to her pension, she had money from the sale of a house, as well as life-insurance payouts from her husband’s and daughter’s deaths—hundreds of thousands of dollars. Barbish convinced her that in her grief, she wasn’t thinking straight, and that people would try to take advantage of her. Wouldn’t it be prudent to turn everything over to him, to let him invest the money and steward her accounts? In 2005, Barbish moved one last time, to Sarasota, Florida. In typically grand fashion, he took up residence in a $1.5 million house, established a jewelry store in the city’s historic downtown, and dissolved the World’s Largest Pearl Co. After all these years, he said, he’d “become weary of the unceasing evils” of those who’d tried to possess his pearl. “It draws the wrong type of people,” he told the Associated Press. “It was made to do something good.” And so he created the Pearl for Peace Foundation , a registered nonprofit organization that pledged to support law enforcement. Anyone who paid a membership fee—from $25 to $600—received a golden badge with an image of the pearl at the center, and a membership card depicting a dove soaring with the pearl in its talons: to unite and protect us all. President George W. Bush was named member No. 1. Barbish’s family says the foundation reflected his passion for America. “His whole life was about trying to do something great for the country,” his son Mario told me. Indeed, the foundation was a precursor to the Blue Lives Matter countermovement. “He knew what was coming,” Mario said, “the disrespect for law enforcement in our country.” Without access to her own money, Laura was compelled to move to Florida to help care for Barbish in his twilight years. He installed her as the manager of his jewelry store and the nominal director of the foundation. On everything from checks to tax returns, Barbish had Laura sign his name. She thought she was doing solid charitable work. Every day, she randomly selected 30 names from the phone book and called for donations. Barbish had prepared the script: The money will be spent on disabled agents, death benefits, bulletproof vests. The goal was to donate $20 million. Laura estimates that in just two years on the Gulf Coast, Barbish took in about $5.5 million through a variety of cons. The Pearl for Peace Foundation’s mission statement ended with what can be read as a blessing, or a curse: “Let the Legend and the Legacy live on from generation to generation …” When I visited Laura in Bradenton, just outside Sarasota, in October, Hurricane Nate had recently struck the Gulf Coast, and trucks were still cruising around town, collecting broken palms. She lives in a bungalow with her third husband, Robert Horn, along with five borzoi dogs, two cockatoos, and a foulmouthed 68-year-old parrot that once belonged to Victor Barbish. Halloween was coming, and the couple had decorated, submerging a plastic replica of the Pearl of Lao Tzu in water: the brain in a vat. The story of Laura and Robert’s union is also the story of her final break with Barbish. While operating the foundation, Laura liked to walk her borzoi through the streets of old Sarasota, and she’d be asked whether she’d ever seen the man with the same striking breed of dog. When she saw the two out walking, she approached the man, who introduced himself as Robert Horn. In a publicity stunt for the jewelry store, they had a Wiccan minister marry their borzoi on the street out front. The humans married soon after, in 2007. Robert was excited to join a large Italian family, headed by a man who struck him as “the godfather of Florida,” the owner of the world-famous Pearl of Lao Tzu. One day, he heard his father-in-law on the phone, sounding distressed. Barbish had found a buyer in New York City, he overheard, but didn’t have the cash in hand to securely transport the pearl. The deal was in peril. Robert leaped at the opportunity to help his new family. It would be only a few months, anyway, until the sale cleared. An accountant by training, Robert still can’t fathom the spell he was under when he cut Barbish a check for $100,000. Although Laura suffered from fibromyalgia, Barbish made her sleep in the jewelry store to protect the merchandise. When he started telling her that jewels were missing from the safe, and accusing her of negligence, Laura thought she was losing her mind. Relying on her years in loss prevention, she staked out the store from a nearby restaurant, and saw Barbish entering the premises after hours. The discovery prompted her to finally turn an investigative lens on her father. She began questioning him about where the foundation’s money had gone, and the exact nature of his deals. Barbish reacted with hostility to her sudden back talk. When he died, peacefully at home in January 2008, his widow, Laura’s aunt, made keepsakes with his ashes and distributed them to his four children. Laura didn’t get one. She obtained her adoption papers, from when her grandparents became her guardians, from the state of Illinois and didn’t recognize the name of her biological father, Richard Walters. By the time she tracked him down, she found only his ashes in an urn. He’d died in 2007. So now she knew. A 50-year hypnosis broke, and Laura began to perceive the full fraudulence of her past. She told Robert to hire a lawyer to get his money back. (Her own, she realized, was long gone.) The Barbish family took this as a direct assault, and the couple claim that Mario Barbish, the executor of his father’s estate, threatened to have them killed if Robert pursued his money. Laura says it wasn’t the first time she feared for her life; she’d earlier hidden a letter: If my husband or I come to harm, please investigate. (Mario denies having issued the threat, calling Laura a “delusional woman” and disputing her version of events.) Yet to his dying breath, Victor Barbish had seen himself as the real victim, a “passionate romanticist” who’d placed too much trust in more-imperfect souls. “I almost was a billionaire,” he lamented in his will, “but due to dishonest law firms, banks and brokers, I got swindled out of my wealth.” Still, he took solace that his legacy was secure. “Fortunately you, my loved ones, were protected,” he wrote. “You have an article in your corporation that is valued between $38–$60 million.” Beneath a signature that doesn’t appear to be his, Victor Barbish added an apt motto for his life: “This is who I am and wish to be.” With the help of Ebby Salinas, a former partner from loss prevention, Laura has been deconstructing Victor Barbish’s lies in her memoir, The Last Con. There’s an element of vindictiveness to the project. When it’s finally finished, Laura and Ebby intend to self-publish and tour it through the cities where Barbish lived, laying waste to the myths he constructed. They want to see The Last Con made into a movie, a stage play, an episode of American Greed. Whatever success The Last Con enjoys, it won’t make up for Laura’s losses. For that, she’s recently turned to a faith her grandmother once practiced in secret—metaphysical Christianity. She’s become an energetic healer in the church, according to which death is merely a transition from one form of energy to another. “Lisa is with me all the time,” Laura told me—manifesting as a barn dove, or purple flowers. Her connection to her deceased husband, Phillip, isn’t so vivid, but in times of crisis, she’ll hear a song by Elvis, and know he’s there. Before leaving Florida, I visited the lawyer for the Barbish estate, who’s functioned as something like the janitor for the aftermath. I saw Robert Horn’s name on a list of claims, along with dozens of others. Despite the alleged threats, Robert had pursued his money after all. But Barbish’s other assets couldn’t come close to satisfying everyone. Only a sale of his share in the pearl could initiate the needed cascade. Even the estate’s lawyer said he was owed half a million dollars. When I asked why on Earth he kept working the case, he said he has to know how the story ends. For decades, the pearl case has dragged on in court, as litigants have tried to finally force a sale and get their money back. The original players are passing away—only Peter Hoffman remains—and the old animosities are enacted by latecomers, like a famous show revived by understudies. This state of paralysis was determined by the fates of two women, who died without ever hearing about the Pearl of Lao Tzu. A fter midnight on March 25, 1974, Ann Phillips was riding in a Cadillac with her husband, Tom, on the Hancock Expressway, in Colorado Springs. When a police light swirled behind them, Tom dutifully pulled over. But instead of police, masked men emerged from the car. They shot Ann dead, knocked her husband unconscious, and fled into the night. Twenty months later, on the evening of November 23, 1975, a man answered the door at the house of his aunt Eloise Bonicelli on West Arvada Street, also in Colorado Springs. As soon as the nephew opened the door, a stranger in a stocking cap shot him in the chest and stormed the house. The nephew escaped to the basement, and minutes later found his aunt in the fetal position on her bedroom floor, dead from a bullet through the heart. For 25 years, the murders went unsolved. But as it turned out, the husbands of Ann Phillips and Eloise Bonicelli had two things in common: They’d both hired a hit man to kill their wives, and they both became investors in the Pearl of Lao Tzu. Joseph Bonicelli owned legitimate businesses in Colorado Springs—a bar, a used-car lot, a construction company—but his reputation was far from spotless. Many former acquaintances recall him as a mobster, or at least a “gangster type”; he’d owned a massage parlor where a woman had been killed before it burned down. Others remember him as a man who dreamed big. In the 1970s, he built a nascar -style racetrack, the Colorado Springs International Speedway, out near the Air Force base. Tom Phillips also owned a bar, but he was never particularly entrepreneurial. He was a heavy gambler, known as “Mr. P.” in Las Vegas, where the house always won. Yet he had an uncanny knack for getting close to people with money, people like Joseph Bonicelli. Even those who loathed Phillips grant that he was charming. By his own admission, Tom Phillips contracted the murder of his wife to collect on her $300,000 life-insurance policy. He paid a local barber to arrange the hit, and staged himself as the victim of a robbery-homicide. So pleased was Phillips with the barber’s service, he recommended it to Bonicelli, who was staring down a costly and bitter divorce with Eloise. Neither man was ever brought to justice—not while alive, anyway. I n Colorado Springs today, some controversy remains over why Bonicelli was finally accused of arranging Eloise’s murder, several years after his death in 1998. Her children say they were motivated to reopen the case by a desire to honor their mother’s memory; others claim that it was an attempt to wrest control of Bonicelli’s estate from his new wife and her daughter, to whom he’d left everything. The means by which Bonicelli was posthumously tried have certainly invited questions. In exchange for testifying against the dead man, Tom Phillips was granted full immunity for arranging his own wife’s murder. Even though he’d been the connection between Bonicelli and the hit man, and committed the exact same heinous crime, Phillips was allowed to go free. He has since died. Based on the Phillips testimony, the children of Eloise brought a civil suit against their dead father’s estate, which possessed at least one major asset that they knew of: a one-third stake in the Pearl of Lao Tzu. Around 1984, Phillips introduced Bonicelli and Barbish, and Barbish brandished a contract for a sale purportedly authored by Ferdinand Marcos. Bonicelli had just sold his speedway for $750,000, and he sank the whole sum into the pearl. Naturally, the sale fell through, and Bonicelli never got over it. In his final years, he’d sit at his kitchen table with a .38, promising to kill Phillips on sight. As for Barbish, Bonicelli said he wanted to blow up his house. In 2005, seven years after his death, Bonicelli was finally found responsible for Eloise’s murder. The judgment was directly tied to the value of the pearl. Though defense lawyers produced records showing that it had only ever sold for $200,000—when Barbish bought it from Cobb’s estate—the testimony of Buzz Steenrod carried the day. He had spruced up his previous appraisal, adjusting for “economic fluctuations,” and set the pearl’s value at $59.75 million. Before a jury, he explained how the pearl had been cultivated by Lao Tzu more than 2,500 years ago. “His thought was that it would symbolize peace and unity of all mankind,” he testified. “This is not a conventional pearl.” The jury awarded Eloise’s children what was reported to be the largest wrongful-death judgment in Colorado history: $32.4 million. Today, the Pearl of Lao Tzu is legally divided between Peter Hoffman and the estate of Victor Barbish; Eloise Bonicelli’s children are owed half of Barbish’s share in the event of a sale. The court battles have waylaid efforts to sell the pearl. But toward the end of 2017, I began to hear whispers that the path might be clearing. Curious to know the status of the pearl, I met Mario Barbish, Victor’s son and the executor of his estate, for lunch at an outlet mall on the outskirts of Colorado Springs. “I totally believe in the entire story,” he told me. “I don’t question it at all.” He believes the pearl was cultivated in ever-larger clams through the centuries; he believes Lao Tzu’s amulet is still lodged deep inside the jewel. “It’s like I’m a Christian,” he said. “I believe in Jesus Christ. Can I prove it? No, it’s a belief.” Mario also believes that the pearl’s reputation has been unfairly sullied. When I met him, the #MeToo movement had been in the news, and Mario likened it to what’s happened to the Pearl of Lao Tzu. “You can discredit somebody’s character, and it never goes away,” he said. What the jewel needs is positive writing, positive promotion, maybe a world tour. “It’s really time to blow life back into the pearl.” To that end, Mario showed me a brochure he’d compiled. It included photos of the pearl laid out on what appeared to be a beach towel, and several pages of text relating the legend. It was almost sad to see Wilburn Cobb’s fantasy ground up like this: Only such a campaign could attract the right buyer, Mario insisted. As for the price, he produced a copy of the Sparrow appraisal, and cited $100 million as his benchmark. In the final analysis, Mario said, the Pearl of Lao Tzu is priceless. When I asked whether he’d consider selling it through an auction house, he demurred. “You want the auction house to think like you do,” he said. “That attitude is what’s going to bring the money.” If a house has its doubts about the pearl’s pricelessness, why would he entrust it to them? And the houses certainly do seem to have doubts. I obtained a memo circulated to the owners in August 2016 by David Beck, a lawyer in Santa Cruz, California, who represents the interests of a long-deceased man. (“I started working the Pearl case when I was a new attorney in the mid-1980s,” Beck wrote. “Now I am nearing retirement.”) Slowly but surely, he’d seen the many claims on the pearl defeated; only Joseph Bonicelli’s has held up in court. At the time of the memo’s writing, Beck stood as the last lawyer still trying to wrestle money out of the pearl. In the final episode of his 30-year struggle, he’d filed a motion to compel a sale, trying to initiate the long-awaited settlements. He’d wanted to understand how such a sale might occur, and he’d asked the esteemed natural-history department at Bonhams, the British auction house, what it would look like to sell the pearl. The department prepared a proposal. But it showed no $100 million figure, no $75 million, no $42 million. Instead, Bonhams offered an estimate of $100,000 to $150,000. “The Pearl has no value except for any historical value there may be,” Bonhams said. “Beyond that, it is a mere curiosity.” Beck’s memo was met with silence. O n February 28, 2018, a United States District Court denied Beck’s motion. And so, after more than 30 years, the final claim on the Pearl of Lao Tzu was vanquished. But obstacles to a sale remain. Mario Barbish told me that Asia would be his ideal market. But because the Tridacna clam is an endangered species, in order to export the pearl, the Philippines would probably have to endorse the transaction—an unlikely scenario. A buyer must emerge from within the United States, but the pearl’s beauty is lost on many Americans. Newspapers have described it as “wrinkled,” a “deformed brain,” “a blob.” Its ungainly size means that it will never be seen as jewelry; one attorney said, “It’s not the sort of thing you wear around your neck unless you’re the Incredible Hulk.” Perhaps its status as the world’s largest pearl would be sufficient enticement, but even that mantle is threatened. In 2016, a fisherman from Palawan came forward with a specimen he’d discovered 10 years earlier when his anchor snagged a giant clam. (He’d been keeping the pearl under his bed as a good-luck charm.) While it hasn’t been officially verified, this pearl reportedly weighs 75 pounds, dwarfing the Pearl of Lao Tzu’s Guinness record. As David Beck observed in his memo to the owners, “We may have missed our moment.” A day after the motion was denied, I called Mario Barbish. He wanted to know the status of my story, which he hoped would focus on the pearl’s beauty and religious significance. When I described what I had learned, his affable tone rocketed to a register of high indignation. The curse of the pearl, he said, was people like me, who sought to discredit the legend. I couldn’t know the truth; I hadn’t spoken with Victor Barbish, or Lee Sparrow, or Wilburn Cobb. “You’ve never seen the pearl. You’ve never seen the growth lines. You don’t know anything about the pearl.” Only Mario had the documents proving the valuation beyond a reasonable doubt, but when I asked him to produce them, he refused: “I could, but I’m not.” He seemed to find me pitiable. “The pearl would amaze you if you just held it in your hands,” he said. “A lot of this garbage you’re spewing out of your mouth, you would let it go, because you’d feel that intrinsic value just holding the pearl.” The Pearl of Lao Tzu isn’t a gem, Mario told me; it’s a “religious artifact.” And just as if the Shroud of Turin went up for auction, he said, those who believe are the ones who will bid. The appraisals will become credible, as if by magic, once you put your faith in the story. (Not the Bonhams appraisal, however; Mario said, “They’re out of their mind.”) That leap of faith will be the sign that Lao Tzu’s pearl has found its true guardian. When I hung up, I thought of something Wilburn Cobb’s daughter Ruth had told me in Union City. We were discussing the new, 75-pound pearl and what its discovery meant for the Pearl of Lao Tzu. Cobb’s pearl was still the famous one, she said. “But the fame came from the stories, and my father started that. And I don’t know what that brings.” The pearl’s long, destructive fiction finally ends with the owners now left holding what is likely the world’s second-largest pearl—a bogus religious artifact—seemingly unable to accept the truth, and escape. If there is something mystical about the Pearl of Lao Tzu, it’s the story’s strange tendency toward repetition. Stare long enough, and the owners’ stubborn faith looks like that of Victor Barbish, who stitched myths together and called them history, or like that of Wilburn Cobb, who never relinquished his romance. They begin to seem like the diver, who drowned all those years ago, when he glimpsed that first fateful flash of white. This article appears in the June 2018 print edition with the headline “Chasing the Pearl of Lao Tzu.” "

"The Birth of the New American Aristocracy - The Atlantic"

"https://www.theatlantic.com/magazine/archive/2018/06/the-birth-of-a-new-american-aristocracy/559130"

"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 A Muslim among Israeli settlers, the pearl at the center of an 80-year-old hoax, Marti Noxon putting women’s rage on TV, and pop culture’s response to Trump. Plus, Kissinger on AI and the end of humanity, an interview with Seth Meyers, the search for life on Mars, NRATV, and more. The 9.9 Percent Is the New American Aristocracy Matthew Stewart Is Television Ready for Angry Women? Sophie Gilbert A Muslim Among Israeli Settlers Wajahat Ali Chasing the Pearl of Lao Tzu Michael LaPointe Can Protest Art Get Its Mojo Back? Spencer Kornhaber How the Enlightenment Ends Henry A. Kissinger A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. The 9.9 Percent Is the New American Aristocracy The class divide is already toxic, and is fast becoming unbridgeable. You’re probably part of the problem. 1. The Aristocracy Is Dead … For about a week every year in my childhood, I was a member of one of America’s fading aristocracies. Sometimes around Christmas, more often on the Fourth of July, my family would take up residence at one of my grandparents’ country clubs in Chicago, Palm Beach, or Asheville, North Carolina. The breakfast buffets were magnificent, and Grandfather was a jovial host, always ready with a familiar story, rarely missing an opportunity for gentle instruction on proper club etiquette. At the age of 11 or 12, I gathered from him, between his puffs of cigar smoke, that we owed our weeks of plenty to Great-Grandfather, Colonel Robert W. Stewart, a Rough Rider with Teddy Roosevelt who made his fortune as the chairman of Standard Oil of Indiana in the 1920s. I was also given to understand that, for reasons traceable to some ancient and incomprehensible dispute, the Rockefellers were the mortal enemies of our clan. Only much later in life did I learn that the stories about the Colonel and his tangles with titans fell far short of the truth. At the end of each week, we would return to our place. My reality was the aggressively middle-class world of 1960s and ’70s U.S. military bases and the communities around them. Life was good there, too, but the pizza came from a box, and it was Lucky Charms for breakfast. Our glory peaked on the day my parents came home with a new Volkswagen camper bus. As I got older, the holiday pomp of patriotic luncheons and bridge-playing rituals came to seem faintly ridiculous and even offensive, like an endless birthday party for people whose chief accomplishment in life was just showing up. I belonged to a new generation that believed in getting ahead through merit, and we defined merit in a straightforward way: test scores, grades, competitive résumé-stuffing, supremacy in board games and pickup basketball, and, of course, working for our keep. For me that meant taking on chores for the neighbors, punching the clock at a local fast-food restaurant, and collecting scholarships to get through college and graduate school. I came into many advantages by birth, but money was not among them. I’ve joined a new aristocracy now, even if we still call ourselves meritocratic winners. If you are a typical reader of The Atlantic , you may well be a member too. (And if you’re not a member, my hope is that you will find the story of this new class even more interesting—if also more alarming.) To be sure, there is a lot to admire about my new group, which I’ll call—for reasons you’ll soon see—the 9.9 percent. We’ve dropped the old dress codes, put our faith in facts, and are (somewhat) more varied in skin tone and ethnicity. People like me, who have waning memories of life in an earlier ruling caste, are the exception, not the rule. By any sociological or financial measure, it’s good to be us. It’s even better to be our kids. In our health, family life, friendship networks, and level of education, not to mention money, we are crushing the competition below. But we do have a blind spot, and it is located right in the center of the mirror: We seem to be the last to notice just how rapidly we’ve morphed, or what we’ve morphed into. Related Story The False Promise of Meritocracy The meritocratic class has mastered the old trick of consolidating wealth and passing privilege along at the expense of other people’s children. We are not innocent bystanders to the growing concentration of wealth in our time. We are the principal accomplices in a process that is slowly strangling the economy, destabilizing American politics, and eroding democracy. Our delusions of merit now prevent us from recognizing the nature of the problem that our emergence as a class represents. We tend to think that the victims of our success are just the people excluded from the club. But history shows quite clearly that, in the kind of game we’re playing, everybody loses badly in the end. 2. The Discreet Charm of the 9.9 Percent Let’s talk first about money—even if money is only one part of what makes the new aristocrats special. There is a familiar story about rising inequality in the United States, and its stock characters are well known. The villains are the fossil-fueled plutocrat, the Wall Street fat cat, the callow tech bro, and the rest of the so-called top 1 percent. The good guys are the 99 percent, otherwise known as “the people” or “the middle class.” The arc of the narrative is simple: Once we were equal, but now we are divided. The story has a grain of truth to it. But it gets the characters and the plot wrong in basic ways. It is in fact the top 0.1 percent who have been the big winners in the growing concentration of wealth over the past half century. According to the UC Berkeley economists Emmanuel Saez and Gabriel Zucman, the 160,000 or so households in that group held 22 percent of America’s wealth in 2012 , up from 10 percent in 1963. If you’re looking for the kind of money that can buy elections, you’ll find it inside the top 0.1 percent alone. A Tale of Three Classes ( Figure 1 ): The 9.9 percent hold most of the wealth in the United States. Every piece of the pie picked up by the 0.1 percent, in relative terms, had to come from the people below. But not everyone in the 99.9 percent gave up a slice. Only those in the bottom 90 percent did. At their peak, in the mid-1980s, people in this group held 35 percent of the nation’s wealth. Three decades later that had fallen 12 points—exactly as much as the wealth of the 0.1 percent rose. In between the top 0.1 percent and the bottom 90 percent is a group that has been doing just fine. It has held on to its share of a growing pie decade after decade. And as a group, it owns substantially more wealth than do the other two combined. In the tale of three classes (see Figure 1), it is represented by the gold line floating high and steady while the other two duke it out. You’ll find the new aristocracy there. We are the 9.9 percent. So what kind of characters are we, the 9.9 percent? We are mostly not like those flamboyant political manipulators from the 0.1 percent. We’re a well-behaved, flannel-suited crowd of lawyers, doctors, dentists, mid-level investment bankers, M.B.A.s with opaque job titles, and assorted other professionals—the kind of people you might invite to dinner. In fact, we’re so self-effacing, we deny our own existence. We keep insisting that we’re “middle class.” As of 2016, it took $1.2 million in net worth to make it into the 9.9 percent; $2.4 million to reach the group’s median; and $10 million to get into the top 0.9 percent. (And if you’re not there yet, relax: Our club is open to people who are on the right track and have the right attitude.) “We are the 99 percent” sounds righteous, but it’s a slogan, not an analysis. The families at our end of the spectrum wouldn’t know what to do with a pitchfork. We are also mostly, but not entirely, white. According to a Pew Research Center analysis, African Americans represent 1.9 percent of the top 10th of households in wealth; Hispanics, 2.4 percent; and all other minorities, including Asian and multiracial individuals, 8.8 percent—even though those groups together account for 35 percent of the total population. One of the hazards of life in the 9.9 percent is that our necks get stuck in the upward position. We gaze upon the 0.1 percent with a mixture of awe, envy, and eagerness to obey. As a consequence, we are missing the other big story of our time. We have left the 90 percent in the dust—and we’ve been quietly tossing down roadblocks behind us to make sure that they never catch up. Let’s suppose that you start off right in the middle of the American wealth distribution. How high would you have to jump to make it into the 9.9 percent? In financial terms, the measurement is easy and the trend is unmistakable. In 1963, you would have needed to multiply your wealth six times. By 2016, you would have needed to leap twice as high—increasing your wealth 12-fold—to scrape into our group. If you boldly aspired to reach the middle of our group rather than its lower edge, you’d have needed to multiply your wealth by a factor of 25. On this measure, the 2010s look much like the 1920s. If you are starting at the median for people of color, you’ll want to practice your financial pole-vaulting. The Institute for Policy Studies calculated that, setting aside money invested in “durable goods” such as furniture and a family car, the median black family had net wealth of $1,700 in 2013, and the median Latino family had $2,000, compared with $116,800 for the median white family. A 2015 study in Boston found that the wealth of the median white family there was $247,500, while the wealth of the median African American family was $8. That is not a typo. That’s two grande cappuccinos. That and another 300,000 cups of coffee will get you into the 9.9 percent. Video: America’s Class Problem N one of this matters, you will often hear, because in the United States everyone has an opportunity to make the leap: Mobility justifies inequality. As a matter of principle, this isn’t true. In the United States, it also turns out not to be true as a factual matter. Contrary to popular myth, economic mobility in the land of opportunity is not high, and it’s going down. Imagine yourself on the socioeconomic ladder with one end of a rubber band around your ankle and the other around your parents’ rung. The strength of the rubber determines how hard it is for you to escape the rung on which you were born. If your parents are high on the ladder, the band will pull you up should you fall; if they are low, it will drag you down when you start to rise. Economists represent this concept with a number they call “intergenerational earnings elasticity,” or IGE, which measures how much of a child’s deviation from average income can be accounted for by the parents’ income. An IGE of zero means that there’s no relationship at all between parents’ income and that of their offspring. An IGE of one says that the destiny of a child is to end up right where she came into the world. According to Miles Corak, an economics professor at the City University of New York, half a century ago IGE in America was less than 0.3. Today, it is about 0.5. In America, the game is half over once you’ve selected your parents. IGE is now higher here than in almost every other developed economy. On this measure of economic mobility, the United States is more like Chile or Argentina than Japan or Germany. The story becomes even more disconcerting when you see just where on the ladder the tightest rubber bands are located. Canada, for example, has an IGE of about half that of the U.S. Yet from the middle rungs of the two countries’ income ladders, offspring move up or down through the nearby deciles at the same respectable pace. The difference is in what happens at the extremes. In the United States, it’s the children of the bottom decile and, above all, the top decile—the 9.9 percent—who settle down nearest to their starting point. Here in the land of opportunity, the taller the tree, the closer the apple falls. All of this analysis of wealth percentiles, to be clear, provides only a rough start in understanding America’s evolving class system. People move in and out of wealth categories all the time without necessarily changing social class, and they may belong to a different class in their own eyes than they do in others’. Yet even if the trends in the monetary statistics are imperfect illustrations of a deeper process, they are nonetheless registering something of the extraordinary transformation that’s taking place in our society. A few years ago, Alan Krueger, an economist and a former chairman of the Obama administration’s Council of Economic Advisers, was reviewing the international mobility data when he caught a glimpse of the fundamental process underlying our present moment. Rising immobility and rising inequality aren’t like two pieces of driftwood that happen to have shown up on the beach at the same time, he noted. They wash up together on every shore. Across countries, the higher the inequality, the higher the IGE (see Figure 2). It’s as if human societies have a natural tendency to separate, and then, once the classes are far enough apart, to crystallize. The Great Gatsby Curve ( Figure 2 ): Inequality and class immobility go together. Economists are prudent creatures, and they’ll look up from a graph like that and remind you that it shows only correlation, not causation. That’s a convenient hedge for those of us at the top because it keeps alive one of the founding myths of America’s meritocracy: that our success has nothing to do with other people’s failure. It’s a pleasant idea. But around the world and throughout history, the wealthy have advanced the crystallization process in a straightforward way. They have taken their money out of productive activities and put it into walls. Throughout history, moreover, one social group above all others has assumed responsibility for maintaining and defending these walls. Its members used to be called aristocrats. Now we’re the 9.9 percent. The main difference is that we have figured out how to use the pretense of being part of the middle as one of our strategies for remaining on top. Krueger liked the graph shown in Figure 2 so much that he decided to give it a name: the Great Gatsby Curve. It’s a good choice, and it resonates strongly with me. F. Scott Fitzgerald’s novel about the breakdown of the American dream is set in 1922, or right around the time that my great-grandfather was secretly siphoning money from Standard Oil and putting it into a shell company in Canada. It was published in 1925, just as special counsel was turning up evidence that bonds from that company had found their way into the hands of the secretary of the interior. Its author was drinking his way through the cafés of Paris just as Colonel Robert W. Stewart was running away from subpoenas to testify before the United States Senate about his role in the Teapot Dome scandal. We are only now closing in on the peak of inequality that his generation achieved, in 1928. I’m sure they thought it would go on forever, too. 3. The Origin of a Species Money can’t buy you class, or so my grandmother used to say. But it can buy a private detective. Grandmother was a Kentucky debutante and sometime fashion model (kind of like Daisy Buchanan in The Great Gatsby , weirdly enough), so she knew what to do when her eldest son announced his intention to marry a woman from Spain. A gumshoe promptly reported back that the prospective bride’s family made a living selling newspapers on the streets of Barcelona. Grandmother instituted an immediate and total communications embargo. In fact, my mother’s family owned and operated a large paper-goods factory. When children came, Grandmother at last relented. Determined to do the right thing, she arranged for the new family, then on military assignment in Hawaii, to be inscribed in the New York Social Register. Sociologists would say, in their dry language, that my grandmother was a zealous manager of the family’s social capital—and she wasn’t about to let some Spanish street urchin run away with it. She did have a point, even if her facts were wrong. Money may be the measure of wealth, but it is far from the only form of it. Family, friends, social networks, personal health, culture, education, and even location are all ways of being rich, too. These nonfinancial forms of wealth, as it turns out, aren’t simply perks of membership in our aristocracy. They define us. We are the people of good family, good health, good schools, good neighborhoods, and good jobs. We may want to call ourselves the “5Gs” rather than the 9.9 percent. We are so far from the not-so-good people on all of these dimensions, we are beginning to resemble a new species. And, just as in Grandmother’s day, the process of speciation begins with a love story—or, if you prefer, sexual selection. The polite term for the process is assortative mating. The phrase is sometimes used to suggest that this is another of the wonders of the internet age, where popcorn at last meets butter and Yankees fan finds Yankees fan. In fact, the frenzy of assortative mating today results from a truth that would have been generally acknowledged by the heroines of any Jane Austen novel: Rising inequality decreases the number of suitably wealthy mates even as it increases the reward for finding one and the penalty for failing to do so. According to one study, the last time marriage partners sorted themselves by educational status as much as they do now was in the 1920s. For most of us, the process is happily invisible. You meet someone under a tree on an exclusive campus or during orientation at a high-powered professional firm, and before you know it, you’re twice as rich. But sometimes—Grandmother understood this well—extra measures are called for. That’s where our new technology puts bumbling society detectives to shame. Ivy Leaguers looking to mate with their equals can apply to join a dating service called the League. It’s selective, naturally: Only 20 to 30 percent of New York applicants get in. It’s sometimes called “Tinder for the elites.” Explore the June 2018 Issue Check out more from this issue and find your next story to read. It is misleading to think that assortative mating is symmetrical, as in city mouse marries city mouse and country mouse marries country mouse. A better summary of the data would be: Rich mouse finds love, and poor mouse gets screwed. It turns out—who knew?—that people who are struggling to keep it all together have a harder time hanging on to their partner. According to the Harvard political scientist Robert Putnam, 60 years ago just 20 percent of children born to parents with a high-school education or less lived in a single-parent household; now that figure is nearly 70 percent. Among college-educated households, by contrast, the single-parent rate remains less than 10 percent. Since the 1970s, the divorce rate has declined significantly among college-educated couples, while it has risen dramatically among couples with only a high-school education—even as marriage itself has become less common. The rate of single parenting is in turn the single most significant predictor of social immobility across counties, according to a study led by the Stanford economist Raj Chetty. None of which is to suggest that individuals are wrong to seek a suitable partner and make a beautiful family. People should—and presumably always will—pursue happiness in this way. It’s one of the delusions of our meritocratic class, however, to assume that if our actions are individually blameless, then the sum of our actions will be good for society. We may have studied Shakespeare on the way to law school, but we have little sense for the tragic possibilities of life. The fact of the matter is that we have silently and collectively opted for inequality, and this is what inequality does. It turns marriage into a luxury good, and a stable family life into a privilege that the moneyed elite can pass along to their children. How do we think that’s going to work out? This divergence of families by class is just one part of a process that is creating two distinct forms of life in our society. Stop in at your local yoga studio or SoulCycle class, and you’ll notice that the same process is now inscribing itself in our own bodies. In 19th-century England, the rich really were different. They didn’t just have more money; they were taller—a lot taller. According to a study colorfully titled “On English Pygmies and Giants,” 16-year-old boys from the upper classes towered a remarkable 8.6 inches, on average, over their undernourished, lower-class countrymen. We are reproducing the same kind of division via a different set of dimensions. Obesity, diabetes, heart disease, kidney disease, and liver disease are all two to three times more common in individuals who have a family income of less than $35,000 than in those who have a family income greater than $100,000. Among low-educated, middle-aged whites, the death rate in the United States—alone in the developed world—increased in the first decade and a half of the 21st century. Driving the trend is the rapid growth in what the Princeton economists Anne Case and Angus Deaton call “deaths of despair” —suicides and alcohol- and drug-related deaths. The sociological data are not remotely ambiguous on any aspect of this growing divide. We 9.9 percenters live in safer neighborhoods, go to better schools, have shorter commutes, receive higher-quality health care, and, when circumstances require, serve time in better prisons. We also have more friends—the kind of friends who will introduce us to new clients or line up great internships for our kids. These special forms of wealth offer the further advantages that they are both harder to emulate and safer to brag about than high income alone. Our class walks around in the jeans and T‑shirts inherited from our supposedly humble beginnings. We prefer to signal our status by talking about our organically nourished bodies, the awe-inspiring feats of our offspring, and the ecological correctness of our neighborhoods. We have figured out how to launder our money through higher virtues. Most important of all, we have learned how to pass all of these advantages down to our children. In America today, the single best predictor of whether an individual will get married, stay married, pursue advanced education, live in a good neighborhood, have an extensive social network, and experience good health is the performance of his or her parents on those same metrics. We’re leaving the 90 percent and their offspring far behind in a cloud of debts and bad life choices that they somehow can’t stop themselves from making. We tend to overlook the fact that parenting is more expensive and motherhood more hazardous in the United States than in any other developed country, that campaigns against family planning and reproductive rights are an assault on the families of the bottom 90 percent, and that law-and-order politics serves to keep even more of them down. We prefer to interpret their relative poverty as vice: Why can’t they get their act together? New forms of life necessarily give rise to new and distinct forms of consciousness. If you doubt this, you clearly haven’t been reading the “personal and household services” ads on Monster.com. At the time of this writing, the section for my town of Brookline, Massachusetts, featured one placed by a “busy professional couple” seeking a “Part Time Nanny.” The nanny (or manny—the ad scrupulously avoids committing to gender) is to be “bright, loving, and energetic”; “friendly, intelligent, and professional”; and “a very good communicator, both written and verbal.” She (on balance of probability) will “assist with the care and development” of two children and will be “responsible for all aspects of the children’s needs,” including bathing, dressing, feeding, and taking the young things to and from school and activities. That’s why a “college degree in early childhood education” is “a plus.” In short, Nanny is to have every attribute one would want in a terrific, professional, college-educated parent. Except, of course, the part about being an actual professional, college-educated parent. There is no chance that Nanny will trade places with our busy 5G couple. She “must know the proper etiquette in a professionally run household” and be prepared to “accommodate changing circumstances.” She is required to have “5+ years experience as a Nanny,” which makes it unlikely that she’ll have had time to get the law degree that would put her on the other side of the bargain. All of Nanny’s skills, education, experience, and professionalism will land her a job that is “Part Time.” The ad is written in flawless, 21st-century business-speak, but what it is really seeking is a governess—that exquisitely contradictory figure in Victorian literature who is both indistinguishable in all outward respects from the upper class and yet emphatically not a member of it. Nanny’s best bet for moving up in the world is probably to follow the example of Jane Eyre and run off with the lord (or lady) of the manor. If you look beyond the characters in this unwritten novel about Nanny and her 5G masters, you’ll see a familiar shape looming on the horizon. The Gatsby Curve has managed to reproduce itself in social, physiological, and cultural capital. Put more accurately: There is only one curve, but it operates through a multiplicity of forms of wealth. Rising inequality does not follow from a hidden law of economics, as the otherwise insightful Thomas Piketty suggested when he claimed that the historical rate of return on capital exceeds the historical rate of growth in the economy. Inequality necessarily entrenches itself through other, nonfinancial, intrinsically invidious forms of wealth and power. We use these other forms of capital to project our advantages into life itself. We look down from our higher virtues in the same way the English upper class looked down from its taller bodies, as if the distinction between superior and inferior were an artifact of nature. That’s what aristocrats do. 4. The Privilege of an Education My 16-year-old daughter is sitting on a couch, talking with a stranger about her dreams for the future. We’re here, ominously enough, because, she says, “all my friends are doing it.” For a moment, I wonder whether we have unintentionally signed up for some kind of therapy. The professional woman in the smart-casual suit throws me a pointed glance and says, “It’s normal to be anxious at a time like this.” She really does see herself as a therapist of sorts. But she does not yet seem to know that the source of my anxiety is the idea of shelling out for a $12,000 “base package” of college-counseling services whose chief purpose is apparently to reduce my anxiety. Determined to get something out of this trial counseling session, I push for recommendations on summer activities. We leave with a tip on a 10-day “cultural tour” of France for high schoolers. In the college-application business, that’s what’s known as an “enrichment experience.” When we get home, I look it up. The price of enrichment: $11,000 for the 10 days. That’s when I hear the legend of the SAT whisperer. If you happen to ride through the yellow-brown valleys of the California coast, past the designer homes that sprout wherever tech unicorns sprinkle their golden stock offerings, you might come across him. His high-school classmates still remember him, almost four decades later, as one of the child wonders of the age. Back then, he and his equally precocious siblings showed off their preternatural verbal and musical talents on a local television program. Now his clients fly him around the state for test-prep sessions with their 16-year-olds. You can hire him for $750, plus transportation, per two-hour weekend session. (There is a weekday discount.) Some of his clients book him every week for a year. At this point, I’m wondering whether life was easier in the old days, when you could buy a spot in the elite university of your choice with cold cash. Then I remind myself that Grandfather lasted only one year at Yale. In those days, the Ivies kicked you out if you weren’t ready for action. Today, you have to self-combust in a newsworthy way before they show you the door. Inevitably, I begin rehearsing the speech for my daughter. It’s perfectly possible to lead a meaningful life without passing through a name-brand college, I’m going to say. We love you for who you are. We’re not like those tacky strivers who want a back-windshield sticker to testify to our superior parenting skills. And why would you want to be an investment banker or a corporate lawyer anyway? But I refrain from giving the speech, knowing full well that it will light up her parental-bullshit detector like a pair of khakis on fire. the skin colors of the nation’s elite student bodies are more varied now, as are their genders, but their financial bones have calcified over the past 30 years. In 1985, 54 percent of students at the 250 most selective colleges came from families in the bottom three quartiles of the income distribution. A similar review of the class of 2010 put that figure at just 33 percent. According to a 2017 study, 38 elite colleges—among them five of the Ivies— had more students from the top 1 percent than from the bottom 60 percent. In his 2014 book, Excellent Sheep , William Deresiewicz, a former English professor at Yale, summed up the situation nicely: “Our new multiracial, gender-neutral meritocracy has figured out a way to make itself hereditary.” The wealthy can also draw on a variety of affirmative-action programs designed just for them. As Daniel Golden points out in The Price of Admission , legacy-admissions policies reward those applicants with the foresight to choose parents who attended the university in question. Athletic recruiting, on balance and contrary to the popular wisdom, also favors the wealthy, whose children pursue lacrosse, squash, fencing, and the other cost-intensive sports at which private schools and elite public schools excel. And, at least among members of the 0.1 percent, the old-school method of simply handing over some of Daddy’s cash has been making a comeback. ( Witness Jared Kushner, Harvard graduate. ) The mother lode of all affirmative-action programs for the wealthy, of course, remains the private school. Only 2.2 percent of the nation’s students graduate from nonsectarian private high schools, and yet these graduates account for 26 percent of students at Harvard and 28 percent of students at Princeton. The other affirmative-action programs, the kind aimed at diversifying the look of the student body, are no doubt well intended. But they are to some degree merely an extension of this system of wealth preservation. Their function, at least in part, is to indulge rich people in the belief that their college is open to all on the basis of merit. The plummeting admission rates of the very top schools nonetheless leave many of the children of the 9.9 percent facing long odds. But not to worry, junior 9.9 percenters! We’ve created a new range of elite colleges just for you. Thanks to ambitious university administrators and the ever-expanding rankings machine at U.S. News & World Report , 50 colleges are now as selective as Princeton was in 1980, when I applied. The colleges seem to think that piling up rejections makes them special. In fact, it just means that they have collectively opted to deploy their massive, tax-subsidized endowments to replicate privilege rather than fulfill their duty to produce an educated public. The only thing going up as fast as the rejection rates at selective colleges is the astounding price of tuition. Measured relative to the national median salary, tuition and fees at top colleges more than tripled from 1963 to 2013. Throw in the counselors, the whisperers, the violin lessons, the private schools, and the cost of arranging for Junior to save a village in Micronesia, and it adds up. To be fair, financial aid closes the gap for many families and keeps the average cost of college from growing as fast as the sticker price. But that still leaves a question: Why are the wealthy so keen to buy their way in? The short answer, of course, is that it’s worth it. In the United States, the premium that college graduates earn over their non-college-educated peers in young adulthood exceeds 70 percent. The return on education is 50 percent higher than what it was in 1950, and is significantly higher than the rate in every other developed country. In Norway and Denmark, the college premium is less than 20 percent; in Japan, it is less than 30 percent; in France and Germany, it’s about 40 percent. All of this comes before considering the all-consuming difference between “good” schools and the rest. Ten years after starting college, according to data from the Department of Education, the top decile of earners from all schools had a median salary of $68,000. But the top decile from the 10 highest-earning colleges raked in $220,000—make that $250,000 for No. 1, Harvard—and the top decile at the next 30 colleges took home $157,000. (Not surprisingly, the top 10 had an average acceptance rate of 9 percent, and the next 30 were at 19 percent.) It is entirely possible to get a good education at the many schools that don’t count as “good” in our brand-obsessed system. But the “bad” ones really are bad for you. For those who made the mistake of being born to the wrong parents, our society offers a kind of virtual education system. It has places that look like colleges—but aren’t really. It has debt—and that, unfortunately, is real. The people who enter into this class hologram do not collect a college premium; they wind up in something more like indentured servitude. So what is the real source of this premium for a “good education” that we all seem to crave? One of the stories we tell ourselves is that the premium is the reward for the knowledge and skills the education provides us. Another, usually unfurled after a round of drinks, is that the premium is a reward for the superior cranial endowments we possessed before setting foot on campus. We are, as some sociologists have delicately put it, a “cognitive elite.” Behind both of these stories lies one of the founding myths of our meritocracy. One way or the other, we tell ourselves, the rising education premium is a direct function of the rising value of meritorious people in a modern economy. That is, not only do the meritorious get ahead, but the rewards we receive are in direct proportion to our merit. But the fact is that degree holders earn so much more than the rest not primarily because they are better at their job, but because they mostly take different categories of jobs. Well over half of Ivy League graduates, for instance, typically go straight into one of four career tracks that are generally reserved for the well educated: finance, management consulting, medicine, or law. To keep it simple, let’s just say that there are two types of occupations in the world: those whose members have collective influence in setting their own pay, and those whose members must face the music on their own. It’s better to be a member of the first group. Not surprisingly, that is where you will find the college crowd. why do America’s doctors make twice as much as those of other wealthy countries? Given that the United States has placed dead last five times running in the Commonwealth Fund’s ranking of health-care systems in high-income countries, it’s hard to argue that they are twice as gifted at saving lives. Dean Baker, a senior economist with the Center for Economic and Policy Research, has a more plausible suggestion : “When economists like me look at medicine in America—whether we lean left or right politically—we see something that looks an awful lot like a cartel.” Through their influence on the number of slots at medical schools, the availability of residencies, the licensing of foreign-trained doctors, and the role of nurse practitioners, physicians’ organizations can effectively limit the competition their own members face—and that is exactly what they do. Lawyers (or at least a certain elite subset of them) have apparently learned to play the same game. Even after the collapse of the so-called law-school bubble, America’s lawyers are No. 1 in international salary rankings and earn more than twice as much, on average, as their wig-toting British colleagues. The University of Chicago law professor Todd Henderson, writing for Forbes in 2016, offered a blunt assessment : “The American Bar Association operates a state-approved cartel.” Similar occupational licensing schemes provide shelter for the meritorious in a variety of other sectors. The policy researchers Brink Lindsey and Steven Teles detail the mechanisms in The Captured Economy. Dentists’ offices, for example, have a glass ceiling that limits what dental hygienists can do without supervision, keeping their bosses in the 9.9 percent. Copyright and patent laws prop up profits and salaries in the education-heavy pharmaceutical, software, and entertainment sectors. These arrangements are trifles, however, compared with what’s on offer in tech and finance, two of the most powerful sectors of the economy. By now we’re thankfully done with the tech-sector fairy tales in which whip-smart cowboys innovate the heck out of a stodgy status quo. The reality is that five monster companies—you know the names—are worth about $3.5 trillion combined, and represent more than 40 percent of the market capital on the nasdaq stock exchange. Much of the rest of the technology sector consists of virtual entities waiting patiently to feed themselves to these beasts. Let’s face it: This is Monopoly money with a smiley emoji. Our society figured out some time ago how to deal with companies that attempt to corner the market on viscous substances like oil. We don’t yet know what to do with the monopolies that arise out of networks and scale effects in the information marketplace. Until we do, the excess profits will stick to those who manage to get closest to the information honeypot. You can be sure that these people will have a great deal of merit. The candy-hurling godfather of today’s meritocratic class, of course, is the financial-services industry. Americans now turn over $1 of every $12 in GDP to the financial sector; in the 1950s, the bankers were content to keep only $1 out of $40. The game is more sophisticated than a two-fisted money grab, but its essence was made obvious during the 2008 financial crisis. The public underwrites the risks; the financial gurus take a seat at the casino; and it’s heads they win, tails we lose. The financial system we now have is not a product of nature. It has been engineered, over decades, by powerful bankers, for their own benefit and for that of their posterity. Who is not in on the game? Auto workers, for example. Caregivers. Retail workers. Furniture makers. Food workers. The wages of American manufacturing and service workers consistently hover in the middle of international rankings. The exceptionalism of American compensation rates comes to an end in the kinds of work that do not require a college degree. You see, when educated people with excellent credentials band together to advance their collective interest, it’s all part of serving the public good by ensuring a high quality of service, establishing fair working conditions, and giving merit its due. That’s why we do it through “associations,” and with the assistance of fellow professionals wearing white shoes. When working-class people do it—through unions—it’s a violation of the sacred principles of the free market. It’s thuggish and anti-modern. Imagine if workers hired consultants and “compensation committees,” consisting of their peers at other companies, to recommend how much they should be paid. The result would be—well, we know what it would be, because that’s what CEOs do. It isn’t a coincidence that the education premium surged during the same years that membership in trade unions collapsed. In 1954, 28 percent of all workers were members of trade unions, but by 2017 that figure was down to 11 percent. education—the thing itself , not the degree—is always good. A genuine education opens minds and makes good citizens. It ought to be pursued for the sake of society. In our unbalanced system, however, education has been reduced to a private good, justifiable only by the increments in graduates’ paychecks. Instead of uniting and enriching us, it divides and impoverishes. 
Which is really just a way of saying that our worthy ideals of educational opportunity are ultimately no match for the tidal force of the Gatsby Curve. The metric that has tracked the rising college premium with the greatest precision is—that’s right—intergenerational earnings elasticity, or IGE. Across countries, the same correlation obtains: the higher the college premium, the lower the social mobility. As I’m angling all the angles for my daughter’s college applications—the counselor is out, and the SAT whisperer was never going to happen—I realize why this delusion of merit is so hard to shake. If I—I mean, she—can pull this off, well, there’s the proof that we deserve it! If the system can be gamed, well then, our ability to game the system has become the new test of merit. So go ahead and replace the SATs with shuffleboard on the high seas, or whatever you want. Who can doubt that we’d master that game, too? How quickly would we convince ourselves of our absolute entitlement to the riches that flow directly and tangibly from our shuffling talent? How soon before we perfected the art of raising shuffleboard wizards? Would any of us notice or care which way the ship was heading? Let’s suppose that some of us do look up. We see the iceberg. Will that induce us to diminish our exertions in supreme child-rearing? The grim truth is that, as long as good parenting and good citizenship are in conflict, we’re just going to pack a few more violins for the trip. 5. The Invisible Hand of Government As far as Grandfather was concerned, the assault on the productive classes began long before the New Deal. It all started in 1913, with the ratification of the Sixteenth Amendment. In case you’ve forgotten, that amendment granted the federal government the power to levy a direct personal-income tax. It also happens that ratification took place just a few months after Grandfather was born, which made sense to me in a strange way. By far the largest part of his lifetime income was attributable to his birth. Grandfather was a stockbroker for a time. I eventually figured out that he mostly traded his own portfolio and bought a seat at the stock exchange for the purpose. Politics was a hobby, too. At one point, he announced his intention to seek the Republican nomination for lieutenant governor of Connecticut. (It wasn’t clear whether anybody outside the clubhouse heard him.) What he really liked to do was fly. The memories that mattered most to him were his years of service as a transport pilot during World War II. Or the time he and Grandmother took to the Midwestern skies in a barnstorming plane. My grandparents never lost faith in the limitless possibilities of a life free from government. But in their last years, as the reserves passed down from the Colonel ran low, they became pretty diligent about collecting their Social Security and Medicare benefits. There is a page in the book of American political thought—Grandfather knew it by heart—that says we must choose between government and freedom. But if you read it twice, you’ll see that what it really offers is a choice between government you can see and government you can’t. Aristocrats always prefer the invisible kind of government. It leaves them free to exercise their privileges. We in the 9.9 percent have mastered the art of getting the government to work for us even while complaining loudly that it’s working for those other people. Consider, for starters, the greatly exaggerated reports of our tax burdens. On guest panels this past holiday season, apologists for the latest round of upwardly aimed tax cuts offered versions of Mitt Romney’s claim that the 47 percent of Americans who pay no federal income tax in a typical year have “no skin in the game.” Baloney. Sure, the federal individual-income tax, which raised $1.6 trillion last year, remains progressive. But the $1.2 trillion raised by the payroll tax hits all workers—but not investors, such as Romney—and it hits those making lower incomes at a higher rate, thanks to a cap on the amount of income subject to the tax. Then there’s the $2.3 trillion raised by state and local governments, much of it collected through regressive sales and property taxes. The poorest quintile of Americans pays more than twice the rate of state taxes as the top 1 percent does , and about half again what the top 10 percent pays. Our false protests about paying all the taxes, however, sound like songs of innocence compared with our mastery of the art of having the taxes returned to us. The income-tax system that so offended my grandfather has had the unintended effect of creating a highly discreet category of government expenditures. They’re called “tax breaks,” but it’s better to think of them as handouts that spare the government the inconvenience of collecting the money in the first place. In theory, tax expenditures can be used to support any number of worthy social purposes, and a few of them, such as the earned income-tax credit, do actually go to those with a lower income. But more commonly, because their value is usually a function of the amount of money individuals have in the first place, and those individuals’ marginal tax rates, the benefits flow uphill. Let us count our blessings: Every year, the federal government doles out tax expenditures through deductions for retirement savings (worth $137 billion in 2013); employer-sponsored health plans ($250 billion); mortgage-interest payments ($70 billion); and, sweetest of all, income from watching the value of your home, stock portfolio, and private-equity partnerships grow ($161 billion). In total, federal tax expenditures exceeded $900 billion in 2013. That’s more than the cost of Medicare, more than the cost of Medicaid, more than the cost of all other federal safety-net programs put together. And—such is the beauty of the system—51 percent of those handouts went to the top quintile of earners, and 39 percent to the top decile. The best thing about this program of reverse taxation, as far as the 9.9 percent are concerned, is that the bottom 90 percent haven’t got a clue. The working classes get riled up when they see someone at the grocery store flipping out their food stamps to buy a T-bone. They have no idea that a nice family on the other side of town is walking away with $100,000 for flipping their house. But wait, there’s more! Let’s not forget about the kids. If the secrets of a nation’s soul may be read from its tax code, then our nation must be in love with the children of rich people. The 2017 tax law raises the amount of money that married couples can pass along to their heirs tax-free from a very generous $11 million to a magnificent $22 million. Correction: It’s not merely tax-free; it’s tax-subsidized. The unrealized tax liability on the appreciation of the house you bought 40 years ago, or on the stock portfolio that has been gathering moths—all of that disappears when you pass the gains along to the kids. Those foregone taxes cost the United States Treasury $43 billion in 2013 alone—about three times the amount spent on the Children’s Health Insurance Program. Grandfather’s father, the Colonel, died in 1947, when the maximum estate-tax rate was a now-unheard-of 77 percent. When the remainder was divvied up among four siblings, Grandfather had barely enough to pay for the Bentley and keep up with dues at the necessary clubs. The government made sure that I would grow up in the middle class. And for that I will always be grateful. 6. The Gilded Zip Code From my Brookline home, it’s a pleasant, 10-minute walk to get a haircut. Along the way, you pass immense elm trees and brochure-ready homes beaming in their reclaimed Victorian glory. Apart from a landscaper or two, you are unlikely to spot a human being in this wilderness of oversize closets, wood-paneled living rooms, and Sub-Zero refrigerators. If you do run into a neighbor, you might have a conversation like this: “Our kitchen remodel went way over budget. We had to fight just to get the tile guy to show up!” “I know! We ate Thai takeout for a month because the gas guy’s car kept breaking down!” You arrive at the Supercuts fresh from your stroll, but the nice lady who cuts your hair is looking stressed. You’ll discover that she commutes an hour through jammed highways to work. The gas guy does, too, and the tile guy comes in from another state. None of them can afford to live around here. The rent is too damn high. From 1980 to 2016, home values in Boston multiplied 7.6 times. When you take account of inflation, they generated a return of 157 percent to their owners. San Francisco returned 162 percent in real terms over the same period; New York, 115 percent; and Los Angeles, 114 percent. If you happen to live in a neighborhood like mine, you are surrounded by people who consider themselves to be real-estate geniuses. (That’s one reason we can afford to make so many mistakes in the home-renovation department.) If you live in St. Louis (3 percent) or Detroit (minus 16 percent), on the other hand, you weren’t so smart. In 1980, a house in St. Louis would trade for a decent studio apartment in Manhattan. Today that house will buy an 80-square-foot bathroom in the Big Apple. Related Story Your Friends Who Own Homes Got Money From Their Parents The returns on (the right kind of) real estate have been so extraordinary that, according to some economists, real estate alone may account for essentially all of the increase in wealth concentration over the past half century. It’s not surprising that the values are up in the major cities: These are the gold mines of our new economy. Yet there is a paradox. The rent is so high that people—notably people in the middle class—are leaving town rather than working the mines. From 2000 to 2009, the San Francisco Bay Area had some of the highest salaries in the nation, and yet it lost 350,000 residents to lower-paying regions. Across the United States, the journalist and economist Ryan Avent writes in The Gated City , “the best opportunities are found in one place, and for some reason most Americans are opting to live in another.” According to estimates from the economists Enrico Moretti and Chang-Tai Hsieh, the migration away from the productive centers of New York, San Francisco, and San Jose alone lopped 9.7 percent off total U.S. growth from 1964 to 2009. It is well known by now that the immediate cause of the insanity is the unimaginable pettiness of backyard politics. Local zoning regulation imposes excessive restrictions on housing development and drives up prices. What is less well understood is how central the process of depopulating the economic core of the nation is to the intertwined stories of rising inequality and falling social mobility. Real-estate inflation has brought with it a commensurate increase in economic segregation. Every hill and dale in the land now has an imaginary gate, and it tells you up front exactly how much money you need to stay there overnight. Educational segregation has accelerated even more. In my suburb of Boston, 53 percent of adults have a graduate degree. In the suburb just south, that figure is 9 percent. This economic and educational sorting of neighborhoods is often represented as a matter of personal preference, as in red people like to hang with red, and blue with blue. In reality, it’s about the consolidation of wealth in all its forms, starting, of course, with money. Gilded zip codes are located next to giant cash machines: a too-big-to-fail bank, a friendly tech monopoly, and so on. Local governments, which collected a record $523 billion in property taxes in 2016, make sure that much of the money stays close to home. But proximity to economic power isn’t just a means of hoarding the pennies; it’s a force of natural selection. Gilded zip codes deliver higher life expectancy, more-useful social networks, and lower crime rates. Lengthy commutes, by contrast, cause obesity, neck pain, stress, insomnia, loneliness, and divorce, as Annie Lowrey reported in Slate. One study found that a commute of 45 minutes or longer by one spouse increased the chance of divorce by 40 percent. Nowhere are the mechanics of the growing geographic divide more evident than in the system of primary and secondary education. Public schools were born amid hopes of opportunity for all; the best of them have now been effectively reprivatized to better serve the upper classes. According to a widely used school-ranking service, out of more than 5,000 public elementary schools in California, the top 11 are located in Palo Alto. They’re free and open to the public. All you have to do is move into a town where the median home value is $3,211,100. Scarsdale, New York, looks like a steal in comparison: The public high schools in that area funnel dozens of graduates to Ivy League colleges every year, and yet the median home value is a mere $1,403,600. Racial segregation has declined with the rise of economic segregation. We in the 9.9 percent are proud of that. What better proof that we care only about merit? But we don’t really want too much proof. Beyond a certain threshold—5 percent minority or 20 percent, it varies according to the mood of the region—neighborhoods suddenly go completely black or brown. It is disturbing, but perhaps not surprising, to find that social mobility is lower in regions with high levels of racial segregation. The fascinating revelation in the data, however, is that the damage isn’t limited to the obvious victims. According to Raj Chetty’s research team , “There is evidence that higher racial segregation is associated with lower social mobility for white people.” The relationship doesn’t hold in every zone of the country, to be sure, and is undoubtedly the statistical reflection of a more complex set of social mechanisms. But it points to a truth that America’s 19th-century slaveholders understood very well: Dividing by color remains an effective way to keep all colors of the 90 percent in their place. With localized wealth comes localized political power, and not just of the kind that shows up in voting booths. Which brings us back to the depopulation paradox. Given the social and cultural capital that flows through wealthy neighborhoods, is it any wonder that we can defend our turf in the zoning wars? We have lots of ways to make that sound public-spirited. It’s all about saving the local environment, preserving the historic character of the neighborhood, and avoiding overcrowding. In reality, it’s about hoarding power and opportunity inside the walls of our own castles. This is what aristocracies do. Zip code is who we are. It defines our style, announces our values, establishes our status, preserves our wealth, and allows us to pass it along to our children. It’s also slowly strangling our economy and killing our democracy. It is the brick-and-mortar version of the Gatsby Curve. The traditional story of economic growth in America has been one of arriving, building, inviting friends, and building some more. The story we’re writing looks more like one of slamming doors shut behind us and slowly suffocating under a mass of commercial-grade kitchen appliances. 7. Our Blind Spot In my family, Aunt Sarah was the true believer. According to her version of reality, the family name was handed down straight from the ancient kings of Scotland. Great-great-something-grandfather William Stewart, a soldier in the Continental Army, was seated at the right hand of George Washington. And Sarah herself was somehow descended from “Pocahontas’s sister.” The stories never made much sense. But that didn’t stop Sarah from believing in them. My family had to be special for a reason. The 9.9 percent are different. We don’t delude ourselves about the ancient sources of our privilege. That’s because, unlike Aunt Sarah and her imaginary princesses, we’ve convinced ourselves that we don’t have any privilege at all. Consider the reception that at least some members of our tribe have offered to those who have foolishly dared to draw attention to our advantages. Last year, when the Brookings Institution researcher Richard V. Reeves, following up on his book Dream Hoarders , told the readers of The New York Times to “Stop Pretending You’re Not Rich,” many of those readers accused him of engaging in “class warfare,” of writing “a meaningless article,” and of being “rife with guilt.” In her incisive portrait of my people, Uneasy Street , the sociologist Rachel Sherman documents the syndrome. A number among us, when reminded of our privilege, respond with a counternarrative that generally goes like this: I was born in the street. I earned everything all by myself. I barely get by on my $250,000 salary. You should see the other parents at our kids’ private school. In part what we have here is a listening problem. Americans have trouble telling the difference between a social critique and a personal insult. Thus, a writer points to a broad social problem with complex origins, and the reader responds with, “What, you want to punish me for my success?” In part, too, we’re seeing some garden-variety self-centeredness, enabled by the usual cognitive lapses. Human beings are very good at keeping track of their own struggles; they are less likely to know that individuals on the other side of town are working two minimum-wage jobs to stay afloat, not watching Simpsons reruns all day. Human beings have a simple explanation for their victories: I did it. They easily forget the people who handed them the crayon and set them up for success. Human beings of the 9.9 percent variety also routinely conflate the stress of status competition with the stress of survival. No, failing to get your kid into Stanford is not a life-altering calamity. The recency of it all may likewise play a role in our failure to recognize our growing privileges. It has taken less than one lifetime for the (never fully formed) meritocracy to evolve into a (fledgling) aristocracy. Class accretes faster than we think. It’s our awareness that lags, trapping us within the assumptions into which we were born. And yet, even allowing for these all-too-human failures of cognition, the cries of anguish that echo across the soccer fields at the mere suggestion of unearned privilege are too persistent to ignore. Fact-challenged though they may be, they speak to a certain, deeper truth about life in the 9.9 percent. What they are really telling us is that being an aristocrat is not quite what it is cracked up to be. A strange truth about the Gatsby Curve is that even as it locks in our privileges, it doesn’t seem to make things all that much easier. I know it wasn’t all that easy growing up in the Colonel’s household, for example. The story that Grandfather repeated more than any other was the one where, following some teenage misdemeanor of his, his father, the 250-pound, 6-foot-something onetime Rough Rider, smacked him so hard that he sailed clear across the room and landed flat on the floor. Everything—anything—seemed to make the Colonel angry. Jay Gatsby might have understood. Life in West Egg is never as serene as it seems. The Princeton man—that idle prince of leisure who coasts from prep school to a life of ease—is an invention of our lowborn ancestors. It’s what they thought they saw when they were looking up. West Eggers understand very well that a bad move or an unlucky break (or three or four) can lead to a steep descent. We know just how expensive it is to live there, yet living off the island is unthinkable. We have intuited one of the fundamental paradoxes of life on the Gatsby Curve: The greater the inequality, the less your money buys. We feel in our bones that class works only for itself; that every individual is dispensable; that some of us will be discarded and replaced with fresh blood. This insecurity of privilege only grows as the chasm beneath the privileged class expands. It is the restless engine that drives us to invest still more time and energy in the walls that will keep us safe by keeping others out. Here’s another fact of life in West Egg: Someone is always above you. In Gatsby’s case, it was the old-money people of East Egg. In the Colonel’s case, it was John D. Rockefeller Jr. You’re always trying to please them, and they’re always ready to pull the plug. The source of the trouble, considered more deeply, is that we have traded rights for privileges. We’re willing to strip everyone, including ourselves, of the universal right to a good education, adequate health care, adequate representation in the workplace, genuinely equal opportunities, because we think we can win the game. But who, really, in the end, is going to win this slippery game of escalating privileges? Under the circumstances, delusions are understandable. But that doesn’t make them salutary, as Aunt Sarah discovered too late. Even as the last few pennies of the Colonel’s buck trickled down to my father’s generation, she still had the big visions that corresponded to her version of the family mythology. Convinced that she had inherited a head for business, she bet her penny on the dot-com bubble. In her final working years, she donned a red-and-black uniform and served burgers at a Wendy’s in the vicinity of Jacksonville, Florida. 8. The Politics of Resentment The political theology of the meritocracy has no room for resentment. We are taught to run the competition of life with our eyes on the clock and not on one another, as if we were each alone. If someone scores a powerboat on the Long Island waterways, so much the better for her. The losers will just smile and try harder next time. In the real world, we humans are always looking from side to side. We are intensely conscious of what other people are thinking and doing, and conscious to the point of preoccupation with what they think about us. Our status is visible only through its reflection in the eyes of others. Perhaps the best evidence for the power of an aristocracy is to be found in the degree of resentment it provokes. By that measure, the 9.9 percent are doing pretty well indeed. The surest sign of an increase in resentment is a rise in political division and instability. We’re positively acing that test. You can read all about it in the headlines of the past two years. The 2016 presidential election marked a decisive moment in the history of resentment in the United States. In the person of Donald Trump, resentment entered the White House. It rode in on the back of an alliance between a tiny subset of super-wealthy 0.1 percenters (not all of them necessarily American) and a large number of 90 percenters who stand for pretty much everything the 9.9 percent are not. According to exit polls by CNN and Pew, Trump won white voters by about 20 percent. But these weren’t just any old whites (though they were old, too). The first thing to know about the substantial majority of them is that they weren’t the winners in the new economy. To be sure, for the most part they weren’t poor either. But they did have reason to feel judged by the market—and found wanting. The counties that supported Hillary Clinton represented an astonishing 64 percent of the GDP, while Trump counties accounted for a mere 36 percent. Aaron Terrazas, a senior economist at Zillow, found that the median home value in Clinton counties was $250,000, while the median in Trump counties was $154,000. When you adjust for inflation, Clinton counties enjoyed real-estate price appreciation of 27 percent from January 2000 to October 2016; Trump counties got only a 6 percent bump. The residents of Trump country were also the losers in the war on human health. According to Shannon Monnat, an associate professor of sociology at Syracuse, the Rust Belt counties that put the anti-government-health-care candidate over the top were those that lost the most people in recent years to deaths of despair —those due to alcohol, drugs, and suicide. 
To make all of America as great as Trump country, you would have to torch about a quarter of total GDP, wipe a similar proportion of the nation’s housing stock into the sea, and lose a few years in life expectancy. There’s a reason why one of Trump’s favorite words is unfair. That’s the only word resentment wants to hear. Even so, the distinguishing feature of Trump’s (white) voters wasn’t their income but their education, or lack thereof. Pew’s latest analysis indicates that Trump lost college-educated white voters by a humiliating 17 percent margin. But he got revenge with non-college-educated whites, whom he captured by a stomping 36 percent margin. According to an analysis by Nate Silver, the 50 most educated counties in the nation surged to Clinton : In 2012, Obama had won them by a mere 17 percentage points; Clinton took them by 26 points. The 50 least educated counties moved in the opposite direction; whereas Obama had lost them by 19 points, Clinton lost them by 31. Majority-minority counties split the same way: The more educated moved toward Clinton, and the less educated toward Trump. The historian Richard Hofstadter drew attention to Anti-intellectualism in American Life in 1963; Susan Jacoby warned in 2008 about The Age of American Unreason ; and Tom Nichols announced The Death of Expertise in 2017. In Trump, the age of unreason has at last found its hero. The “self-made man” is always the idol of those who aren’t quite making it. He is the sacred embodiment of the American dream, the guy who answers to nobody, the poor man’s idea of a rich man. It’s the educated phonies this group can’t stand. With his utter lack of policy knowledge and belligerent commitment to maintaining his ignorance, Trump is the perfect representative for a population whose idea of good governance is just to scramble the eggheads. When reason becomes the enemy of the common man, the common man becomes the enemy of reason. Did I mention that the common man is white? That brings us to the other side of American-style resentment. You kick down, and then you close ranks around an imaginary tribe. The problem, you say, is the moochers, the snakes, the handout queens; the solution is the flag and the religion of your (white) ancestors. According to a survey by the political scientist Brian Schaffner, Trump crushed it among voters who “strongly disagree” that “white people have advantages because of the color of their skin,” as well as among those who “strongly agree” that “women seek to gain power over men.” It’s worth adding that these responses measure not racism or sexism directly, but rather resentment. They’re good for picking out the kind of people who will vehemently insist that they are the least racist or sexist person you have ever met, even as they vote for a flagrant racist and an accused sexual predator. No one is born resentful. As mass phenomena, racism, xenophobia, anti-intellectualism, narcissism, irrationalism, and all other variants of resentment are as expensive to produce as they are deadly to democratic politics. Only long hours of television programming, intelligently manipulated social-media feeds, and expensively sustained information bubbles can actualize the unhappy dispositions of humanity to the point where they may be fruitfully manipulated for political gain. Racism in particular is not just a legacy of the past, as many Americans would like to believe; it also must be constantly reinvented for the present. Mass incarceration, fearmongering, and segregation are not just the results of prejudice, but also the means of reproducing it. The raging polarization of American political life is not the consequence of bad manners or a lack of mutual understanding. It is just the loud aftermath of escalating inequality. It could not have happened without the 0.1 percent (or, rather, an aggressive subset of its members). Wealth always preserves itself by dividing the opposition. The Gatsby Curve does not merely cause barriers to be built on the ground; it mandates the construction of walls that run through other people’s minds. But that is not to let the 9.9 percent off the hook. We may not be the ones funding the race-baiting, but we are the ones hoarding the opportunities of daily life. We are the staff that runs the machine that funnels resources from the 90 percent to the 0.1 percent. We’ve been happy to take our cut of the spoils. We’ve looked on with smug disdain as our labors have brought forth a population prone to resentment and ripe for manipulation. We should be prepared to embrace the consequences. The first important thing to know about these consequences is the most obvious: Resentment is a solution to nothing. It isn’t a program of reform. It isn’t “populism.” It is an affliction of democracy, not an instance of it. The politics of resentment is a means of increasing inequality, not reducing it. Every policy change that has waded out of the Trump administration’s baffling morass of incompetence makes this clear. The new tax law; the executive actions on the environment and telecommunications, and on financial-services regulation; the judicial appointments of conservative ideologues—all will have the effect of keeping the 90 percent toiling in the foothills of merit for many years to come. The second thing to know is that we are next in line for the chopping block. As the population of the resentful expands, the circle of joy near the top gets smaller. The people riding popular rage to glory eventually realize that we are less useful to them as servants of the economic machine than we are as model enemies of the people. The anti-blue-state provisions of the recent tax law have miffed some members of the 9.9 percent, but they’re just a taste of the bad things that happen to people like us as the politics of resentment unfolds. The past year provides ample confirmation of the third and most important consequence of the process: instability. Unreasonable people also tend to be ungovernable. I won’t belabor the point. Just try doing a frequency search on the phrase constitutional crisis over the past five years. That’s the thing about the Gatsby Curve. You think it’s locking all of your gains in place. But the crystallization process actually has the effect of making the whole system more brittle. If you look again at history, you can get a sense of how the process usually ends. 9. How Aristocracies Fall For months, Colonel Robert W. Stewart dodged the subpoenas. He was in Mexico or South America, undertaking business negotiations so sensitive that revealing his precise location would jeopardize the national interest, or so said his lawyer. Senator Thomas J. Walsh of Montana at last dragged the lawyer to the stand and presented him with clippings from the gossip columns of the Havana newspapers, complete with incriminating photographs. The Colonel, always known to appreciate a good horse, was apparently quite the fixture at the Jockey Club. His smile had also flashed for the cameras at an impressive round of luncheons and dinners, and an evening ball at the Havana Yacht Club. When the senators finally roped the Colonel in for questioning about those shell-company bonds that had spread like bedbugs through the political ecosystem, he let them know just who was in charge. “I do not think that the line of interrogation by this committee is within the jurisdiction of the committee under the laws of the United States,” he declared. Even so, he added, as if proffering a favor, he did not “personally receive any of these bonds.” Which was not, on any ordinary construction of the English language, true. The twilight of the fabled Stewart dynasty was not glorious. A fancy lawyer got the Colonel “aquibbled” from charges of contempt, as one journalist sneered, but Rockefeller Jr. wasn’t ready to forgive him the public-relations fiasco. After an epic but futile battle for the hearts of shareholders, the Colonel hung up his spurs and retreated for life to the family compound in Nantucket. None of which changed the reality that the Teapot Dome scandal, with its bribes and kickbacks and sweetheart deals for rich oilmen, made plain. Under the immense pressure of the Gatsby Curve, American democracy was on the ropes. The people in charge were the people with the money. Ultimately, what the moneymen of the 1920s wanted is what moneymen always want. And their servants delivered. The Calvin Coolidge administration passed a huge tax cut in 1926, making sure that everyone could go home with his winnings. The rich seemed to think they had nothing else to worry about—until October 1929. Where were the 90 percent during these acts of plunder? An appreciable number of them could be found at Ku Klux Klan rallies. And as far as the most vocal (though not necessarily the largest) part of the 90 percent was concerned, America’s biggest problems were all due to the mooching hordes of immigrants. You know, the immigrants whose grandchildren have come to believe that America’s biggest problems now are all due to the mooching hordes of immigrants. The toxic wave of wealth concentration that arose in the Gilded Age and crested in the 1920s finally crashed on the shoals of depression and war. Today we like to think that the social-welfare programs that were planted by the New Deal and that blossomed in the postwar era were the principal drivers of a new equality. But the truth is that those efforts belong more to the category of effects than causes. Death and destruction were the real agents of change. The financial collapse knocked the wealthy back several steps, and war empowered labor—above all working women. That gilded, roaring surge of destruction was by no means the first such destabilizing wave of inequality to sweep through American history. In the first half of the 19th century, the largest single industry in the United States, measured in terms of both market capital and employment, was the enslavement (and the breeding for enslavement) of human beings. Over the course of the period, the industry became concentrated to the point where fewer than 4,000 families (roughly 0.1 percent of the households in the nation) owned about a quarter of this “human capital,” and another 390,000 (call it the 9.9 percent, give or take a few points) owned all of the rest. The slaveholding elite were vastly more educated, healthier, and had much better table manners than the overwhelming majority of their fellow white people, never mind the people they enslaved. They dominated not only the government of the nation, but also its media, culture, and religion. Their votaries in the pulpits and the news networks were so successful in demonstrating the sanctity and beneficence of the slave system that millions of impoverished white people with no enslaved people to call their own conceived of it as an honor to lay down their life in the system’s defense. That wave ended with 620,000 military deaths, and a lot of property damage. It did level the playing field in the American South for a time—though the process began to reverse itself all too swiftly. The United States, to be clear, is hardly the most egregious offender in the annals of human inequality. The European nations from which the colonists of North America emigrated had known a degree of inequality and instability that Americans would take more than a century to replicate. Whether in ancient Rome or the Near East, Asia or South America, the plot remains the same. In The Great Leveler , the historian Walter Scheidel makes a disturbingly good case that inequality has reliably ended only in catastrophic violence: wars, revolutions, the collapse of states, or plagues and other disasters. It’s a depressing theory. Now that a third wave of American inequality appears to be cresting, how much do we want to bet that it’s not true? The belief in our own novelty is one of the defining characteristics of our class. It mostly means that we don’t know our predecessors very well. I had long assumed that the Colonel was descended from a long line of colonels, each passing down his immense sense of entitlement to the next. Aunt Sarah’s propaganda was more effective than I knew. Robert W. Stewart was born in 1866 on a small farm in Iowa and raised on the early mornings and long hours of what Paul Henry Giddens, a historian of Standard Oil of Indiana, politely describes as “very modest circumstances.” The neighbors, seeing that the rough-cut teenager had something special, pitched in to send him to tiny Coe College, in the meatpacking town of Cedar Rapids. It would be hard not to believe that the urgent need to win at everything was already driving the train when the scholarship boy arrived at Yale Law School a few years later. The flashbulbs at the Havana Yacht Club captured a pose that was perhaps first glimpsed in a scratchy mirror somewhere in the silent plains of the Midwest. 10. The Choice I like to think that the ending of The Great Gatsby is too down-beat. Even if we are doomed to row our boats ceaselessly back into the past, how do we know which part of the past that will be? History shows us a number of aristocracies that have made good choices. The 9.9 percenters of ancient Athens held off the dead tide of the Gatsby Curve for a time, even if democracy wasn’t quite the right word for their system of government. America’s first generation of revolutionaries was mostly 9.9 percenters, and yet they turned their backs on the man at the very top in order to create a government of, by, and for the people. The best revolutions do not start at the bottom; they are the work of the upper-middle class. These exceptions are rare, to be sure, and yet they are the story of the modern world. In total population, average life expectancy, material wealth, artistic expression, rates of violence, and almost every other measure that matters for the quality of human life, the modern world is a dramatically different place than anything that came before. Historians offer many complicated explanations for this happy turn in human events—the steam engine, microbes, the weather—but a simple answer precedes them all: equality. The history of the modern world is the unfolding of the idea at the vital center of the American Revolution. The defining challenge of our time is to renew the promise of American democracy by reversing the calcifying effects of accelerating inequality. As long as inequality rules, reason will be absent from our politics; without reason, none of our other issues can be solved. It’s a world-historical problem. But the solutions that have been put forward so far are, for the most part, shoebox in size. Well-meaning meritocrats have proposed new and better tests for admitting people into their jewel-encrusted classrooms. Fine—but we aren’t going to beat back the Gatsby Curve by tweaking the formulas for excluding people from fancy universities. Policy wonks have taken aim at the more-egregious tax-code handouts, such as the mortgage-interest deduction and college-savings plans. Good—and then what? Conservatives continue to recycle the characterological solutions, like celebrating traditional marriage or bringing back that old-time religion. Sure—reforging familial and community bonds is a worthy goal. But talking up those virtues won’t save any families from the withering pressures of a rigged economy. Meanwhile, coffee-shop radicals say they want a revolution. They don’t seem to appreciate that the only simple solutions are the incredibly violent and destructive ones. The American idea has always been a guide star, not a policy program, much less a reality. The rights of human beings never have been and never could be permanently established in a handful of phrases or old declarations. They are always rushing to catch up to the world that we inhabit. In our world, now, we need to understand that access to the means of sustaining good health, the opportunity to learn from the wisdom accumulated in our culture, and the expectation that one may do so in a decent home and neighborhood are not privileges to be reserved for the few who have learned to game the system. They are rights that follow from the same source as those that an earlier generation called life, liberty, and the pursuit of happiness. Recommended Reading The Masthead Discusses a “New American Aristocracy” Karen Yuan and Caroline Kitchener The Secret Shame of Middle-Class Americans Neal Gabler Images of a New American Aristocracy Caroline Kitchener Yes, the kind of change that really matters is going to require action from the federal government. That which creates monopoly power can also destroy it; that which allows money into politics can also take it out; that which has transferred power from labor to capital can transfer it back. Change also needs to happen at the state and local levels. How else are we going to open up our neighborhoods and restore the public character of education? It’s going to take something from each of us, too, and perhaps especially from those who happen to be the momentary winners of this cycle in the game. We need to peel our eyes away from the mirror of our own success and think about what we can do in our everyday lives for the people who aren’t our neighbors. We should be fighting for opportunities for other people’s children as if the future of our own children depended on it. It probably does. This article appears in the June 2018 print edition with the headline “The Birth of a New American Aristocracy.” "

"A Muslim Among Israeli Settlers - The Atlantic"

"https://www.theatlantic.com/magazine/archive/2018/06/a-muslim-among-the-settlers/559145"

"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 A Muslim among Israeli settlers, the pearl at the center of an 80-year-old hoax, Marti Noxon putting women’s rage on TV, and pop culture’s response to Trump. Plus, Kissinger on AI and the end of humanity, an interview with Seth Meyers, the search for life on Mars, NRATV, and more. The 9.9 Percent Is the New American Aristocracy Matthew Stewart Is Television Ready for Angry Women? Sophie Gilbert A Muslim Among Israeli Settlers Wajahat Ali Chasing the Pearl of Lao Tzu Michael LaPointe Can Protest Art Get Its Mojo Back? Spencer Kornhaber How the Enlightenment Ends Henry A. Kissinger A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. A Palestinian worker in Shiloh tends to the grounds of what some Jews believe was the first capital of the Israelite kingdom. A Muslim Among Israeli Settlers What happens when a Pakistani American writer goes deep into the West Bank? Image above: A Palestinian worker in Shiloh tends to the grounds of what some Jews believe was the first capital of the Israelite kingdom. I was here to report on Jewish settlers, the 600,000 citizens of Israel living beyond its pre-1967 borders. My main concern was whether the normally guarded and cautious settler community would open up and talk to me: a brown-skinned, practicing Muslim from the United States. I. The Old City Should I lie to an Israeli soldier in order to be allowed to pray? This was a theological dilemma I never studied in Sunday school, one I never thought I would have to confront. Anxious and on edge, the soldier was standing in front of me, rifle in hand, blocking my way, and all I had to do was tell him I was 50 years old, and then I could pray at one of Islam’s holiest sites. One minor problem: I’m 37. Typically, when violence happens in the Old City of Jerusalem, Israeli authorities ban men younger than 50 from entering Haram al-Sharif, the compound known to Jews and Christians as the Temple Mount. And there had just been a small—by Middle Eastern standards anyway—spasm of violence. Three Palestinians had shot and killed two Israeli police officers near al-Aqsa Mosque inside Haram al-Sharif, which led to Israeli retaliations, which led to mass Palestinian protests, which led to yet another predictable round of stories datelined Jerusalem about the legendary Middle Eastern “cycle of violence.” When I had arrived at Ben Gurion Airport, outside Tel Aviv, a few days earlier, I had not anticipated this conundrum. This was not my first time in Israel. I’m a Pakistani-American Muslim, and I’ve been to Israel more times than half the Jews I know. At the airport, I had been greeted by the giant, flawless face of the model Bar Refaeli, stretched across a billboard to sell me designer sunglasses. Tel Aviv is modern, its politics are progressive (at least by the dysfunctional standards of the Middle East), and much of the food there isn’t kosher. An hour later I was in Jerusalem, which might as well be on a different planet. About Jerusalem: It is maybe the most contested real estate on Earth, sacred to each of the Abrahamic religions. For Muslims, Jerusalem is al-Quds, “the holy one,” and, many hope, the site of a future Palestinian capital; it’s currently occupied territory. For Jews, it’s their biblical home, finally liberated and reunified in 1967, a dream fulfilled after 2,000 years. For Christians, it’s the home of the Church of the Holy Sepulchre, which is believed to be the site of Jesus’s crucifixion and entombment. Ever since the creation of the modern state of Israel—a miracle for the Jews, the Nakba (“catastrophe”) for the Palestinians—Jerusalem’s daily weather forecast could be described as sunny with a slight chance of apocalypse. The city frequently erupts; lives are lost on both sides. Israelis fear their Palestinian neighbors, and Palestinians are suffocated and immiserated by the Israeli occupation. It’s a real-estate dispute, yes, but seeded with a profound religious complexity that casts a shadow across the Middle East, and all the way to America, where many Jewish and Muslim communities circle each other with apprehension and mistrust. “You. Fifty?” the young Israeli soldier asked me. He inspected my U.S. passport, hunting for my birth date. Muslim men who are 49 pose an existential threat to Israel; at 50, evidently, we turn into neutered kittens. Which means that all that stood between me and my chance to perform Friday prayers at al-Aqsa Mosque was a simple lie—as well as a squad of nervous soldiers carrying automatic rifles. I figured Allah would give me a celestial get-out-of-jail-free card for a white lie, but I haven’t aged horribly and can’t pass for 50. “Fifty? Fifty?” the soldier asked again, as I was pushed in the back by the bottleneck of Muslims trying to squeeze into a narrow gap. Next to me, Abdullah Antepli, my guide and traveling companion, pleaded with another soldier. He proffered his passport, mixing his Turkish-accented English with bits of Arabic and Hebrew. Abdullah, who is usually jovial, reddened as his frustration grew. The irony was thick. Abdullah, an imam and the director of Muslim affairs at Duke University, as well as a teacher in the divinity school there, was in Jerusalem to head a delegation from the Muslim Leadership Initiative, which he created with the Shalom Hartman Institute. The initiative brings American Muslims to the proudly Zionist Hartman Institute, headquartered in Jerusalem, for an intensive course about Judaism—and about how Jews understand the meaning of Zionism. “He’s 50. Him. Not me,” I lied to the officer while pointing to Abdullah, who on a good day looks every one of his 44 years; that day, fortuitously, was not a good day. “Okay, you come,” the young officer said to Abdullah, allowing the exasperated imam inside the compound. “You stay,” he said to me officiously. With my small lie, Abdullah, ostensibly a security threat, walked in at the nearest entry point—a darkly comic episode in a surreal landscape, where everyone is perpetually nervous and obsessed with security. I grew up eating Hebrew National kosher hot dogs in my Fremont, California, home. Back then, halal meat was alien to the local supermarket, so Jewish dietary restrictions came to the rescue of an overweight Pakistani American kid. Straightforward anti-Semitism was not taught in my Muslim household or in weekend Koran classes. My father never dusted off The Protocols of the Elders of Zion from the living-room bookshelf. Instead, I carpooled to an all-male Jesuit high school with my Jewish neighbor Brian, with whom I never debated the implications of the wars of 1948 or 1967, but with whom I did regularly have heated exchanges about the merits of Star Trek: The Next Generation versus Star Trek: Deep Space Nine. Growing up, I was taught that Christians and Jews were considered “People of the Book,” part of the same Abrahamic tradition as Muslims. But the specter of Israel, the suffering of Palestinians, and the occupation of Jerusalem in particular loomed large in conversations at home and in the religious teachings I received. When visiting Pakistan, I heard relatives and friends lament how “the Jews” oppressed “the Muslims.” In America, the Muslims I knew discussed their envy of Jewish power and influence: If only we Muslims were as organized and strategic as the Jews, we could replicate their success. Among my community, respect for the Jews’ mythical status as the magical minority was its own subtle form of anti-Semitism. Sometimes my dad would read aloud the credits at the end of a movie and say, “Spielberg … Jewish. Cohn … Jewish. Adelstein? Definitely Yehudi ! See, Wajahat, if Jews can dominate Hollywood, there’s no reason you can’t!” As an undergraduate at UC Berkeley, I was a member of the Muslim Student Association. I recall listening to more passionate khutbahs —Friday sermons—about the injustices in Palestine than stories about the Prophet Muhammad and his companions. The conflict in the Holy Land superseded all other Muslim suffering, including the ongoing occupation of Kashmir, the repression of Chechen Muslims, and the daily racism experienced by many African-American Muslims. I became a bit actor in a never-ending cosmic drama. I would parrot a script written by others, and serve as a proxy soldier for a tragedy happening across the Atlantic. The Jewish kids from the campus Hillel were my foil. We showed up to “debates,” predictable affairs where each side cheered and booed when appropriate but rarely engaged in a constructive dialogue. We marched, chanted, rallied. We wore zionism is racism T-shirts. We thought we were differentiating Judaism from Zionism, the political ideology espoused by Theodor Herzl at the turn of the 20th century, which argued for the creation of a Jewish state in the Jews’ ancestral homeland of Israel. But too few of us Muslims bothered to ask how the many American Jews who consider themselves in some way Zionist felt upon hearing that Zionism was racism. Video: The ‘Most Contentious Place on Earth’ I ’ve moved quite a distance from my student-activist days. I first met Abdullah Antepli, the imam, in 2011. Abdullah is always in search of Jewish conversation partners who are willing to discuss something more than a shared affection for hummus. He found an unlikely one in Yossi Klein Halevi, an Israeli journalist, a Shalom Hartman Institute fellow, and a self-described former Jewish extremist. Born in Brooklyn to Holocaust survivors, Halevi grew up hearing warnings from his traumatized father about how the Jews will always be hated and persecuted. Unsurprisingly, Halevi became radicalized as a young man. He once told me, solemnly, that he could describe 24 ways that Israel could be destroyed by its neighbors. (I stopped him after the second scenario.) Abdullah cooked up the Muslim Leadership Initiative with Halevi in 2013. The Shalom Hartman Institute itself was created by David Hartman, a rabbi who left Montreal for Israel in 1971. He wanted to produce thinkers who would elevate the quality of Jewish life by debating and teaching how Judaism and Israel are functioning in the modern world. The institute is now run by his son Rabbi Donniel Hartman. On my first Hartman Institute trip with Abdullah, in 2013, I had been asked to lead a panel about Islamophobia in America. At the end of the panel, one of the Jewish Israeli attendees had told me, “I didn’t know Muslims could be funny.” Another had confessed, “When I heard they were bringing Muslim leaders here, I assumed you’d all be like [then–Iranian President Mahmoud] Ahmadinejad.” The bar had been low. For my second trip, the bar was a lot higher. The Muslim Leadership Initiative didn’t turn me into a Zionist “interfaith Trojan horse”—as I’ve been described by a few Muslim and Arab American activists. Quite the opposite—my experience in Israel underscored for me the urgency of working out how Palestinians could emerge from under the often-brutal Israeli occupation. I also remain committed to keeping this conflict from continually leaching into America, poisoning the relations between the religions and inspiring the worst, drunk angels of Jewish and Muslim communities to rise and fight in a Pyrrhic battle. But what my first trip with the initiative did for me was this: It turned the Jews into complicated humans. It exposed me to their narratives. On my first trip, I was overwhelmed by the reality that this mess seemed unfixable. But I was also overwhelmed by what I discovered was a gap in my knowledge. I was surrounded, at the Hartman Institute and on my forays into places such as Tel Aviv, by liberal Israelis who supported a two-state solution. Some of them didn’t know very much about Islam, but in the sheltering confines of the institute, there was not only respect for my Muslim faith, but also an acknowledgment that another people have a reasonable claim to the land that Israeli Jews call their own. The people at Hartman—and the people in the cafés of Tel Aviv—could, theoretically, be part of a solution. But I knew this was only one side of Israel—empathetic, nuanced. For my most recent trip, I wanted to go where the deepest fault lines—and what I believe is the biggest impediment to peace—lie: the settlements in the West Bank, the home of the several hundred thousand Jews who have moved to the heart of what is, legally, Palestine. I’ve always been interested in fanatics. I admire (and fear) their zealous conviction, unclouded by doubt, anchored by an arrogant righteousness, unwilling to tolerate dissent. Every community, including mine, has them—people who believe in only one truth, and that those who don’t completely embrace or support that truth are to be excommunicated or fought as villains. The Palestinians and the Jews are heavily burdened with these kinds of people. Historically, Hamas has not sought peaceful coexistence with Jews. I always assumed that Hamas and the settlers needed each other to justify their respective existences: lovers dancing a waltz, pouring gasoline as the world burned around them. I wanted to talk with settlers myself; I wanted to understand how they thought and to ask them a couple of questions: Would they ever leave the West Bank in exchange for peace with the Palestinians? And, maybe even more important: What’s given them their strident conviction? (I figured I’d ask hard-line Palestinians the same question.) This was a fraught project. I didn’t have the impression that the settlers would have much patience for a brown-skinned Muslim critical of the occupation. I asked my friends at the Hartman Institute where I should go first. They suggested that I ease in gently. And so my first stop was Efrat, the Scarsdale of the settlements. II. Efrat Haim Cohen, my Israeli driver, took me up into the hills south of Jerusalem, past security checkpoints, toward the settlement of Efrat, in the West Bank, near Bethlehem. Established in 1983, Efrat is an affluent community of 10,000 residents, built on the high ground of seven hills in the Judaean Mountains. It’s one of the gentrified jewels of Gush Etzion, a collection of more than a dozen settlements housing more than 80,000 people. Efrat is one of those settlements that many believe would become part of Israel in a land swap with Palestine. Not that such a deal is on the horizon. Stunning vineyards, beautiful maple and pine trees, and flourishing gardens filled the landscape. The roads were spotless; the roundabouts had striking green grass, perfectly cut; and all around us we saw idyllic, sand-colored homes made of Jerusalem stone and red tiles. In the administrative building, I waited for a meeting with Oded Revivi, the popular mayor of Efrat, currently serving his second term. A bulletin board advertised houses for sale. I did the conversion in my head: Each unit was selling for $1 million. Efrat is about 85 percent Orthodox Jewish and 15 percent secular. Mayor Revivi told me that settler communities attract three types of people. First, members of the Haredim , ultra-devout Jews who need a religious community and physical space to accommodate their growing families. Second, secular Jews who want a big, clean suburban home and an easy commute to Tel Aviv. And third, the minority, those who move here for purely ideological reasons, because “Judaea and Samaria”—the West Bank—“is full of biblical historical sites,” Revivi told me. “As religious Jews, we believe this is the promised land and we are entitled to live here.” Revivi asked me to sit in on his meeting with about a dozen students, most of them American. He told our group that the international reputation of the settlements is that they are fenced cities, surrounded by Arab villages. Do you see any fences? he asked us. No, we answered. “They don’t provide security,” he added. “I personally believe not in fences but in building bridges.” Revivi is fond not just of clichés but of analogies. What do cowboys do when they see Indians? he asked. “Circle the wagons,” someone replied. Revivi nodded, and said that the principal misconception about the settlements is their lack of security; he assured us that if we visited late on Friday night, we’d see “thousands of kids walking in the streets freely” to return home, where their parents are fast asleep, confident that their kids are safe. I asked Revivi to respond to criticism from fellow Jews who see the settler movement as entrenching the occupation and subverting the democratic ideals of Zionism. He disagreed with my use of the word occupation , which I reminded him was consistent with international law. He answered with an extreme analogy: “Your line of accusation is almost like the accusation that a woman comes and reports that she’s raped, and people say, ‘Oh, you’ve been raped because the way you look, the way you dress, or because the way you’ve acted.’ ” If the settlers were the rape victims in this analogy, then who were the Palestinians? I walked outside and was greeted by a firm handshake and an American accent. Bob Lang, the 59-year-old head of Efrat’s religious council, offered to give me a quick tour of the settlement. The son of German immigrants to the United States, Lang moved to Israel for religious and ideological reasons, because according to him, this is “where Jewish history happened.” These are the valleys, he said, where his forefathers—Abraham, Isaac, and Jacob—walked. I wondered whether Abraham, a shepherd, would have been able to get a mortgage in Efrat. Lang told me it “annoys him” when people say the settlers illegally occupy the land. Depending on your perspective, he said, the land was taken, captured, or liberated by Israel during the Six-Day War, in 1967. Which term do you prefer?, I asked. “ Liberated ,” he replied. And what would he do with the land liberated by Israel? His answer surprised me. Lang favors a one-state solution that would absorb all the Jews and Palestinians in the West Bank: “I should have the right to live in their community, and they should have the right to live here.” I let that statement linger as I gazed at the hills populated exclusively by Jewish settlers. III. Alon Shvut Meeting settlers for the first time in these bourgeois utopias, I felt like I was the token minority at an upscale New York City party; I could feel myself being scrutinized with equal measures of fascination and curiosity, and not a small quotient of horror. The settlers were friendly, a bit guarded and standoffish at first, but mostly curious why a guy who looked like a Long Island Uber driver had come to Israel to talk with them. I learned quickly that everyone in Israel loves offering solicited—and unsolicited—opinions about politics and religion. The last thing I expected to hear upon arriving at Alon Shvut, a short drive from Efrat and part of the same bloc of settlements, was the adhan , the Islamic call to prayer. My guide, Hanan Schlesinger, a 60-year-old rabbi, told me that it came from a neighboring Palestinian village. His community of 800 families totaling almost 3,200 people, 95 percent of whom are Orthodox Jews, has no mosques. “Sometimes, I think my Jewish neighbors don’t hear” the adhan , he said. “It’s the way their mind is structured.” Schlesinger’s mind had once been structured the same way. To him, the Palestinians had been “background noise—the gray, drab scenery that passes in the distance in a movie.” About four years ago, Schlesinger attended an interfaith meeting where he met Yasin, a 17-year-old Palestinian who was wearing a seeds of peace T-shirt he had received at a camp in Maine. Schlesinger was baffled that a Palestinian could promote peace; the concept was an oxymoron to him. Schlesinger then met Jamaal, the boy’s father, and learned that the family was from the Palestinian town Beit Ummar. Jamaal told him that when the Palestinian children in his town saw a Jewish settler like Schlesinger, they ran and cried. “Why?,” Schlesinger asked. “They all carry submachine guns, and they kill our kids,” Jamaal replied. A lot of his friends did carry Uzis or pistols, Schlesinger conceded. He considered this exchange to be a “blessing,” because it was the first time in his life that he had experienced how “the other” experienced him—as an occupier. The revelation was like a “dagger to my heart,” Schlesinger told me. He’d never thought of what the settlers were doing as an occupation: “Living around here, I see the return of the Jewish people to our land after 2,000 years of exile. I see triumph. I see righteousness … And suddenly, I hear that our triumph is another nation’s tragedy, and our righteousness is another nation’s suffering. I didn’t know where to put that.” IV. Neve Erez In Neve Erez, an outpost established in 1999 on a dusty West Bank hilltop, I thought briefly that I’d stumbled upon a Zionist Coachella. For miles I was surrounded by mostly empty land and sunbaked hills. The man I was to interview, a settler named Noam Cohen, appeared, walking past his front porch, which sported two dirty sofas and a table that was currently being used by his dog for shade. With his long hair tied in a ponytail, graying temples, and white T-shirt and green pants fitted on a lean frame, Cohen looked like Iggy Pop. I felt that I’d seen Cohen countless times before on Telegraph Avenue, in Berkeley, shrouded in a fog of weed. “I’m the luckiest person on Earth,” Cohen told me as we stood on his back porch overlooking his utopia. Cohen’s kids, barefoot, were running around. Cohen said that his community is considered an illegal outpost, but that the Israeli government helps it out: “They give us money to build everything—all the lights around, all the roads in here.” The government also provides water, picks up the garbage, and sends a school bus for his kids. “We got everything, but not officially,” he added. Cohen loves nature and sincerely believes that one day all of humanity will be one. (“There won’t be religions anymore,” and “there won’t be differences anymore,” he said, sounding like an unproduced John Lennon song.) But for that to happen, he also believes that “we have to pass the process.” I asked him whether that process includes expelling and forcibly transferring Palestinians to Jordan. “I think it’s going to be part of it. We have to transport people,” he said without hesitation. Before departing, I asked Cohen to take me to his music studio, where I pointed to random instruments and asked him to play. He performed an impromptu 10-minute concert, effortlessly cycling through traditional Israeli instruments, drums, and even a didgeridoo. He was damn good and thoroughly enjoyed himself. Here was a man who had realized his dream on the top of a hill in the middle of a desert. “Do you feel God here?,” I asked. “I feel safe,” he replied. V. The Old City, Part II “I actually don’t mind the word conquered ,” Daniel Luria told me in his Australian accent, referring to Israel’s acquisition of Palestinian land after the 1967 war. We were walking outside the Old City walls on a cool Jerusalem night. A few hundred Israelis, flanked by soldiers and police vehicles, were gathering for an annual march organized by the Women in Green, a group dedicated to the preservation of what it believes to be the Jews’ God-given biblical homeland. Luria was raised in a religious Zionist home in Australia. He tried at age 11 to emigrate by himself, intending to get from Melbourne to Israel. (He was stopped a few miles from home, carrying underwear, an atlas, and a Bible.) Years later, at age 30, he finally found his way to Jerusalem, and he now lives in Ma’ale Adumim, one of the West Bank’s largest settlements, with his wife and five kids. Many Israelis believe that Ma’ale Adumim, which sits east of Jerusalem, would have to be part of Israel in any peace deal. Palestinians see what that would do to the West Bank—effectively cut it in half. Explore the June 2018 Issue Check out more from this issue and find your next story to read. “Joshua conquered the land,” Luria said, pounding his chest with both fists as he invoked the man who led the Israelite tribes after the death of Moses. “He came back. Today, conquered has become a negative word. But we’ve come back home. We are the natural heirs of this country—and we are here to stay.” His eyes flashing with defiance, he added, “The truth is there’s nothing the world can do about it.” The word occupied makes Luria’s “blood boil”: “You can’t be an illegal occupier of your own land.” I pointed out that much of the international community, led by the United Nations, disagrees. “Doesn’t matter what the world says,” he countered. For Luria, there is no Green Line—the armistice border established after the war of 1948. “There’s one line,” he told me, and it runs from the Mediterranean Sea to the Jordan River. “Sea, river. Sea, river. Palestine equals Jewish national homeland.” That homeland belongs only to the Jewish people, because “it’s never been a homeland to anyone else, not a single nation, not a single person, definitely not the so-called Palestinians.” As it happened, Luria and I were talking on Tisha B’Av, the ninth day of the Jewish month of Av, which is, as Yossi Klein Halevi, the Israeli journalist and Hartman Institute fellow, once put it, “the black hole of the Jewish calendar.” On this day in history, over the centuries, Jewish tradition holds that the first temple was destroyed by the Babylonians; the second temple was destroyed by the Romans; the Jews were expelled from Spain; and World War I began, leading to the disintegration of Europe and paving the way, ultimately, for the rise of Nazi Germany. Tisha B’Av is a day of mourning, but for many Jews today, their return to the land from which the Romans exiled them makes the mourning substantially less bitter. “I’m not in exile, anymore … I’ve got my country,” Luria said. Isn’t that enough?, I asked him. No, he said. For Luria and his fellow marchers that day, redemption will not be complete until they achieve the missing piece that will make the fragmented dream whole: the Temple Mount. Luria is a spokesman for Ateret Cohanim, a group founded in 1978 and dedicated to, as he puts it, “the revival of Jewish life.” The organization helps settle Jews in the Muslim Quarter of the Old City and in neighborhoods of East Jerusalem. Some 3,000 Jews now live, protected by armed Israelis, in the densely populated Muslim Palestinian areas of the Old City and Silwan. Luria sees almost no difference between his work and what the Zionist pioneers did 150 years ago, “when they came back from Europe and moved to Israel to build up the country.” But B’Tselem, an Israeli nonprofit that documents human-rights violations in the occupied territories, alleges that Ateret Cohanim aggressively acquires land, displacing Palestinians. A 2016 survey by B’Tselem found that eviction claims filed by Ateret Cohanim were pending against 81 Palestinian families who had lived in the Batan al-Hawa region of Silwan for decades. Whereas Palestinians and human-rights organizations see occupation by Jewish settlers as chaotic disruption, Luria sees peace: “When Jews move into an area, it becomes a safe area. If you have one Jew there, he’s attacked; if you have 30 Jews there, suddenly it’s a quiet neighborhood.” Luria, like other extremists I was coming to know (on both sides of the divide, I should point out), favors a one-state solution in which Palestinians would be allowed to vote as citizens of Israel—but their citizenship would be revocable if they incited terrorism. “What if a Palestinian was born here?,” I asked. “Big deal!,” Luria said. “There’s never been a Palestinian state or a Palestinian people.” He asked me whether I’d heard of the book, once sold on Amazon but since removed, called A History of the Palestinian People: From Ancient Times to the Modern Era —which consisted entirely of 132 blank pages. Luria doesn’t consider Jews who want to liberate the Temple Mount to be on the same level as Muslim terrorists, “depraved animals” who stab people. I told Luria that he sounded like a fundamentalist. “I believe in the fundamentals of Judaism,” he replied. “Nothing wrong with that,” as long as it doesn’t lead to violence like the stabbings and beheadings committed by some Muslims. “Have you ever had moments of doubt—where you felt, ‘Maybe I’m not doing it right, maybe I’m not fulfilling God’s—’?” “Never, not once,” he said, cutting me off. “In your entire life?” “Never.” Y ossi Klein Halevi says he fears Jews like Daniel Luria. He believes that they have a “spiritual madness,” and that their longing for the Temple Mount reveals a “fundamental lack of responsibility.” At sunset, Halevi invited Abdullah and me to accompany him to the Western Wall, where he would be offering prayers. Halevi brought kippot for us. I joked that it would be just my luck if a pro-Palestinian media outlet filmed me at the exact moment Halevi placed a kippah on my head. But Abdullah and I agreed to accompany Halevi through the Jewish Quarter, and to wear the kippot out of respect once we reached the wall. As we walked, I told Halevi about some of my recent interviews with settlers. He agrees that they have a claim to the land—but thinks “the price of implementing that claim is too high.” He believes that the quest of Luria and the Temple Mount Faithful is a profoundly “anti-Zionist act” that risks “putting Israel and the Jewish people in danger.” Luria and his ilk, Halevi believes, are “playing with spiritual fire” that could cause the immolation of the Jews all around the world. “You don’t think the Temple Mount is worth it?,” I asked. “Absolutely not,” he said without hesitation. He proposed a solution, laughing: “The Jews and the Muslims should give it to the Baha’i.” Descending to the wall, we put on our kippot along with hundreds of Jewish men, some praying out loud, others seated in small prayer circles, a few swaying back and forth, not quite lamenting or weeping, but all gathered with a dedicated solemnity. I’ve visited the wall three times, and each time I’ve approached it with respect and reverence, as a visitor who would expect the same from his Jewish brothers and sisters at a Muslim holy site. I see how the wall, with prayers embedded in the narrow spaces between its bricks, inspires an expansion of hearts, bringing joy and love to the faces of believers. The same wall ironically constricts: Men and women must be separated when they pray. Jewish women have returned to the Western Wall after thousands of years, only to be denied equal rights. VI. Al-Amari Refugee Camp The quickest way to tell you’re in a Palestinian neighborhood is to look for clusters of big, unsightly black barrels crowding the skyline. These eyesores store water, which is almost entirely controlled, even in the Palestinian territories, by the state of Israel. Our guide, Ashraf Ehab (I’ve changed his name at his request), told me that some Palestinian residents get water about two days a week. The limitations force Palestinians to get creative with conservation. “You sometimes take five or six shits before flushing,” he said. This is just one of the challenges for Palestinians who live on the West Bank side of the wall separating most of Jerusalem from the settlements. On the Israeli side, we drove past neat lawns and clean streets, and we breathed fresh air. Then we crossed through the Qalandiya checkpoint into the West Bank, which has almost no police presence and scant municipal services. Cans and plastic bottles littered the roads. Trash was caked onto the rocks and dirt. Crushed cars were stacked like pancakes. Palestinians line up at the checkpoint, hoping to enter Jerusalem for jobs or medical services, or to reach their property. Some have a blue ID card, which indicates residency in, but not citizenship of, Israel, and which allows them to enter Jerusalem. They come on foot or by car, sometimes waiting 15 minutes, sometimes hours, subject to the whims of young Israeli soldiers manning the checkpoint. Ever since the 1967 war, Palestinians possessing only a green ID card—indicating West Bank residency—cannot get into Jerusalem without a special permit. Ehab told me that many Palestinian residents of the West Bank have never entered Jerusalem, despite living just feet away. The 280-mile-long wall doesn’t make it easy. Known as “the separation barrier,” the wall, which is more than 25 feet tall in sections, stretches from Jenin in the north to Hebron in the south, dividing Israelis from Palestinians. It has also separated thousands of Palestinians who once lived in the same city. This creates absurdities: The Palestinian neighborhood of Kafr Aqab is part of East Jerusalem—but since the building of the wall, it is now physically separated from the city, so many of its residents have to travel daily through the Qalandiya checkpoint, blue ID in hand, just to reach work, attend school, or meet other family members in Jerusalem. Israel justifies the wall as a necessary security measure, citing the dozens of suicide attacks that took place inside Israel from late 2000 to early 2004 during the second intifada, in which more than 900 Israelis, soldiers and civilians, died. Ehab told me the wall is a “thriving business for the Palestinian mafia.” He took me to a section where people were using a makeshift ladder to cross over illegally into Jerusalem for work and criminal activities. “What security?” he asked. Ehab wanted to stop near Ramallah, at the al-Amari refugee camp, which was established in 1949 and serves as a home to more than 6,000 Palestinian refugees, many of whom are still holding on to the hope for a “right of return.” They want to go back to villages that no longer exist. Al-Amari is one of 19 refugee camps in the West Bank. Several generations of Palestinians have been born and raised in these camps. The scene reminded me of cities in Pakistan: graffiti, trash, barefoot children playing on dirt roads. An electricity line crisscrossed between several buildings barely separated by narrow alleys. Posters of young men holding guns hung on the walls. Some of the older men bragged that their camp had produced 100 shuhada (“martyrs”), and 40 resistance fighters who are serving a life sentence in Israeli prisons. They complained that the Israel Defense Forces come in whenever they want and have often placed men in “administrative detention” for up to six months. The unemployment rate in the West Bank is 18 percent. The people there loathe Israel. They hate the Palestinian Authority even more. We encountered a family on the way to a social event. The mother, 60-year-old Umm al-Abad, was dressed in a floral white hijab and a dark-blue dress. She has been in the camp for more than 45 years, and she said she wants to reclaim all the land from the river to the sea, stating, “The Jews should go back to where they come from.” Her daughter, Samaha, 37, who was born in the camp and is the mother of two boys and two girls, added: “May God take all the Israelis to hell.” Samaha’s next-door neighbor Rowayda, a 60-year-old grandmother who was born in Jordan, told me her family had been kicked out of Lydda, a Palestinian city, in 1948. She eventually moved to the camp in 1982. She said that “everything is hard” in the camp. “I have about 50 people living in this house. Look at it—me and my children and my children’s children.” She kept pointing to the kids and telling me they have no place to play. Although Rowayda realizes it’s unlikely that she will return to her original land, she still holds out hope. She said her grandfather had owned farms in Lydda and cultivated crops there, but “they”—the Jews—“took our homes, took our land.” She said she’ll “never be able to forgive the settlers,” even if they gave all the land back, because of all the suffering she’s experienced in her life. She said she wants to “eat them all alive.” You hear this anger again and again from many Palestinians in the West Bank. In the global conversation about the occupation, people assume that Palestinians, when or if they are freed to have a country of their own in the West Bank, will be satisfied with their lot. But many Palestinians I encountered think of the people in Tel Aviv as settlers as well. In al-Bireh, a Palestinian city north of Jerusalem, I met a woman named Umm Khusay, who had turned the front lawn of her house into a museum of the occupation, featuring a palm tree decorated with tear-gas canisters. As we walked up the steps to the front door, I could see a giant hole in one of the windows, recently broken by what seemed to be a stone. Khusay, a 48-year-old Muslim who was born in Michigan—she is an American citizen—but raised in al-Bireh, met us at the top of the stairs wearing a beige jilbab covering her from head to toe. All of her children are American citizens now. “I die here rather than have happy life in the United States,” she said when I asked her why she didn’t join her family in the U.S. “I love my land. I have many problems, but I can’t leave.” Khusay said she feels anger when she sees the settlers of Psagot, just up the road from al-Bireh. “This is Palestinian land. Why did they take this land? Why?” She paused and looked at me: “Would you like someone to take your home?” I asked whether she also blamed the Palestinian youth for instigating some of the conflicts outside her home by throwing stones and burning tires. “The Israeli soldiers are afraid of stones?” she asked. “The soldiers have a weapon, and they’re afraid of the boys that hold stones? This is fair? And they kill them? This is not fair.” She, like Umm al-Abad, wants all the Israelis “to go back where they came from.” Khusay added: “There’s no solution with them until they go back home.” Her mission in life, she said, was to defend al-Aqsa from the Jews. To her, al-Aqsa is more than just a mosque or a building, it is aqeedah , the creed itself. “Not just for Palestinians, for all Muslims. All the Muslims have to protect al-Aqsa,” she stressed. “What’s one thing you want to tell the settlers?,” I asked. “Go back home. They took our land.” “How do you want the settlers to see you?” “Why am I enemy?” she asked. “I don’t have nothing—guns, weapons, nothing.” VII. Hebron Throughout my trip, everyone told me to brace myself for what I’d see in Hebron. “You’ll need to detox with a lot of strong sheesha ,” Abdullah warned. About 800 Jewish settlers live in this enclave, protected by 650 or so Israeli soldiers and surrounded by 200,000 Palestinians, who are penned in by dozens of roadblocks and checkpoints around the city. The dreams of those 800 or so Jewish settlers shape and distort the lives of all the Palestinians living there. Hebron had a Jewish community until 1929, when the Jews were killed in a riot. In 1968, settlers came back for good. We met one of these settlers, Noam Arnon, near the entrance to a playground. He shuffled toward us in his sandals, resembling a kindly Jewish American grandfather. In 1972, at 18, Arnon decided to visit the settlement of Kiryat Arba. He kept returning, eventually becoming involved in excavations and helping restore the old synagogue. Today he is not only a spokesman of the Jewish community of Hebron but also a historian and an expert on the Tomb of the Patriarchs. Yishai Fleisher, a radio host and frequent commentator for international media, was to lead our tour. Born in Israel, he earned a legal degree at Cardozo School of Law, in the U.S. Fleisher leaped out of his car with a boyish energy, extending his hand and welcoming us with a giant grin. He was carrying a big, visible handgun. “There are only two kinds of minorities in the Middle East,” Fleisher told me. “Armed and unarmed.” Arnon gave us a quick tour around the community before we headed over to the Tomb of the Patriarchs. He took us first into the playground and pointed at a mural depicting flames emerging from a baby carriage. It was to honor a 10-month-old baby who had been killed in 2001 by a sniper bullet that had come from “over there,” he said, motioning toward a nearby hill. I asked him whether it was worth staying in Hebron, especially with children, considering the danger. Yes, he said. “Children play here, and every one of them is a victory over terror.” Arnon said he believes that the Jewish condition in Hebron “is an apartheid”: “The Jews are in a ghetto. The Jews are limited to 3 percent of the town.” A ghetto? This was the first time I’d heard anyone accuse the Palestinians of imposing an apartheid regime on their neighbors. The Jews of Hebron “don’t have rights to build or to develop,” he said, adding that anyone who considers the occupation to be illegal is wrong. “Jewistically, they are wrong,” he continued, coining a new word in his ardor. “Historically, they are wrong … Geographically, ecologically, everything wrong.” He said he believes that his community, unlike the Palestinian leadership, “takes care for human rights of Arabs, for health of Arabs, for supplying water for Arabs.” Arnon told me that a two-state solution would end up pushing Arabs to form a “terrorist, jihadistic, Islamic regime.” He is for one state, the entire land of Israel, including the occupied territories, and for “one loyal person, one vote.” He even said he would be fine with a Palestinian prime minister—provided that he or she is “loyal to the vision of the state of Israel.” The condescension was a bit much for me to take. Fleisher talked about an “equitable solution” to the conflict, but the one described would have Jewish settlers seizing disputed property, and the Palestinians deprived of legal remedies. Doesn’t that sound a lot like colonialism?, I asked. “What is it to do with colonialism?,” Fleisher said, offended. “We’re taking our property. It’s our land. We purchased it. We’re trying to move into here. How is that possibly colonialism?” On our way to the Tomb of the Patriarchs, I asked Fleisher whether Arab citizens of Israel could be equal to Jews. “No, not in my opinion,” he said. He added that the word occupier is a “fantastic, audacious, bold move to delegitimize Jewish presence” in Hebron, which he credited to the forces of “narrative jihad.” At the steps leading up to the Jewish entrance of the tomb, I twice annoyed Fleisher by referring to the Temple Mount as the al-Aqsa compound. “It’s not just disrespectful; it’s supposed to be historical, right?” he said. “It was for 1,400 years, before Islam came around, the Temple Mount.” We passed by green walls and arches, saw several worshippers and tourists, most of them Orthodox, and eventually reached the cenotaph. Looking through the green bars of the gate, you could see the section for Muslim visitors, about 10 feet across on the opposite side. In between us was Abraham, the forefather uniting Islam and Judaism, allegedly buried here, in the Cave of Machpelah, thousands of years ago by his sons Isaac and Ishmael. In the 21st century, he was lying between both children, dividing them. L ater that day, on the Palestinian side of Hebron, I met a man named Jihad Rashid. “The land is more important than our families. More important than blood. Jerusalem, Palestine, al-Aqsa Mosque is more important than all of the above. It is part of our religion,” he said. I felt I had found the perfect interfaith partner for Fleisher and Arnon. The three men are saying the same thing, but speak from different texts. Would Rashid ever leave Hebron and the occupation? “Even if they gave me all of America and the White House, I would not leave,” he replied. He had lost two children in the fight against Israel. Had it been worth it? “It’s worth it.” We left Rashid’s shop and entered a souk, venturing deeper into the old city of Hebron. Shop after shop was closed, the green metal doors shut. Above us was wire mesh in between long, lime-green metal bars that crisscrossed and formed a semiopen dome. I felt like we were birds in a cage. Ashraf Ehab told me that this “shield” had been installed years ago to protect Palestinians from the trash that Israeli settlers would throw down from the houses above. We walked toward a two-story building that was surrounded on three sides by the Jewish community of Hebron. At the top of a yellow metal staircase, by the front door, we met an overweight Palestinian kid in dark-blue sweats and a multicolored T-shirt who looked like I had when I was 10. He was leaning against a railing, looking down at a pristine basketball court used exclusively by Jewish settlers, constructed between his building and a Jewish neighbor’s house. At this Palestinian home, effectively nestled inside the Jewish settlement, we were greeted by Nasreen, a 28-year-old mother of five, whose serious face revealed the spartan toughness needed to survive here. She had moved in 14 years ago, right after she’d married Shadi, now 34, whose family had lived in Hebron for generations. She shared the two-story home with Shadi’s first wife, who stood behind Nasreen, welcoming us with a big smile. Seventeen people live in the house. The three shops we’d passed by before reaching their house, all welded shut, had belonged to Shadi. Nasreen said all three had been forcibly closed by Israeli soldiers. Now the family members were essentially prisoners in this house; they had to make sure that at least one adult was in the building at all times to prevent a takeover. Despite the challenges, Nasreen affirmed, “we will all remain steadfast for Palestine.” What about her kids and their future? “I will die in this house,” she said. “Me, my children, my husband—all of us.” “Your grandchildren?,” I asked. She nodded. “We can’t leave. How can we? As soon as we leave, the settlers will come and take this house.” The settlers, she said, pointing at a window that looked down directly to the basketball court, throw wine bottles into her home. She said that if the settlers ever see any member of her family looking at them while they play, they start cursing. Once, settlers tried to flood the home when her family was sleeping. Another time, she alleged, “my daughter was sleeping here in the middle of the night, and they threw a bottle of alcohol that cut her face, and she had to go to the ICU.” After that, her family put bars on the windows. What would happen if settlers offered you money? Could you leave?, I asked. They already had offered. “$4 million,” Shadi said from the background. “U.S. dollars?,” I asked. “U.S. dollars.” “How about if they offered $1 billion?,” I asked. “No, nothing,” she said, shaking her head. Even if there’s a magical peace process, Nasreen said she believes that it will be very hard for her to live side by side with Israeli settlers, “because they are all devils” and have made her life “very difficult for 14 years.” Nasreen wanted to show us the roof. She said that if soldiers saw us they might yell at us to go down or, worse, bring more soldiers to the home and detain us there for hours. I felt that I could have touched the nearest Jewish settlement building. To our left and our right was the Jewish community. Just take the $4 million , I thought to myself, shaking my head, observing this absurd existence—a life sentence served in an open-air prison in the heart of Hebron. A young Israeli soldier spotted us and started yelling “Leave now! Leave now!” in Hebrew. Nasreen wasn’t fazed. “More will come now, you’ll see,” she predicted, and all of a sudden three more soldiers popped up, like characters in a video game. We left. As we went down the stairs, the young Palestinian boy kept staring at the basketball court. In a normal world, he would be attempting layups with a Jewish khalil , a friend, who lived right across from him. But here, in the old city of Hebron, one boy must play within the walls of his home, while the other boy has a playground right outside, visible behind barred windows, beyond reach, surrounded by Israeli soldiers. VIII. Al-Aqsa, At Last Our final day in Israel coincided with Friday prayers, so Abdullah and I decided to try again to pray at al-Aqsa, hoping for a better outcome than the last one. I waited for the imam past the Jaffa Gate, near the Muslim Quarter. I reflected on the past two weeks and thought of where I had been around the same time the previous Friday: meeting at a Jerusalem train station with the writer and historian Gershom Gorenberg, the author of the influential book The Accidental Empire: Israel and the Birth of the Settlements, 1967–1977. Gorenberg made aliyah from America some 40 years ago and lives in Jerusalem. He had arrived for lunch on his bicycle wearing a black shirt, black pants, and black gloves, his round face surrounded by a thicket of scraggly black-and-white hair. We discussed the creation of the settlements, religious nationalism, and the future of Israel. Gorenberg told me he believes that “the two-state outcome is still the best bad plan we have” for Palestinians to eventually have self-determination and for Jews to maintain self-determination and a democracy. He believes the settlements are the greatest hurdle to achieving this end. “Every additional room that is built in a home in a settlement is a deliberate impediment to having that,” he warned. Ultimately, he said, Israel has to encourage Jews living in settlements to “move to the Jewish state.” I told him I didn’t think that was going to happen. Gorenberg then said something that I wrote down in my notebook and starred: “I’ve lived here for 40 years and nothing important that has happened was expected.” At Haram al-Sharif, Abdullah and I entered unperturbed by soldiers, and I thought of Gorenberg’s hopeful words. It was a perfect Jerusalem day, sunny but not humid, with a subtle wind. No one could have guessed that just recently this place had been the site of violent clashes. Abdullah and I walked toward the wudu station to make ablutions. The golden Dome of the Rock was on our left. Kids kicked soccer balls, giggling, as their mothers and aunts sat in the shade. Elderly men relaxed in chairs, circling their prayer beads, talking. Teenagers took selfies in front of the dome. A young couple, visiting from America, held hands as they walked across the compound. Abdullah and I entered the Dome of the Rock, passed by women who were offering their prayers, and walked down the steps to the small cave cut into the rock from which Muhammad is believed to have ascended to heaven. I offered a prayer, taking my time to appreciate the space. We walked out and sat on the steps in between the Dome of the Rock and al-Aqsa, waiting for the call to prayer. Sitting there, I prayed that the many Palestinians I had met who had never been allowed to visit al-Aqsa could stand next to me in Juma prayer. I prayed that Palestinian kids would be able to run freely around the city without fear, not worrying about upsetting a soldier or neighbor. I prayed that men like Daniel Luria would be able to come up and say a prayer, and maybe find release from their absolutism. I prayed that Jihad Rashid, the father of two martyrs, and other Palestinians who use and abuse religion to validate hate and sanction violence would realize that they didn’t have to give their life or their children’s lives to defend this place. I prayed for all those Israelis and Palestinians suffering from a permanent state of rage, hijacked by this small volcano the size of New Hampshire, which simultaneously inspires love and loathing, madness and inspiration. As a result of engaging with Zionists, I found that once you allow a space for conflicting narratives, even those that might repulse you, the characters take up room in your mind and your heart. You can no longer unsee or unfeel them. You have to negotiate their presence without compromising your core principles. Yossi Klein Halevi had somehow conjured two dozen ways that Muslim extremists could destroy his people—but he also kissed my Muslim babies and looked at them lovingly, yearning for grandchildren. Throughout the trip and afterward, I kept asking: Is this land worth all the pain and suffering and bloodshed? I couldn’t ask God, because I’m convinced that he’s now an absentee landowner. He sold Abraham’s children a lemon. I prayed for the settlers. I’m convinced that their zeal to redeem the land has transformed it into a golden calf—an idol, placed on a pedestal where even God, Jewish morality, and democracy can barely reach it. And I’m convinced that the settlements have become the Achilles’ heel of Israel’s security. Each new settlement beyond the Green Line is paving another road to insecurity and fear, and continuing the cycle of violence, in which generation after generation will sleep with one eye open. One of the most startling things about the West Bank is the fixedness of the settlements. These are not tent camps and hipster organic farms; they are massive cities of Jerusalem stone. Even the far-flung ones, the ones that could in no way be merged into a contiguous Israeli state, project a feeling of permanence and domination over the landscape. Recommended Reading Israeli Settlers Weren't Always So Religious—They Were Once Secular Hippies Emma Green Is It Time for the Jews to Leave Europe? Jeffrey Goldberg Dear Therapist: When I Bring Up Anything Serious, My Boyfriend Falls Apart Lori Gottlieb If everyone in the region has a shot at interpreting God’s will, then I’ll offer my own vision. I believe that Jews and Palestinians are religious cousins, more alike than different. They have lived together in the past, eaten each other’s olives, worked each other’s fields, married each other’s family members. Learning to live together again should not be impossible. But this isn’t happening, not anytime soon. So as a realist, I support a two-state solution, one that gives the Jews something of what they want but also treats the Palestinians in a way they haven’t been treated, not by the Israelis or their Arab brethren—with fairness, respect, and an acknowledgment of the right to self-determination. But the political will to reach this solution is missing. The two-state solution has become the inshallah of peace plans. “God willing,” one day maybe, but most people in the West Bank know the two-state solution is just a mirage, a convenient talking point for politicians and diplomats. On my final day in Jerusalem, I recalled a famous saying of the Prophet Muhammad, who was circling the Kaaba, the holiest site in Islam and the figurative house of God on Earth. He looked to it in awe and reverence, ultimately concluding: “But by Him in whose hand is Muhammad’s soul, the sanctity of a believer’s blood and property in the sight of Allah is greater than your sanctity!” Two things stand in the way of actual peace. The first is the yearning of some Palestinians for all the Jews to leave. Israelis are not going to make peace with someone who tells them that their leaving is a condition for such a peace. But the second problem—perhaps the even bigger problem—is the settlements, and the exclusivist attitude that motivates the people who live in them. A two-state solution is, theoretically, the best in a basket of bad solutions. But given the dismal realities on the ground, what might be better, alas, is a one-state solution that absorbs all the Palestinians as citizens of Israel and gives everyone an equal vote and equal rights. Ironically, this might be the only thing that many of the most hard-line settlers, and many of the most unbending Palestinians, agree on. This article appears in the June 2018 print edition with the headline “A Muslim Among the Settlers.” Support for this project was provided by the Henry Luce Foundation. "

"Is Google Making Us Stupid? - The Atlantic"

"https://www.theatlantic.com/magazine/archive/2008/07/is-google-making-us-stupid/306868"

"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 A gift that gets them talking. Give a year of stories to spark conversation, Plus a free tote. More From 160 Years of Atlantic Stories More From 160 Years of Atlantic Stories 160 Years of the American Idea Annika Neklason When Einstein Warned the World Atthar Mirza America's Most Widely Misread Literary Work Jackie Lay The Double-Consciousness of a Dark Body Tynesha Foreman Is Google Making Us Stupid? What the Internet is doing to our brains “Dave, stop. Stop, will you? Stop, Dave. Will you stop, Dave?” So the supercomputer HAL pleads with the implacable astronaut Dave Bowman in a famous and weirdly poignant scene toward the end of Stanley Kubrick’s 2001: A Space Odyssey. Bowman, having nearly been sent to a deep-space death by the malfunctioning machine, is calmly, coldly disconnecting the memory circuits that control its artificial “ brain. “Dave, my mind is going,” HAL says, forlornly. “I can feel it. I can feel it.” I can feel it, too. Over the past few years I’ve had an uncomfortable sense that someone, or something, has been tinkering with my brain, remapping the neural circuitry, reprogramming the memory. My mind isn’t going—so far as I can tell—but it’s changing. I’m not thinking the way I used to think. I can feel it most strongly when I’m reading. Immersing myself in a book or a lengthy article used to be easy. My mind would get caught up in the narrative or the turns of the argument, and I’d spend hours strolling through long stretches of prose. That’s rarely the case anymore. Now my concentration often starts to drift after two or three pages. I get fidgety, lose the thread, begin looking for something else to do. I feel as if I’m always dragging my wayward brain back to the text. The deep reading that used to come naturally has become a struggle. I think I know what’s going on. For more than a decade now, I’ve been spending a lot of time online, searching and surfing and sometimes adding to the great databases of the Internet. The Web has been a godsend to me as a writer. Research that once required days in the stacks or periodical rooms of libraries can now be done in minutes. A few Google searches, some quick clicks on hyperlinks, and I’ve got the telltale fact or pithy quote I was after. Even when I’m not working, I’m as likely as not to be foraging in the Web’s info-thickets—reading and writing e-mails, scanning headlines and blog posts, watching videos and listening to podcasts, or just tripping from link to link to link. (Unlike footnotes, to which they’re sometimes likened, hyperlinks don’t merely point to related works; they propel you toward them.) For me, as for others, the Net is becoming a universal medium, the conduit for most of the information that flows through my eyes and ears and into my mind. The advantages of having immediate access to such an incredibly rich store of information are many, and they’ve been widely described and duly applauded. “The perfect recall of silicon memory,” Wired ’s Clive Thompson has written , “can be an enormous boon to thinking.” But that boon comes at a price. As the media theorist Marshall McLuhan pointed out in the 1960s, media are not just passive channels of information. They supply the stuff of thought, but they also shape the process of thought. And what the Net seems to be doing is chipping away my capacity for concentration and contemplation. My mind now expects to take in information the way the Net distributes it: in a swiftly moving stream of particles. Once I was a scuba diver in the sea of words. Now I zip along the surface like a guy on a Jet Ski. I’m not the only one. When I mention my troubles with reading to friends and acquaintances—literary types, most of them—many say they’re having similar experiences. The more they use the Web, the more they have to fight to stay focused on long pieces of writing. Some of the bloggers I follow have also begun mentioning the phenomenon. Scott Karp, who writes a blog about online media , recently confessed that he has stopped reading books altogether. “I was a lit major in college, and used to be [a] voracious book reader,” he wrote. “What happened?” He speculates on the answer: “What if I do all my reading on the web not so much because the way I read has changed, i.e. I’m just seeking convenience, but because the way I THINK has changed?” Bruce Friedman, who blogs regularly about the use of computers in medicine , also has described how the Internet has altered his mental habits. “I now have almost totally lost the ability to read and absorb a longish article on the web or in print,” he wrote earlier this year. A pathologist who has long been on the faculty of the University of Michigan Medical School, Friedman elaborated on his comment in a telephone conversation with me. His thinking, he said, has taken on a “staccato” quality, reflecting the way he quickly scans short passages of text from many sources online. “I can’t read War and Peace anymore,” he admitted. “I’ve lost the ability to do that. Even a blog post of more than three or four paragraphs is too much to absorb. I skim it.” Anecdotes alone don’t prove much. And we still await the long-term neurological and psychological experiments that will provide a definitive picture of how Internet use affects cognition. But a recently published study of online research habits, conducted by scholars from University College London, suggests that we may well be in the midst of a sea change in the way we read and think. As part of the five-year research program, the scholars examined computer logs documenting the behavior of visitors to two popular research sites, one operated by the British Library and one by a U.K. educational consortium, that provide access to journal articles, e-books, and other sources of written information. They found that people using the sites exhibited “a form of skimming activity,” hopping from one source to another and rarely returning to any source they’d already visited. They typically read no more than one or two pages of an article or book before they would “bounce” out to another site. Sometimes they’d save a long article, but there’s no evidence that they ever went back and actually read it. The authors of the study report: Thanks to the ubiquity of text on the Internet, not to mention the popularity of text-messaging on cell phones, we may well be reading more today than we did in the 1970s or 1980s, when television was our medium of choice. But it’s a different kind of reading, and behind it lies a different kind of thinking—perhaps even a new sense of the self. “We are not only what we read,” says Maryanne Wolf, a developmental psychologist at Tufts University and the author of Proust and the Squid: The Story and Science of the Reading Brain. “We are how we read.” Wolf worries that the style of reading promoted by the Net, a style that puts “efficiency” and “immediacy” above all else, may be weakening our capacity for the kind of deep reading that emerged when an earlier technology, the printing press, made long and complex works of prose commonplace. When we read online, she says, we tend to become “mere decoders of information.” Our ability to interpret text, to make the rich mental connections that form when we read deeply and without distraction, remains largely disengaged. Reading, explains Wolf, is not an instinctive skill for human beings. It’s not etched into our genes the way speech is. We have to teach our minds how to translate the symbolic characters we see into the language we understand. And the media or other technologies we use in learning and practicing the craft of reading play an important part in shaping the neural circuits inside our brains. Experiments demonstrate that readers of ideograms, such as the Chinese, develop a mental circuitry for reading that is very different from the circuitry found in those of us whose written language employs an alphabet. The variations extend across many regions of the brain, including those that govern such essential cognitive functions as memory and the interpretation of visual and auditory stimuli. We can expect as well that the circuits woven by our use of the Net will be different from those woven by our reading of books and other printed works. Sometime in 1882, Friedrich Nietzsche bought a typewriter—a Malling-Hansen Writing Ball, to be precise. His vision was failing, and keeping his eyes focused on a page had become exhausting and painful, often bringing on crushing headaches. He had been forced to curtail his writing, and he feared that he would soon have to give it up. The typewriter rescued him, at least for a time. Once he had mastered touch-typing, he was able to write with his eyes closed, using only the tips of his fingers. Words could once again flow from his mind to the page. But the machine had a subtler effect on his work. One of Nietzsche’s friends, a composer, noticed a change in the style of his writing. His already terse prose had become even tighter, more telegraphic. “Perhaps you will through this instrument even take to a new idiom,” the friend wrote in a letter, noting that, in his own work, his “‘thoughts’ in music and language often depend on the quality of pen and paper.” Recommended Reading Living With a Computer James Fallows How to Trick People Into Saving Money Rob Walker The Dark Psychology of Social Networks Jonathan Haidt and Tobias Rose-Stockwell “You are right,” Nietzsche replied, “our writing equipment takes part in the forming of our thoughts.” Under the sway of the machine, writes the German media scholar Friedrich A. Kittler , Nietzsche’s prose “changed from arguments to aphorisms, from thoughts to puns, from rhetoric to telegram style.” The human brain is almost infinitely malleable. People used to think that our mental meshwork, the dense connections formed among the 100 billion or so neurons inside our skulls, was largely fixed by the time we reached adulthood. But brain researchers have discovered that that’s not the case. James Olds, a professor of neuroscience who directs the Krasnow Institute for Advanced Study at George Mason University, says that even the adult mind “is very plastic.” Nerve cells routinely break old connections and form new ones. “The brain,” according to Olds, “has the ability to reprogram itself on the fly, altering the way it functions.” As we use what the sociologist Daniel Bell has called our “intellectual technologies”—the tools that extend our mental rather than our physical capacities—we inevitably begin to take on the qualities of those technologies. The mechanical clock, which came into common use in the 14th century, provides a compelling example. In Technics and Civilization , the historian and cultural critic Lewis Mumford described how the clock “disassociated time from human events and helped create the belief in an independent world of mathematically measurable sequences.” The “abstract framework of divided time” became “the point of reference for both action and thought.” The clock’s methodical ticking helped bring into being the scientific mind and the scientific man. But it also took something away. As the late MIT computer scientist Joseph Weizenbaum observed in his 1976 book, Computer Power and Human Reason: From Judgment to Calculation , the conception of the world that emerged from the widespread use of timekeeping instruments “remains an impoverished version of the older one, for it rests on a rejection of those direct experiences that formed the basis for, and indeed constituted, the old reality.” In deciding when to eat, to work, to sleep, to rise, we stopped listening to our senses and started obeying the clock. The process of adapting to new intellectual technologies is reflected in the changing metaphors we use to explain ourselves to ourselves. When the mechanical clock arrived, people began thinking of their brains as operating “like clockwork.” Today, in the age of software, we have come to think of them as operating “like computers.” But the changes, neuroscience tells us, go much deeper than metaphor. Thanks to our brain’s plasticity, the adaptation occurs also at a biological level. The Internet promises to have particularly far-reaching effects on cognition. In a paper published in 1936 , the British mathematician Alan Turing proved that a digital computer, which at the time existed only as a theoretical machine, could be programmed to perform the function of any other information-processing device. And that’s what we’re seeing today. The Internet, an immeasurably powerful computing system, is subsuming most of our other intellectual technologies. It’s becoming our map and our clock, our printing press and our typewriter, our calculator and our telephone, and our radio and TV. When the Net absorbs a medium, that medium is re-created in the Net’s image. It injects the medium’s content with hyperlinks, blinking ads, and other digital gewgaws, and it surrounds the content with the content of all the other media it has absorbed. A new e-mail message, for instance, may announce its arrival as we’re glancing over the latest headlines at a newspaper’s site. The result is to scatter our attention and diffuse our concentration. The Net’s influence doesn’t end at the edges of a computer screen, either. As people’s minds become attuned to the crazy quilt of Internet media, traditional media have to adapt to the audience’s new expectations. Television programs add text crawls and pop-up ads, and magazines and newspapers shorten their articles, introduce capsule summaries, and crowd their pages with easy-to-browse info-snippets. When, in March of this year, The New York Times decided to devote the second and third pages of every edition to article abstracts , its design director, Tom Bodkin, explained that the “shortcuts” would give harried readers a quick “taste” of the day’s news, sparing them the “less efficient” method of actually turning the pages and reading the articles. Old media have little choice but to play by the new-media rules. Never has a communications system played so many roles in our lives—or exerted such broad influence over our thoughts—as the Internet does today. Yet, for all that’s been written about the Net, there’s been little consideration of how, exactly, it’s reprogramming us. The Net’s intellectual ethic remains obscure. About the same time that Nietzsche started using his typewriter, an earnest young man named Frederick Winslow Taylor carried a stopwatch into the Midvale Steel plant in Philadelphia and began a historic series of experiments aimed at improving the efficiency of the plant’s machinists. With the approval of Midvale’s owners, he recruited a group of factory hands, set them to work on various metalworking machines, and recorded and timed their every movement as well as the operations of the machines. By breaking down every job into a sequence of small, discrete steps and then testing different ways of performing each one, Taylor created a set of precise instructions—an “algorithm,” we might say today—for how each worker should work. Midvale’s employees grumbled about the strict new regime, claiming that it turned them into little more than automatons, but the factory’s productivity soared. More than a hundred years after the invention of the steam engine, the Industrial Revolution had at last found its philosophy and its philosopher. Taylor’s tight industrial choreography—his “system,” as he liked to call it—was embraced by manufacturers throughout the country and, in time, around the world. Seeking maximum speed, maximum efficiency, and maximum output, factory owners used time-and-motion studies to organize their work and configure the jobs of their workers. The goal, as Taylor defined it in his celebrated 1911 treatise, The Principles of Scientific Management , was to identify and adopt, for every job, the “one best method” of work and thereby to effect “the gradual substitution of science for rule of thumb throughout the mechanic arts.” Once his system was applied to all acts of manual labor, Taylor assured his followers, it would bring about a restructuring not only of industry but of society, creating a utopia of perfect efficiency. “In the past the man has been first,” he declared; “in the future the system must be first.” Taylor’s system is still very much with us; it remains the ethic of industrial manufacturing. And now, thanks to the growing power that computer engineers and software coders wield over our intellectual lives, Taylor’s ethic is beginning to govern the realm of the mind as well. The Internet is a machine designed for the efficient and automated collection, transmission, and manipulation of information, and its legions of programmers are intent on finding the “one best method”—the perfect algorithm—to carry out every mental movement of what we’ve come to describe as “knowledge work.” Google’s headquarters, in Mountain View, California—the Googleplex—is the Internet’s high church, and the religion practiced inside its walls is Taylorism. Google, says its chief executive, Eric Schmidt, is “a company that’s founded around the science of measurement,” and it is striving to “systematize everything” it does. Drawing on the terabytes of behavioral data it collects through its search engine and other sites, it carries out thousands of experiments a day, according to the Harvard Business Review , and it uses the results to refine the algorithms that increasingly control how people find information and extract meaning from it. What Taylor did for the work of the hand, Google is doing for the work of the mind. The company has declared that its mission is “to organize the world’s information and make it universally accessible and useful.” It seeks to develop “the perfect search engine,” which it defines as something that “understands exactly what you mean and gives you back exactly what you want.” In Google’s view, information is a kind of commodity, a utilitarian resource that can be mined and processed with industrial efficiency. The more pieces of information we can “access” and the faster we can extract their gist, the more productive we become as thinkers. Where does it end? Sergey Brin and Larry Page, the gifted young men who founded Google while pursuing doctoral degrees in computer science at Stanford, speak frequently of their desire to turn their search engine into an artificial intelligence, a HAL-like machine that might be connected directly to our brains. “The ultimate search engine is something as smart as people—or smarter,” Page said in a speech a few years back. “For us, working on search is a way to work on artificial intelligence.” In a 2004 interview with Newsweek , Brin said, “Certainly if you had all the world’s information directly attached to your brain, or an artificial brain that was smarter than your brain, you’d be better off.” Last year, Page told a convention of scientists that Google is “really trying to build artificial intelligence and to do it on a large scale.” Such an ambition is a natural one, even an admirable one, for a pair of math whizzes with vast quantities of cash at their disposal and a small army of computer scientists in their employ. A fundamentally scientific enterprise, Google is motivated by a desire to use technology, in Eric Schmidt’s words, “to solve problems that have never been solved before,” and artificial intelligence is the hardest problem out there. Why wouldn’t Brin and Page want to be the ones to crack it? Still, their easy assumption that we’d all “be better off” if our brains were supplemented, or even replaced, by an artificial intelligence is unsettling. It suggests a belief that intelligence is the output of a mechanical process, a series of discrete steps that can be isolated, measured, and optimized. In Google’s world, the world we enter when we go online, there’s little place for the fuzziness of contemplation. Ambiguity is not an opening for insight but a bug to be fixed. The human brain is just an outdated computer that needs a faster processor and a bigger hard drive. The idea that our minds should operate as high-speed data-processing machines is not only built into the workings of the Internet, it is the network’s reigning business model as well. The faster we surf across the Web—the more links we click and pages we view—the more opportunities Google and other companies gain to collect information about us and to feed us advertisements. Most of the proprietors of the commercial Internet have a financial stake in collecting the crumbs of data we leave behind as we flit from link to link—the more crumbs, the better. The last thing these companies want is to encourage leisurely reading or slow, concentrated thought. It’s in their economic interest to drive us to distraction. Maybe I’m just a worrywart. Just as there’s a tendency to glorify technological progress, there’s a countertendency to expect the worst of every new tool or machine. In Plato’s Phaedrus , Socrates bemoaned the development of writing. He feared that, as people came to rely on the written word as a substitute for the knowledge they used to carry inside their heads, they would, in the words of one of the dialogue’s characters, “cease to exercise their memory and become forgetful.” And because they would be able to “receive a quantity of information without proper instruction,” they would “be thought very knowledgeable when they are for the most part quite ignorant.” They would be “filled with the conceit of wisdom instead of real wisdom.” Socrates wasn’t wrong—the new technology did often have the effects he feared—but he was shortsighted. He couldn’t foresee the many ways that writing and reading would serve to spread information, spur fresh ideas, and expand human knowledge (if not wisdom). The arrival of Gutenberg’s printing press, in the 15th century, set off another round of teeth gnashing. The Italian humanist Hieronimo Squarciafico worried that the easy availability of books would lead to intellectual laziness, making men “less studious” and weakening their minds. Others argued that cheaply printed books and broadsheets would undermine religious authority, demean the work of scholars and scribes, and spread sedition and debauchery. As New York University professor Clay Shirky notes, “Most of the arguments made against the printing press were correct, even prescient.” But, again, the doomsayers were unable to imagine the myriad blessings that the printed word would deliver. So, yes, you should be skeptical of my skepticism. Perhaps those who dismiss critics of the Internet as Luddites or nostalgists will be proved correct, and from our hyperactive, data-stoked minds will spring a golden age of intellectual discovery and universal wisdom. Then again, the Net isn’t the alphabet, and although it may replace the printing press, it produces something altogether different. The kind of deep reading that a sequence of printed pages promotes is valuable not just for the knowledge we acquire from the author’s words but for the intellectual vibrations those words set off within our own minds. In the quiet spaces opened up by the sustained, undistracted reading of a book, or by any other act of contemplation, for that matter, we make our own associations, draw our own inferences and analogies, foster our own ideas. Deep reading , as Maryanne Wolf argues, is indistinguishable from deep thinking. If we lose those quiet spaces, or fill them up with “content,” we will sacrifice something important not only in our selves but in our culture. In a recent essay , the playwright Richard Foreman eloquently described what’s at stake: As we are drained of our “inner repertory of dense cultural inheritance,” Foreman concluded, we risk turning into “‘pancake people’—spread wide and thin as we connect with that vast network of information accessed by the mere touch of a button.” I’m haunted by that scene in 2001. What makes it so poignant, and so weird, is the computer’s emotional response to the disassembly of its mind: its despair as one circuit after another goes dark, its childlike pleading with the astronaut—“I can feel it. I can feel it. I’m afraid”—and its final reversion to what can only be called a state of innocence. HAL’s outpouring of feeling contrasts with the emotionlessness that characterizes the human figures in the film, who go about their business with an almost robotic efficiency. Their thoughts and actions feel scripted, as if they’re following the steps of an algorithm. In the world of 2001 , people have become so machinelike that the most human character turns out to be a machine. That’s the essence of Kubrick’s dark prophecy: as we come to rely on computers to mediate our understanding of the world, it is our own intelligence that flattens into artificial intelligence. ​​When you buy a book using a link on this page, we receive a commission. Thank you for supporting The Atlantic. "

"Why the Krack Wi-Fi Mess Will Take Decades to Clean Up | WIRED"

"https://www.wired.com/story/krack-wi-fi-iot-security-broken"

"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 Why the Krack Wi-Fi Mess Will Take Decades to Clean Up Getty Images Save this story Save Save this story Save A vulnerability in Wi-Fi encryption has sent the entire tech industry scrambling; the so-called Krack attack affects nearly every wireless device to some extent, leaving them subject to hijacked internet connections. In terms of scope, it doesn’t get much worse—especially for the Internet of Things. The extent of the Krack fallout remains to be seen. Security analysts say it’s a tricky vulnerability to take advantage of, and major platforms like iOS, macOS, and Windows are either unaffected or have already been patched. But given the millions of routers and other IoT devices that will likely never see a fix, the true cost of Krack could play out for years. “For the general sphere of IoT devices, like security cameras, we’re not just underwater,” says Kevin Fu, a computer scientist at the University of Michigan who focuses on medical device security. “We’re under quicksand under water.” Krack exposes just how deeply those problems run—and how slowly the industry has moved to fix them. Whatever advice you may have heard for dealing with Krack, only one actually has tangible benefit: Patch your devices. (You can find a running list of companies that have provided one here. ) If you have an iPhone, Mac, or Windows computer, you really should patch right now. If you have an Android device, an update’s in the offing, though it may take some time to reach you if you have anything but a Pixel or Nexus. But after that, you're all set! Those are in good shape. 'We're not just underwater. We're under quicksand under water.' Prof. Kevin Fu, University of Michigan But your router? Your security camera? Your internet-connected garage door ? Get comfy. “We’re probably still going to find vulnerable devices 20 years from now,” says HD Moore, a network security researcher at Atredis Partners. That’s because even under the best of circumstances, IoT devices rarely receive the necessary software updates to correct security issues. For a problem as complex as Krack, which impacts the industry at a protocol level and requires a coordinated effort to fix, in many cases your best bet is just to buy new equipment once patched options are on the market. The challenges also go beyond the mere availability of a patch. Take Netgear. To its credit, the company made fixes available for a dozen of its router models the day that Krack went public. But it makes over 1200 products, each of which needs to be tested for specific Krack impact. In many cases, Netgear also can’t make those fixes alone; it needs its chipset partners to tackle the issue as well. 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 when those patches do become available, the company has limited ways to inform customers they need to update as soon as possible. It sends emails to those who register their products, and sends out an advisory, and posts in community forums. The remainder of Netgear customers—the bulk of them—will have to read a news report like this one, and hunt down the right download link to install the fix. And even if they do that , the actual patching process requires logging into Netgear’s access point web-management interface from your computer, which may rightly baffle a number of router owners. “I wouldn’t claim that anyone can just do it,” says Netgear CIO Tejas Shah. “We recognize the need to educate the customer and help the customer when they’re faced with this problem.” Those issues aren’t unique to Netgear, which, again, gets a star for making patches immediately available. But they do underscore just how ill-prepared wireless devices are for this kind of industry-wide calamity. And that’s just routers, which people by and large are at least aware connect to the internet. IoT devices are a whole extra level of opaque. “Users aren’t even going to realize that they have a Wi-Fi IoT device. The refrigerator could be one of those,” says Bob Rudis, chief data scientist at security company Rapid7. “The fridge is probably not going to get patches on its own.” A connected refrigerator may sound like a silly example, but they do exist, as do connected windows and sprinkler systems and pretty much everything else. These often have no easily accessible interface, making applying patches difficult, even if they somehow do exist. And Rudis says that while a hacked appliance won’t cough up your browsing history or contact lists to a hacker, vulnerable IoT devices present a different kind of threat. “It’s not just confidentiality. It’s the integrity. If someone does manage to successfully do this attack and targets your IoT devices, they could take advantage of the vulnerability and open your garage or unlock your door,” Rudis says. And until or unless you upgrade those (needless to say expensive) connected devices, chances are they’ll remain exposed for decades. That feeling that’s sinking in is hopelessness. The problems with IoT security run both so broadly and so deep, and Krack exposes them so fully, that giving up altogether feels about right. It doesn’t have to, though. There has, in recent months and years, been some movement toward fixing IoT security, or at least making it less comically inept. 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 Go back to routers for a minute. If you have an older model, you’re almost certainly out of luck—in fact, if you go back far enough, it may not even support WPA2 in the first place. But a glimmer of hope has appeared in a new generation of mesh-network routers, devices that come with an app for easy interface access, and that, crucially, offer auto-update abilities. That means that when a Krack does happen, the company can both alert users immediately to the issue, and push out a fix without an owner having to raise a finger, much less navigate an access point web management GUI. Take Eero, one of the original mesh network companies. It had automatically pushed out a fix to its beta customers within hours of the Krack news. After thorough testing—to ensure that the cure doesn’t have unexpected side effects—it’ll send its Krack patch out to all of its users at once. “Our system was designed for scenarios like this from the ground up,” says Eero CEO Nick Weaver. “If we need to push an update to 100 percent of our Eeros, we can do that almost instantaneously. That’s one of the core features of our product.” 'If a car manufacturer has a fundamental flaw in a car, it doesn’t matter how long that flaw has been there. Once it’s been identified, they have to do a recall, they have to fix it or replace it.' Bob Rudis, Rapid7 Autoupdates have their own issues. In August, a smart-lock company called Lockstate unintentionally bricked one of its products by pushing a buggy software. Some customers had to send their locks back to the company for a “reset” before they were able to secure their doors again. Not ideal. Hackers have also used autoupdates to push malware on a large scale, as the NotPetya malware that plagued the Ukraine—and several large multinational corporations—did this summer. Still, in the ever-present risk calculation between convenience and security, IoT autoupdates seem like a net good, especially with a thorough beta process in place to squash any bugs before they go wide. “In general, autoupdate is more beneficial than not,” says Moore, "assuming it's done right." Netgear, too, has embraced that model on its higher-end Orbi mesh network system. Shah says the company plans to “enable as many products as possible to autoupdate.” That doesn't help, though, any of Krack-afflicted routers already on the market. Slow improvement has come from other quarters as well. The price of entry into a smart-home ecosystem like Apple’s HomeKit includes meeting certain security requirements; as the IoT industry continues to coalesce around those platforms, they’ll have to demonstrate at least a base competence in keeping their devices safe, and an interest in maintaining that integrity. And failing that, the specter of regulation looms. Senator Mark Warner of Virginia introduced a bill in August that would mandate certain security minimums for smart devices. While it hasn’t seen much traction yet, highly publicized security meltdowns like Krack could pressure other lawmakers to take notice. 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 “Vulnerability in WPA2 highlights the impact of vulnerabilities in widely-adopted components and protocols, and illustrates the importance of adopting basic hygiene requirements for the rapidly proliferating Internet of Things,” Warner said in a statement to WIRED. Those measures could help some, but experts remain skeptical that they go far enough. “I suspect at the end of the day there will be some kind of regulatory, or at least policy-based methods to incentivize baseline cybersecurity hygiene,” says Fu, who has testified before Congress on IoT security issues. “The sad news is, it’s so far below the bar. It’s like handing out Kleenex when you’ve got Ebola.” Rapid7’s Rudis suggests borrowing from another industry’s existing framework. “If a car manufacturer has a fundamental flaw in a car, it doesn’t matter how long that flaw has been there. Once it’s been identified, they have to do a recall, they have to fix it or replace it,” Rudis says. Related Stories standards Lily Hay Newman Lily Hay Newman Lily Hay Newman A similar enough system does, in fact, apply for connected medical devices. Companies need not only to issue recalls but follow through on them, contacting each consumer directly. It seems unlikely, though, to carry over to the broader world of IoT any time soon. There’s likely no panacea for IoT’s security woes. The best hope probably lies in a combination of companies becoming more agile, more able to fix broken things quickly—and for consumers to see that as an important selling point, to create an economic incentive where currently none exists. “We need to create these things so that they can fail gracefully, rather than catastrophically,” says Fu. It doesn’t seem like so much to ask. But a catastrophe like Krack shows just how far IoT has until it gets there. Executive Editor, News X Andy Greenberg Lily Hay Newman Kate O'Flaherty Matt Burgess Reece Rogers Andrew Couts Lily Hay Newman 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 "

"Why Tech’s Best Minds Are Very Worried About the Internet of Things | WIRED"

"https://www.wired.com/2014/05/iot-report"

"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 Klint Finley Business Why Tech’s Best Minds Are Very Worried About the Internet of Things Illustration: Pat Kinsella Save this story Save Save this story Save The Internet of Things is coming. And the tech cognoscenti aren't sure that's a good thing. For years, the prospect of an online world that extends beyond computers, phones, and tablets and into wearables, thermostats, and other devices has generated plenty of excitement and activity. But now, some of the brightest tech minds are expressing some doubts about the potential impact on everything from security and privacy to human dignity and social inequality. That's the conclusion of a new survey from the Pew Research Center. For ten years, the Washington, D.C. think tank has surveyed thousands of technology experts--like founding father Vint Cerf and Microsoft social media scholar danah boyd--about the future of the Internet. But while previous editions have mostly expressed optimism, this year people started expressing more concern. "We had a lot of warnings, a lot of people pushing back," says Janna Anderson, co-author of the report. >'We had a lot of warnings, a lot of people pushing back.' The 1,606 respondents said they saw many potential benefits to the Internet of Things. New voice- and gesture-based interfaces could make computers easier to use. Medical devices and health monitoring services could help prevent and treat diseases. Environmental sensors could detect pollution. Salesforce.com chief scientist JP Rangaswami said that improved logistics and planning systems could reduce waste. But most of the experts warned of downsides as well. Security was one of the most immediate concerns. "Most of the devices exposed on the internet will be vulnerable," wrote Jerry Michalski, founder of the think tank REX. "They will also be prone to unintended consequences: they will do things nobody designed for beforehand, most of which will be undesirable." We've already seen security camera DVRs hacked to mine bitcoins as well as a worm that targets internet connected devices like home routers. As more devices come online, we can expect to see an increase in this kind of attack. Beyond security concerns, there's the threat of building a world that may be too complex for our own good. If you think error messages and applications crashes are a problem now, just wait until the web is embedded in everything from your car to your sneakers. Like the VCR that forever blinks 12:00, many of the technologies built into the devices of the future may never be used properly. "We will live in a world where many things won't work and nobody will know how to fix them," wrote Howard Rheingold. That complexity could also leave many people behind. Developing nations--precisely the ones that could most benefit from IoT's environmental benefits--will be least able to afford them, says Miguel Alcaine, an International Telecommunication Union area representative for Central America. In an interview, Pew's Internet & American Life Project director Lee Raine pointed out that the IoT could lead to a much larger digital divide, one in which those who cannot or choose not to participate are shut out entirely from many daily activities. What happens when you need a particular device to pay for items at your local convenience store? Meanwhile, those that do partake in the IoT may find it dehumanizing, especially in the workplace. We've already seen some companies explore the possibility of monitoring their employees through wearables. "The danger will be in loss of privacy and a reduction of people into numbers: the dark side of the quantified self," wrote Andrew Chen, a computer information systems professor of at Minnesota State University. Peter R. Jacoby, an English professor at San Diego Mesa College, summed up this line of thought bluntly: "By 2025, we will have long ago give up our privacy. The Internet of Things will demand--and we will give willingly--our souls." Not everyone thinks this loss of privacy is inevitable. Harvard fellow David "Doc" Searls argues that we needn't sacrifice our privacy in order to enjoy the advantages of connected devices. There's no reason that all devices must connect to the internet as opposed to private networks. And even those that are connected to the public internet could use encryption to talk to private servers, protecting your data from large companies. "People's Clouds of Things can be as personal and private as their houses (and, when encrypted, even more so)," he wrote. "They can also be far more social than any ‘social network’ because they won’t involve centralized control of the kind that Facebook, Google, and Twitter provide." 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 Searls imagines a world with more fine-tuned control over not just privacy, but the terms of service that govern the products we consume today. We've already seen some progress towards such a vision with open-source Internet of Things projects such as Spark , Tessel , Skynet and Nodered. The question is whether these types of platforms can be used to build truly open consumer products, and, if so, whether anyone will want to use them. It's also possible that the Internet of Things will fail to take off in any meaningful way. "The Internet of Things has been in the red zone of the hypometer for over a decade now," Bill St. Arnaud, a self-employed green internet consultant wrote. "Yes, there will be many niche applications, but it will not be the next big thing, as many pundits predict." An unnamed co-founder of a consultancy with practices in internet technology and biomedical engineering agreed. "Inter-networked wearables will remain a toy for the wealthy," he wrote. He thinks wearables and other connected devices will be useful for the military, hospitals, prisons and other niche operations, but he doesn't expect them to be particularly life-changing. Justin Reich, a fellow at Harvard University’s Berkman Center for Internet & Society, hedged his bets. "I’m not sure that moving computers from people's pockets (smartphones) to people’s hands or face will have the same level of impact that the smartphone has had," he wrote. "But things will trend in a similar direction. Everything that you love and hate about smartphones will be more so." Contributor X Topics Enterprise IoT Amit Katwala Kari McMahon Will Knight David Gilbert Andy Greenberg Khari Johnson Andy Greenberg Joel Khalili 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 "

"Watch Joel McHale Answers the Web's Most Searched Questions | Autocomplete Interview | WIRED"

"https://www.wired.com/video/watch/autocomplete-inverviews-joel-mchale-autocomplete"

"Open Navigation Menu To revisit this article, visit My Profile, then View saved stories. Close Alert Backchannel Business Culture Gear Ideas Science Security Merch To revisit this article, select My Account, 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 Joel McHale Answers the Web's Most Searched Questions About Credits Released on 12/01/2020 What has Joel McHale done? Now I feel like you're accusing me of murder. You're saying something like, What have you done!? [funky music] Hi, everybody. It's me, Joel McHale. Today I'll be doing the Wired Autocomplete Interview. [funky music] Here we go, guys. Why Joel McHale. Why Joel McHale tiger king. Why not? Well that fell into my lap because Ted Sarandos, basically, it was just like, Do you want to host the follow-up special to Tiger King? And COVID, it was just as they, it was like the week after it was all locked down. You know, it was when you thought, Well, if I look at someone weird they're gonna get COVID or maybe I'm gonna get COVID if I look at them too long, I don't know. So I got to host that thing and it's, I know it's a part of the actual series, but I had nothing to do with it. I barely, I showed up, I recorded some things. I did talk to those people for a very long time. So even though that special is like 33 minutes long or something, I talked to each of them for like two hours. It was, it was exhausting. I don't know how I do it. I don't know. We almost got Joe Exotic, but the prison or the jail he was in got a COVID scare. So that went away very quickly. Why is Joel McHale famous? [laughing] That is a good question. Why is Joel McHale podcast? Why? Why do we do a podcast? Ken is one of my good, good, good friends. If not one of my great friends. You know, I'm Joe, but he's a real doctor. I mean he really knows what he's doing. And I would call him and ask him about the virus. And he, we kind of were like, hey, we should do a podcast and talk about this. And then we'll talk to our friends after that. And so that's how that started. And Ken knows what he's talking about. I just read articles and then pretend to know what I'm talking about. Some publicist called me and be like, We would like to put our client on your podcast. Can you please give us the name of your Booker? And I'm like, You're talking to 'em. And, or Ken, or we're the bookers. So Ken's been, you know, on the most successful shows on TV right now with The Masked Singer and I Can See Your Voice and all the other ones. And so now I think he, that has kind of like, he's got a little more free time. How Joel McHale, here we go. How tall Joel McHale? Well I think everybody knows I'm 8'1. But that's just the lower half, it's very long. I am 6'4. How old is Joel McHale? I am 48 years old. So I could be your dad, in a lot of cases your granddad, so yeah. So you know, let's see some respect. 48, yeah not for much longer, next week. No, two weeks, I'm 49. I'm 49. How does Joel McHale... stay in shape? Thanks for saying that. That's right. I'm doing an ab workout right now. So I do like 40 minutes a day. Sometimes if I got a little more free time, I'll do an hour. But I try to carve out... And everyone's like, Don't you take days off? I'm like, I do not. I try to get it in every day somehow. I want to eat spaghetti carbonara for every meal. But if you operate at a caloric deficit, you'll not even stay in shape. You'll look like you're in shape. Thank you. How much does Joel McHale make for card sharks? How much money do I make for card sharks? Oh, well yeah. Well that's how I get paid. I have to play the game myself. So some weeks I'm making like over half a million dollars. Other weeks, gift certificate. So, but I just have to go out there and turn the cards over myself and then, and the producers always, you know, like, Come on, dude, keep going. You gotta, you gotta four up there. It's gotta be higher. And then like, Oh, we're so sorry. We're so sorry. We're so sorry. And now a kombucha break. I'm kidding. This is chilled red wine! Does Joel McHale. There we go. Does Joel McHale leave Community? No, I mean, I did. I stayed with it all six years. Other people left, but I certainly didn't. Wait, did I? And it's still going. Is that what happened? Does show still on? Does Joel McHale have lions? Yes, because I was paid in big cats for the Tiger King special. Does Joel McHale have a brother? No, I don't. I have two brothers. Oooh! And people like, Oh, are you the oldest? And I'm like, No. The youngest? No. I'm like, I'm the middle. And they'll go like, Totally. That's why he became an actor. Right, 'cause you, you just needed the attention and it doesn't mean you're in the middle. What are you talking about? Yes, because if I had been the youngest one I would have to have been a pilot. Their names are Chris and Steven. We look alike. Okay, does Joel McHale play accordion? [laughing] It's not play the accordion; it's play accordion. I do not play the accordion. I don't play any instrument. Bang! Joel, these are all blanks. This is Joel McHale and then just blanks. Joel McHale... The soup! Oh, takes you back, doesn't it? Yeah, that was the thing that helped me get the audition for, you know, like a zillion. Like I did not expect that I was going to be a host at all in my career. I think everyone thought I was the next, you know, Joel Edgerton. No, I stumbled into that job and got very lucky because a couple of executives at E! decided to take a shot and it, we, boy, that's 2005, geez. I didn't have a child then, or no did I? No I didn't even have a child then. Yeah, those were the days I got to do that for 12 years. It was really fun. Joel McHale drag race, wow. Yes, I loved being a judge. I think Michelle wanted to rip my head off. Michelle and I are friends, okay. We had a very fun time. That show's amazing. And the amount of work the performers put in is staggering. And like the changes they have to make it is remarkable. Joel McHale [grunting] Joel McHale dog. No three, three dogs. I got a French bulldog, a pug, and a thing called a coton de tulear. The French bulldog is a maniac and an alpha male apex predator. And then our pug, I got him on The Great Indoors, which was a short lived show. There was a scene that required this guest star to be holding a baby pug. The person in charge let me adopt that dog. And that dog is here now. And he's the sweetest boy. And in the show, the dog's name was Jonathan. And the dog, the puppy's name was Cowboy. So I brought him home and at that point my kids were like 11 and eight. And I was like, well, the dog's name is Cowboy. And the name of the dog on TV was Jonathan. And, but I was like, you can name the dog whatever you want. And they looked at me like I was crazy. They were like, The dog's name is Cowboy Jonathan. And I went, Okay, it is. Joel McHale knife collection. Correction, knife comma sword and weapon collection. Yeah I don't know what's wrong with me. It's just I've always collected knives and like nunchucks and billy clubs and throwing knives. I don't know why. And it's weird, people like, It's weird! I'm like, Yeah, I just was always obsessed with them. And it's hard for me not to go into a knife store if I'm walking by one. On Instagram I follow a bunch of knife companies, you know, to keep up. And my wife is like, Can you just put all those away? And I was like, Yeah. And then I never do. Last one on this page. Zodiac sign! Scorpio which means we have tails that are poisonous. Is Joel McHale. Is Joel McHale oh, here we go, nice. [beep] yeah. What are you looking at? Is Joel McHale related to Ryan Seacrest? His pile of money goes all the way to the clouds. So he's a very nice successful man. We are not related. We worked at E! forever or as I like to call it the Eh network. So I would see them in the hallways and I would just, he would just, he was always so busy counting his money that so I didn't, you know, I don't want to interrupt that. Very nice guy. And now he has a beard. Copied me. Is Joel McHale Left-handed. Oh, why would you ask? It's weird, I am left-handed for writing and like brushing my teeth and fine motor skills. And I am right-handed for gross motor skills. So throwing balls and golfing and batting. I could become a professional athlete if all my talent was in one arm. But alas it's not. We all have crosses to bear and I would bear mine on my right shoulder. Is Joel McHale a lawyer? No, not even close. I'm super dyslexic and cheated my way through high school and college and everything. I played one and it made, I said words out loud that sounded like I was one kind of, but no, I would be a terrible lawyer. Where Joel McHale. Okay, where is Joel McHale from? Seattle is my hometown. So that's, that's where I'm from. And as everybody know, I started a little coffee company called Starbucks, a little computer company called Microsoft, and some, I helped start an online shopping thing called Amazone. I can't remember the name of it. Anyway. Where did Joel McHale go to college? Oh, thank you. I went to the University of Washington. Go Huskies. Where has Joel McHale been? Where have I been, where have you been!? I feel like I'm constantly doing interviews like this so you don't have to ask that question. Where have you been? I've been trying to get your attention this whole time! Where have I been? On card sharks on ABC Sunday nights at 10 o'clock, nine central. Last one, oof, pressure, here we go. Where did Joel McHale meet his wife? Oh, that's a good question. Well, I met her twice. First time I was a freshman and she was a senior. Ooh, older woman. She's only one year older because I entered college as an older person. And she was very young for college and I met her and I was like, That's a very pretty woman. And then I did not see her again for like three years. And then I was shooting a movie, a crazy movie in Seattle, and her mom was an extra and her brother was a production assistant and he reintroduced us and she was like, Yeah, I know who he is. I don't need to see him again. And that's when she fell in love with me. No, I called my friend Kim and I was like, Hey, do you think you could put a good word in for me with Sarah Williams? And she was like, Haha, good luck. But Sarah took pity on me and allowed me to take her out. And, and then I, I wore her down and she then eventually agreed to marry me. Thank God that was almost 24 years ago. And she's regretted it ever since. Well, that was very fun. Thanks for having me. And this is the part of the show where people would say, Thank you, Wired. and then they'd throw the board, but I'm not gonna do that. I'm gonna throw those little things. I'll see you later. I'm off camera, right? Ah shit. Starring: Joel McHale Melissa McCarthy & Kristen Bell Answer The Web’s Most Searched Questions NASA Astronauts Answer The Web’s Most Searched Questions Common Answers The Web’s Most Searched Questions Ice Cube Answers The Web’s Most Searched Questions Eve Answers The Web’s Most Searched Questions Seth Rogen & Rose Byrne Answer The Web’s Most Searched Questions The Cast of Warcraft Answer The Web's Most Searched Questions Slow Mo Guys, MatPat, AsapSCIENCE, and Burnie Burns Answer the Web's Most Searched Questions Dana Carvey Answers the Web’s Most Searched Questions Mr. Robot's Carly Chaikin Answers the Web's Most Searched Questions Cara Delevingne Answers the Web’s Most Searched Questions Chelsea Handler Answers the Web’s Most Searched Questions Blindspot's Jaimie Alexander Answers the Web's Most Searched Questions Jennifer Aniston & Jason Bateman Answer the Web's Most Searched Questions Kate McKinnon & Vanessa Bayer Answer the Web's Most Searched Questions The Cast of "Rogue One" Answers the Web's Most Searched Questions Tracy Morgan Answers the Web's Most Searched Questions The Cast of 'Sesame Street' Answer the Web's Most Searched Questions Samuel L. Jackson Answers the Web's Most Searched Questions Jennifer Lawrence & Chris Pratt Answer the Web's Most Searched Questions Reggie Watts Answers the Web's Most Searched Questions Ryan Reynolds & Jake Gyllenhaal Answer the Web's Most Searched Questions Chris Evans Answers the Web's Most Searched Questions Morgan Freeman, Michael Caine, and Alan Arkin Answer the Web's Most Searched Questions Anne Hathaway & Jason Sudeikis Answer the Web's Most Searched Questions Salma Hayek & Eugenio Derbez Answer the Web's Most Searched Questions Amy Schumer & Goldie Hawn Answer the Web's Most Searched Questions Steve Carell & Kristen Wiig Answer the Web's Most Searched Questions Will Ferrell & Amy Poehler Answer the Web's Most Searched Questions Al Gore Answers the Web's Most Searched Questions on Climate Change Matthew McConaughey & Idris Elba Answer the Web's Most Searched Questions Dave Franco, Kumail Nanjiani and Fred Armisen Answer the Web's Most Searched Questions Tom Cruise & Doug Liman Answer the Web's Most Searched Questions Josh Brolin & Taylor Kitsch Answer the Web's Most Searched Questions Matt Damon & Julianne Moore Answer the Web's Most Searched Questions Nick Jonas Answers the Web's Most Searched Questions Gaten Matarazzo and Joe Keery Answer the Web's Most Searched Questions The Last Jedi Cast Answer the Web's Most Searched Questions John Cena Answers the Web's Most Searched Questions Owen Wilson & Ed Helms Answer the Web's Most Searched Questions Will Smith & Joel Edgerton Answer the Web's Most Searched Questions Black Panther Cast Answer the Web's Most Searched Questions Google Search Team Answers the Web's Most Searched Questions Bruce Willis Answers the Web's Most Searched Questions Charlize Theron & David Oyelowo Answer the Web's Most Searched Questions This Is Us Cast Answers the Web's Most Searched Questions Alicia Vikander Answers the Web's Most Searched Questions Jennifer Garner Answers the Web's Most Searched Questions Charlie Day Answers the Web's Most Searched Questions Jeff Goldblum Answers the Web's Most Searched Questions Taraji P. Henson & Tyler Perry Answer the Web's Most Searched Questions John Krasinski Answers the Web's Most Searched Questions Ansel Elgort & Suki Waterhouse Answer the Web's Most Searched Questions Terry Crews Answers the Web's Most Searched Questions Shawn Mendes Answers the Web's Most Searched Questions Solo Cast Answer the Web's Most Searched Questions Jodie Foster Answers the Web's Most Searched Questions Best of Autocomplete: The Cast of Black Panther, Stranger Things and More Answer the Web's Most Searched Questions Robert Pattinson & Mia Wasikowska Answer the Web's Most Searched Questions Alison Brie & Marc Maron Answer the Web's Most Searched Questions 'Sorry to Bother You' Cast Answers the Web's Most Searched Questions 'Ant-Man and the Wasp' Cast Answer the Web's Most Searched Questions Will Arnett Answers the Web's Most Searched Questions Mila Kunis & Justin Theroux Answer the Web's Most Searched Questions Ewan McGregor & Hayley Atwell Answer the Web's Most Searched Questions Liza Koshy Answers the Web's Most Searched Questions 'Dog Days' Cast Answer the Web's Most Searched Questions Ken Jeong Answers the Web's Most Searched Questions Mark Wahlberg, Ronda Rousey and Lauren Cohan Answer the Web's Most Searched Questions John Cho Answers the Web's Most Searched Questions Rami Malek & Charlie Hunnam Answer the Web's Most Searched Questions Anna Kendrick & Blake Lively Answer the Web's Most Searched Questions Paul McCartney Answers the Web's Most Searched Questions Keegan-Michael Key & Olivia Munn Answer the Web's Most Searched Questions Elizabeth Olsen Answers the Web's Most Searched Questions Kevin Hart & Tiffany Haddish Answer the Web's Most Searched Questions Rhett & Link Answer the Web's Most Searched Questions Riverdale Cast Answers the Web's Most Searched Questions Bella Thorne Answers the Web's Most Searched Questions John Mulaney & Nick Kroll Answer the Web's Most Searched Questions Aubrey Plaza & Craig Robinson Answer the Web's Most Searched Questions The Try Guys Answer the Web's Most Searched Questions Keira Knightley & Mackenzie Foy Answer the Web's Most Searched Questions Julia Roberts & Dermot Mulroney Answer the Web's Most Searched Questions Emily Ratajkowski & Aaron Paul Answer the Web's Most Searched Questions Sarah Silverman & John C. Reilly Answer the Web's Most Searched Questions Margot Robbie & Saoirse Ronan Answer the Web's Most Searched Questions Natalie Portman & Jude Law Answer the Web's Most Searched Questions Lin-Manuel Miranda Answers the Web's Most Searched Questions Best WIRED Autocomplete Moments of 2018 Feat. Liza Koshy, David Dobrik, The Try Guys & More Ninja Answers the Web's Most Searched Questions Zedd Answers the Web's Most Searched Questions Bryce Dallas Howard Answers the Web's Most Searched Questions James McAvoy & Sarah Paulson Answer the Web's Most Searched Questions Jane Fonda & Lily Tomlin Answer the Web's Most Searched Questions Daniel Radcliffe Answers the Web's Most Searched Questions Priyanka Chopra, Rebel Wilson & Adam Devine Answer the Web's Most Searched Questions David Dobrik Answers the Web's Most Searched Questions Brie Larson Answers the Web's Most Searched Questions Freddie Highmore Answers the Web's Most Searched Questions Oscar Isaac & Pedro Pascal Answer the Web's Most Searched Questions Markiplier Answers the Web's Most Searched Questions Colin Farrell & Danny DeVito Answer the Web's Most Searched Questions Queer Eye Cast Answer the Web's Most Searched Questions Nikolaj Coster-Waldau Answers the Web's Most Searched Questions Gina Rodriguez Answers the Web's Most Searched Questions Sean Bean Answers the Web's Most Searched Questions Anthony Mackie Answers the Web's Most Searched Questions Lily Collins & Nicholas Hoult Answer the Web's Most Searched Questions Wu-Tang Clan Answer the Web's Most Searched Questions Wanda Sykes Answers the Web's Most Searched Questions Charles Melton Answers the Web's Most Searched Questions Jessica Alba & Gabrielle Union Answer the Web's Most Searched Questions Jon Hamm & David Tennant Answer the Web's Most Searched Questions Thomas Middleditch & O'Shea Jackson Jr. Answer the Web's Most Searched Questions Sophie Turner & Jessica Chastain Answer the Web's Most Searched Questions Mindy Kaling & Emma Thompson Answer the Web's Most Searched Questions Smosh Answers the Web's Most Searched Questions Tom Holland, Zendaya & Jacob Batalon Answer the Web's Most Searched Questions Millie Bobby Brown, Finn Wolfhard & Noah Schnapp Answer the Web's Most Searched Questions Winona Ryder & David Harbour Answer the Web's Most Searched Questions Eric Andre Answers the Web's Most Searched Questions Machine Gun Kelly Answers the Web's Most Searched Questions Charlie Puth Answers the Web's Most Searched Questions Novak Djokovic Answers the Web's Most Searched Questions Anderson Cooper Answers the Web's Most Searched Questions Jim Gaffigan Answers the Web's Most Searched Questions Liam Payne Answers the Web's Most Searched Questions Lilly Singh Answers the Web's Most Searched Questions Gwen Stefani Answers the Web's Most Searched Questions Dove Cameron Answers the Web's Most Searched Questions Kevin Smith Answers the Web's Most Searched Questions Niall Horan Answers the Web's Most Searched Questions Lele Pons Answers the Web's Most Searched Questions Hailee Steinfeld Answers the Web's Most Searched Questions Louis Tomlinson Answers the Web's Most Searched Questions Kiernan Shipka & Isabela Merced Answer the Web's Most Searched Questions Kristen Stewart, Naomi Scott, and Ella Balinska Answer the Web's Most Searched Questions Jack Black & Awkwafina Answer the Web's Most Searched Questions KJ Apa Answers the Web's Most Searched Questions The Best of Autocomplete 2019: Funniest Moments from Stranger Things, Spider-Man and More Billy Eichner & Cobie Smulders Answer the Web's Most Searched Questions Frozen 2 Cast Answer the Web's Most Searched Questions Jada Pinkett Smith Answers the Web's Most Searched Questions Zach Galifianakis & Zoe Saldana Answer the Web's Most Searched Questions Elijah Wood Answers the Web's Most Searched Questions Noah Centineo & Lana Condor Answer the Web's Most Searched Questions Lucy Hale Answers the Web's Most Searched Questions Patrick Stewart Answers the Web's Most Searched Questions Norman Reedus Answers the Web's Most Searched Questions Astronaut Chris Hadfield Answers the Web's Most Searched Questions Nick Offerman Answers the Web's Most Searched Questions Binging with Babish Answers the Web's Most Searched Questions Jamie Dornan & Shailene Woodley Answer the Web's Most Searched Questions Ellie Kemper Answers the Web's Most Searched Questions Joe Biden Answers the Web's Most Searched Questions Ricky Gervais Answers the Web's Most Searched Questions Alicia Keys Answers the Web's Most Searched Questions Tony Hawk Answers the Web's Most Searched Questions Russell Crowe Answers the Web's Most Searched Questions Kevin Bacon Answers the Web's Most Searched Questions Joey King & Joel Courtney Answer the Web's Most Searched Questions Kermit & Miss Piggy Answer the Web's Most Searched Questions Alessia Cara Answers the Web's Most Searched Questions Jamie Foxx & Joseph Gordon-Levitt Answer the Web's Most Searched Questions Mayim Bialik Answers the Web's Most Searched Questions Desus & Mero Answer the Web's Most Searched Questions Dolly Parton Answers the Web's Most Searched Questions Ruby Rose Answers the Web's Most Searched Questions Sonequa Martin-Green Answers the Web's Most Searched Questions Chelsea Handler Answers the Web's Most Searched Questions John C. Reilly & Tim Heidecker Answer the Web's Most Searched Questions Joel McHale Answers the Web's Most Searched Questions Questlove Answers the Web's Most Searched Questions Dua Lipa Answers the Web's Most Searched Questions Zara Larsson Answers the Web's Most Searched Questions Bob Odenkirk and RZA Answer the Web's Most Searched Questions SpongeBob's Tom Kenny & Bill Fagerbakke Answer the Web's Most Searched Questions Jackson Wang Answers the Web's Most Searched Questions Eric Andre Answers the Web's Most Searched Questions...Again LILHUDDY Answers the Web's Most Searched Questions Polo G Answers the Web's Most Searched Questions Hank Azaria Answers the Web's Most Searched Questions Zack Snyder Answers the Web's Most Searched Questions TWICE Answer the Web's Most Searched Questions MONSTA X Answer the Web's Most Searched Questions Siri, Alexa and Google Home Answer the Web's Most Searched Questions Rich Brian and NIKI Answer the Web's Most Searched Questions B.I Answers the Web's Most Searched Questions Never Have I Ever Cast Answer the Web's Most Searched Questions M. Night Shyamalan Answers the Web's Most Searched Questions Henry Golding Answers the Web's Most Searched Questions BTS Answer the Web's Most Searched Questions Emily Blunt & Dwayne Johnson Answer The Web's Most Searched Questions Jennifer Hudson Answers the Web's Most Searched Questions Outer Banks Cast Answer the Web's Most Searched Questions Rita Ora Answers the Web's Most Searched Questions Dove Cameron Answers the Web's Most Searched Questions...Again Daniel Radcliffe Answers MORE of the Web's Most Searched Questions Ben Platt & Amandla Stenberg Answer The Web's Most Searched Questions Tom Hardy & Andy Serkis Answer the Web's Most Searched Questions On My Block Cast Answer the Web's Most Searched Questions Daniel Craig & Lashana Lynch Answer the Web's Most Searched Questions William Shatner Answers the Web's Most Searched Questions Madison Beer Answers the Web's Most Searched Questions Marshmello Answers the Web's Most Searched Questions Amanda Seyfried & Finn Wittrock Answer the Web's Most Searched Questions Nina Dobrev Answers the Web's Most Searched Questions Kit Harington Answers the Web's Most Searched Questions Kristen Bell & Kirby Howell-Baptiste Answer the Web's Most Searched Questions Dominic Monaghan & Billy Boyd Answer the Web's Most Searched Questions Cowboy Bebop Cast Answer the Web's Most Searched Questions YouTube Search Team Answers the Web's Most Searched Questions Jack Whitehall Answers the Web's Most Searched Questions Andrew Garfield Answers the Web's Most Searched Questions Sabrina Carpenter Answers the Web's Most Searched Questions Simu Liu Answers the Web's Most Searched Questions Tom Holland, Zendaya & Jacob Batalon Answer MORE of the Web's Most Searched Questions Eric Nam Answers the Web's Most Searched Questions Ben Affleck & Lily Rabe Answer the Web's Most Searched Questions ATEEZ Answer the Web's Most Searched Questions Seth Rogen Answers The Web’s Most Searched Questions Owen Wilson Answers The Web’s Most Searched Questions David Byrne Answers the Web's Most Searched Questions Johnny Knoxville Answers the Web's Most Searched Questions Channing Tatum & Sandra Bullock Answer the Web's Most Searched Questions Karen Gillan Answers the Web's Most Searched Questions Leslie Mann & Judd Apatow Answer the Web's Most Searched Questions Cole Sprouse Answers the Web's Most Searched Questions Nicolas Cage Answers the Web's Most Searched Questions TommyInnit Answers the Web's Most Searched Questions Drew Gooden Answers the Web's Most Searched Questions Seth MacFarlane Answers the Web's Most Searched Questions Sadie Sink, Noah Schnapp & Gaten Matarazzo Answer the Web’s Most Searched Questions Taika Waititi Answers the Web’s Most Searched Questions Maisie Williams Answers the Web’s Most Searched Questions Jacksepticeye Answers the Web's Most Searched Questions Chris Hemsworth Answers the Web's Most Searched Questions Guinness World Records Answer the Web's Most Searched Questions The Russo Brothers Answer the Web's Most Searched Questions Keke Palmer Answers the Web's Most Searched Questions Marques Brownlee Answers the Web's Most Searched Questions Neil Patrick Harris Answers the Web's Most Searched Questions Jennifer Lopez & Leah Remini Answer the Web's Most Searched Questions Dakota Johnson & Jeff Bridges Answer the Web's Most Searched Questions High School Musical: The Musical: The Series Cast Answer the Web's Most Searched Questions Kevin Hart & Mark Wahlberg Answer the Web's Most Searched Questions Danny DeVito Answers the Web's Most Searched Questions Lili Reinhart Answers the Web's Most Searched Questions John Boyega Answers the Web's Most Searched Questions Sofía Vergara & Simon Cowell Answer the Web's Most Searched Questions Steve-O Answers the Web's Most Searched Questions Stray Kids Answer the Web's Most Searched Questions Charli & Dixie D'Amelio Answer the Web's Most Searched Questions NCT 127 Answer the Web's Most Searched Questions Hasan Minhaj Answers the Web's Most Searched Questions Cobra Kai's Ralph Macchio Answers the Web's Most Searched Questions Mrwhosetheboss Answers the Web's Most Searched Questions Chloë Grace Moretz Answers the Web's Most Searched Questions Millie Bobby Brown Answers the Web's Most Searched Questions Jenna Ortega Answers the Web's Most Searched Questions Veritasium's Derek Muller Answers the Web's Most Searched Questions Jason Momoa Answers the Web's Most Searched Questions LaurDIY Answers the Web's Most Searched Questions Nigel Ng & Uncle Roger Answer the Web's Most Searched Questions Finn Wolfhard & Guillermo del Toro Answer the Web's Most Searched Questions Ludwig Answers the Web's Most Searched Questions John Krasinski & Michael Kelly Answer the Web's Most Searched Questions ITZY Answer the Web's Most Searched Questions Danny Gonzalez Answers the Web's Most Searched Questions Ashton Kutcher Answers the Web's Most Searched Questions Paul Rudd & Jonathan Majors Answer the Web's Most Searched Questions Outer Banks Cast Answer the Web's Most Searched Questions Again Kelly Slater Answers Surfing Questions From Twitter KAROL G Answers the Web's Most Searched Questions Penn Badgley Answers the Web's Most Searched Questions Chris Pine, Hugh Grant & Michelle Rodriguez Answer the Web's Most Searched Questions Willem Dafoe Answers the Web's Most Searched Questions KSI Answers the Web's Most Searched Questions Bob Odenkirk Answers the Web's Most Searched Questions Jisoo Answers the Web's Most Searched Questions Ali Wong & Steven Yeun Answer the Web's Most Searched Questions Chris Evans & Ana de Armas Answer the Web's Most Searched Questions Airrack Answers the Web's Most Searched Questions ChatGPT Answers the Web's Most Searched Questions James & Sean Gunn Answer the Web's Most Searched Questions Mark Hamill Answers the Web's Most Searched Questions Shameik Moore, Issa Rae & Hailee Steinfeld Answer The Web's Most Searched Questions Tom Segura Answers The Web's Most Searched Questions Robert Downey Jr. & Christopher Nolan Answer The Web's Most Searched Questions Bear Grylls Answers The Web's Most Searched Questions Smosh Answer The Web's Most Searched Questions Ice Cube Answers The Web's Most Searched Questions Stephen Curry Answers The Web's Most Searched Questions 'Heart of Stone' Cast Answers The Web's Most Searched Questions 'Critical Role' Cast Answers The Web's Most Searched Questions Harry Mack Freestyles The Web's Most Searched Questions Olivia Rodrigo Answers The Web's Most Searched Questions Pokimane Answers The Web's Most Searched Questions MoistCr1TiKaL Answers The Web's Most Searched Questions Dream Answers The Web's Most Searched Questions Fanum Answers The Web's Most Searched Questions Casey Neistat Answers The Web's Most Searched Questions | WIRED Måneskin Answer the Web's Most Searched Questions 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 "

"What to Do When Hackers Crash Your Gene Pool Party | WIRED"

"https://www.wired.com/story/gadget-lab-podcast-618"

"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 Michael Calore Lauren Goode Boone Ashworth Gear What to Do When Hackers Crash Your Gene Pool Party Illustration: Yaroslav Kushta/Getty Images Save this story Save Save this story Save Genetic testing companies like 23andMe and Ancestry offer a pretty enticing prospect. Just mail off a little bit of your spit in a tube and the company's lab can reveal the details of your ethnic background and trace the many branches of your family tree. The popularity of such tests means these genomics and biotechnology companies hold a whole lot of very personal data about their customers, and hackers tend to see their databases as targets ripe for the picking. Earlier this month, the private data of millions of 23andMe customers was stolen and put up for sale on hacker forums. Most troublingly, the data gathered targeted specific ethnic groups, including Ashkenazi Jews and people of Chinese descent. This week on Gadget Lab, we talk with WIRED senior writer Lily Hay Newman about the 23andMe hack, what it means for the people who were directly affected, and whether it's a good idea to give companies access to your genetic material and history in the first place. Read more from Lily about the 23andMe hack and some updates on how it has gotten even worse. Follow all of WIRED’s cybersecurity coverage. Lily recommends Taylors of Harrogate Yorkshire Tea, specifically the flavor Malty Biscuit Brew. Lauren recommends Pasta e Ceci. Mike recommends the episode of the New York Times podcast Popcast titled, “ Do We Need Album Reviews Anymore? ” Lily Hay Newman can be found on social media @ lilyhnewman. Lauren Goode is @ LaurenGoode. Michael Calore is @ snackfight. Bling the main hotline at @ GadgetLab. The show is produced by Boone Ashworth (@ booneashworth ). 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. Michael Calore : Lauren? Lauren Goode : Mike. Michael Calore : Have you ever had your genome sequenced? 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 mean like one of those kits where you spit in a tube and mail it off and find out that you hate cilantro and your father is not your father? Michael Calore : Yeah, that's pretty much what I mean. Lauren Goode : I like cilantro though. I have done one of those kits as a matter of fact. Michael Calore : What did you learn about yourself? Lauren Goode : I learned that I am 33 percent cat. Michael Calore : That tracks. Have you ever wondered about your genetic data leaking? Lauren Goode : I think about it all the time, and also I think about where it goes if 23andMe or companies like it get acquired. Because someone has to absorb that data and it's an entity that I wasn't planning on having my data. Michael Calore : That's right. And I think you should be paranoid about it. Lauren Goode : Really? Michael Calore : Yes, we're going to talk all about it today. Lauren Goode : Oh boy. I can't wait. Michael Calore : Let's do it. [ Gadget Lab intro theme music plays ] Michael Calore : Hi, everyone. Welcome to Gadget Lab. I am Michael Calore. I'm a senior editor at WIRED. Lauren Goode : And I am Lauren Goode. I'm a senior writer at WIRED. Michael Calore : We're also joined this week by WIRED senior writer Lily Hay Newman. Lily, welcome back to the show. Lily Hay Newman : Thanks for having me. Michael Calore : Of course. It's always a banger when you're on the show. People see your name in the show description and they put the kids to bed and they lock the door because they know that we're going to talk about cybersecurity and hacks and cybercrime and all that lovely stuff. Lily Hay Newman : Yeah, maybe I'm actually a deterrent to listeners. Michael Calore : So if you've ever been curious about your ancestors or what part of the world your family really comes from, you may have been tempted to send a bit of yourself to companies like 23andMe or Ancestry. You just spit into a little tube and mail it to the company. And within weeks, you get back a detailed map of your lineage. And if you want, the same map of other people that you might be related to. It's pretty cool at least until that data falls into the wrong hands. That is exactly what happened with 23andMe. At the beginning of October, the company announced that it was hacked and as a result, the names, birth years and general descriptions of genetic data for millions of people were posted on hacker forums. The hack appeared to target specific ethnic groups and the methods used to obtain the data appeared to be relatively low tech. Late last week, the breach became even worse with another hacker posting millions of more records on hacker forums. Lily, you cover all sorts of hacks and data breaches on our security desk here at WIRED. And you've written about this 23andMe breach. What kind of information was revealed? 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 Lily Hay Newman : So the data that was revealed is not raw genetic data, but it is information that could give you a sense of who someone is and potentially identify them. So things like a display name, sex, birth year. And details about broad genetic ancestry. So something like broadly Arabian or broadly European. And then potentially some more specific geographic ancestry information as well. So it's not the crown jewels, but it starts to really get into who someone is and some information about their background. Lauren Goode : So it sounds like it's specific to ethnic background and not necessarily biomarkers for diseases or other medical conditions that might show up from some of these tests? Lily Hay Newman : Yeah. The way the data was collected on this broad scale was by scraping or collecting information that users had opted to share in this 23andMe feature called DNA Relatives. So the feature is all about helping you connect with other relatives and find people and is sort of like a social-ified service. So the actors who scraped this data seemed to have searched under certain criteria and that's how they had broad buckets of information on Ashkenazi Jews, is one category they were searching for. And then scraping people of Chinese descent. There were about 300,000 of those. And then as we mentioned, the actor has continued to post more data both in those categories and in a broader range. So yeah, that's why it's clustered in those areas. But all of this information is geared towards what customers might've opted into sharing with other 23andMe users. So it's not public to the public internet, but public within the service. Lauren Goode : Mm-hmm. And just to be clear for folks, when Lily refers to actor , that's a term used in the cybersecurity world to describe someone who's taking an action. For example, a bad actor is someone with malicious intent. We're not referring in this instance to Leonardo DiCaprio. Although, it would be quite a story if he was the one who hacked 23andMe. Lily Hay Newman : That would be a big scoop. Michael Calore : Now, obviously we can't necessarily ascribe motive, but we can guess why this actor would target specific ethnic groups and make that known in their announcement when they post the data for sale. 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 Lily Hay Newman : Right. I think there's a lot of reasons that it could have been done this way. It could have to do with wanting to specifically expose people in those groups, like there could have been some sort of geopolitical or other ideological motivation. But also a lot of researchers I talked to speculated that things like this are often just for notoriety to try to ... Because this data is being sold on hacker forums. And so a lot of times, actors, there's that word, actors , will do things like this simply to make their product more appealing or gain notoriety or get exposure and bring attention to hawk their wares essentially. So it's possible that it was for some sort of insidious, racially motivated reason. But that's not necessarily the case. Michael Calore : How did the hacker actually get into people's accounts? How much of this points to perhaps a lack of security on the part of 23andMe? Lily Hay Newman : So the company would say that that's not the case. They want to make the distinction that the way they say this happened was that a small number of accounts were compromised using a technique called credential stuffing, which is really just going through all these combinations of usernames and passwords that have been previously leaked or stolen, and other breaches from around the internet not necessarily related to the victim or the target in question, and then actors trying those stolen credentials against all different logins. And the idea there is if you've reused a username and password on multiple accounts, the same username and password that was stolen in one place will let the attackers into your account in another place. So 23andMe says that it's not a breach of their systems and isn't exactly hacking. It's like stealing the key and then just walking in the front door. You don't have to break down the door if you have the key. The crucial thing there though is to get from those few accounts to all the millions of people whose data was impacted by this, that's where I use the term scraping. The concept is that then, the attackers use their access into that small group of accounts to simply look at or pull up records that were shared with the accounts from the DNA relative's service and hoard massive amount of data from there. But so, how much is this a security issue and what does this say about 23andMe's defenses? It's an interesting area because scraping as a technique, companies can say and do say, "That's not a breach." Users have to opt into sharing that information. They could choose not to share it. And companies will say things like, "We take measures to reduce scraping." But it's inherent in publishing data to a broad set of users or publicly and we can't stop it completely. But when you're seeing scraping like this with a genetic service, it underscores what researchers and privacy advocates have been saying for a long time, which is that scraping isn't just getting a copy of the phone book or something. These digital services make it really easy for actors to hoard and gather all this data and we need to think about that and take mitigating that risk seriously, rather than just saying, "Well, it wasn't a breach of our systems, so we weren't hacked." This isn't our problem. 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 : So the data was posted for sale at a site called BreachForums. What can you tell us about this corner of the internet? Lily Hay Newman : BreachForums is a popular and well-known kind of clearinghouse for people to post all sorts of data and tools, other information, and it fits into a broader ecosystem of hacker forums for advertising and posting data. Sometimes, these forums can be used in positive ways to just share information about potential concerns. But they can also be used at times to distribute stolen data or at least advertise its existence and then actually distribute it elsewhere. Michael Calore : Right. Lauren Goode : Mike's been hanging out there a lot. Yeah, he doesn't know. I can see his computer here at the office and I'm like, "What is Mike doing at breachforums.com?" Michael Calore : Yeah, I lost the keys to my car and I'm trying to figure out how to get into it. It's totally white hat, totally up and up. I swear. Lauren Goode : You don't have a car. Lily Hay Newman : When Calore and I see each other, he says, "See you on BreachForums." And I say, "Not if I see you first." Michael Calore : All right, well on that note, let's take a break and we'll come right back. [ Break ] Michael Calore : All right, welcome back. For years, companies like 23andMe and Ancestry have been collecting genetic information from millions of people. They've used it to generate massive pools of data about some of the most important things you can know about a person. Where you come from, who you're related to, what genetic conditions might run in your family. It's intimate, personal information gleaned from just a little bit of spit. Lily, I'm sorry for asking such a leading question, but should people be willingly sending their genes to these companies? Are all of our family trees already up for grabs now somewhere? Lily Hay Newman : So it's a really good question. It's the type of thing that you want to think about in terms of genetic testing, but that also applies conceptually to a lot of things. Ultimately, I think there isn't a clear-cut answer because it's more of a cost-benefit assessment of what you're getting out of it. First of all, in other contexts, people do genetic testing for medical reasons, to find out things about their health status and that might be urgent or very important. But even for the consumer facing more home tests, which also potentially have a medical purpose but aren't necessarily being prescribed or recommended by a doctor or something like 23andMe, there still could be a massive personal and emotional and psychological value to someone knowing more about the ancestry component or the finding relatives, finding biological connections. So I don't want to minimize or downplay and say, "Well, these are just curiosities and it's become way too mainstream and people shouldn't be using it", because I don't think that's the case. But if there isn't a specific and compelling reason to do it or if there aren't these pressing personal questions that people are wanting to get some insight on, I do think it's really worth taking a pause, especially for services that have this social component. I think that's really the tie into this breach. And like I said, this can apply to a lot of things. If there's a social component to a service, where to really be able to use it and get the full feature set out of it, you're going to need to opt into sharing data, not just with the company, but with other users and a broad network of users, you start to encounter these issues. The same ones that the traditional social networks have grappled with about social graph and what else can be gleaned about you and a cohort of people that you then can be grouped into from that data that you're sharing semi publicly with other users. So I think that's what this incident with 23andMe really underscores. 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 : I was wondering about the fine print in some of these apps like Ancestry or 23andMe that people should be aware of in the event of some kind of partnership or acquisition. Because years ago, I was writing a lot about health and fitness apps that were very consumer facing. And one by one, a bunch of them got acquired. They were not sustainable businesses on their own. It was hard to convince people to pay for a subscription service to use, just your favorite running app or something like that. And I had signed up for and used all of them. And all of a sudden I thought, "OK, great. So I guess Under Armour owns all of my data now. Google owns all of this fitness data now." What should people know about what happens if 23andMe or other entities like it end up getting acquired someday? Where does that data go? Lily Hay Newman : I think the crucial concept in general, which ties into what we've all just been talking about, is that once you release data into the wild, it can't be put back in the box. That's just the core of what the stakes are for something like genetic data, but again, could apply to other things too. And it's hard, but I try to be thoughtful about it in every context I can think of. Like, well, what if I make a shared calendar with someone to coordinate about whatever workout schedules? And then that means they have that data in their calendar app and I have it in my app. So I think thinking through just that on off switch or that binary of once it's out there, it could be stolen, it could be sold to another company. You can just keep riding that wave to places you never even would've thought of on the day that you spit in the tube. Michael Calore : Yeah. When you do spit in the tube, you do have some choices about how your data is used by the company. You can consent to allowing your data to be used in research, particularly for pharmaceutical companies. There are partnerships between the companies that collect and process your genetic data for you and the companies that develop drugs that work on people with specific conditions. So when a user submits to that and they say, "Yes, you can use my data", before your data is passed along to the partner company, it's anonymized and aggregated. Can you explain briefly what that means? What does anonymized data look like and is it truly anonymous? 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 Lily Hay Newman : This is a big topic. The basic concept is stripping the personally identifiable components away so that what's left is data that is about you, but could be about anyone and can't be specifically linked to you. So without a bunch of … your name, your specific characteristics, your hair color, let's say. Like OPSEC breach here, I have brown hair. The fact that that data point in the dataset is my brown hair versus someone else's brown hair is stripped away or becomes anonymized when it's not no longer connected to my name, my birthday, other things about me. So that's the concept, is to strip that away. There have been a lot of studies and a lot of research on the specific techniques that are used by different companies that even have been invented and exist abstractly to anonymized data sets. And often, the conclusion is that there is some reverse engineering that's possible and that the information has not been totally anonymized. So that's one factor to consider. But another thing to consider is, again, this 23andMe data dump did not include raw genetic data. But in the case of raw genetic data, you really have to pull the information very far apart and isolate specific things in order to anonymize it. Because if you just have a leak, again hypothetically, not in this situation of full genomes or even segments of someone's genome, that is the ultimate identifying information. So even if my name isn't on it anymore, if there's another dataset that does have my genetic information, that does have my name, that anonymized dataset can be linked back to me. Michael Calore : Right. All right. Well, Lily, thanks for taking us through all of this stuff. I know it's hairy and you're still reporting on it, right? Lily Hay Newman : Yes, more is still coming to light about this incident. And as you all brought up, the broader questions around genetic privacy and the privacy implications of scraping are just huge topics that we're continuing to delve into at WIRED. Michael Calore : And we look forward to reading more of those stories. Everybody can find them at WIRED.com. Let's take a break and we'll come right back with our recommendations. 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 [ Break ] Michael Calore : OK, Lily, you've done this a few times. You know how it works and you're prepared, I'm sure. What is your recommendation for our listeners? Lily Hay Newman : I like that jab as if perhaps I am not prepared. I am sure you're prepared. Michael Calore : I would expect nothing less. Lily Hay Newman : My recommendation this week, there's a lot of really heavy stuff going on in the world, and so I wasn't sure, should I recommend something very intense or like a humanitarian thing, or should I recommend something really light? But I don't want to be too jokey. So I am going to recommend something light, but something that has been just grounding for me and helpful to me lately, which is a type of tea. It is not a magic tea. It is a normal tea. And— Lauren Goode : What's a magic tea? Michael Calore : I think she means like psychotropic. Lauren Goode : Like a hallucinogenic? Michael Calore : Yeah. Lily Hay Newman : Yeah. Lauren Goode : OK. You can ... Please continue. Lily Hay Newman : Have me back on the show. We'll see what happens next week. Lauren Goode : Done. Lily Hay Newman : But this week, I'm just recommending regular tea. This was tea that was gifted to me by a WIRED colleague, Matt Burgess on the Security desk, and imported for me from the United Kingdom where he lives. It's Taylors of Harrogate Yorkshire Tea, and specifically it's a novelty flavor called Malty Biscuit Brew. So I call it biscuit tea. Lauren Goode : And does it have caffeine in it? Lily Hay Newman : Yeah, it's a black tea, but normal. It's not like a huge amount of caffeine, just the normal black tea amount, I think. But then it also has this sort of toasted malt grain in it that makes it taste like eating tea and biscuits all in the tea and it's really delicious. And normally, for me, I was concerned that this was my one box ever until Matt comes back to the US and that I would never be able to get it again. But then I saw that it actually is sold online from some importers and is not that unreasonable on Amazon. So depending on where people want to buy their tea, if you're in the US, there are options. And if you're in the UK, I think you can buy it at grocery stores. Yorkshire Tea, Malty Biscuit Brew. It's just delicious and very comforting. 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 : It sounds great. Michael Calore : Do you have to put milk in it? Lauren Goode : I was just going to ask that because our colleague Jeremy White came on the show a few months ago now to talk about Tesla. And his recommendation at the end was related to tea and he had very specific directions around this. He's also British, by the way. Lily, do you put milk in your tea? Lily Hay Newman : Well now, I've gotten myself into trouble because I think the answer is yes, that that is a requirement. And I think it ... So Matt and I brewed some of this tea when we were at the WIRED New York office a few months ago and he brought the tea. And we put milk in it there because I think that's just what is supposed to happen, and he spearheaded that initiative. And it does make it more biscuity in a way. I don't know exactly how to describe it. But I personally typically don't put milk in my tea and I just drink it black or whatever you would call it. And the tea is great that way too. Though I'm sure I'm revealing my ignorance somehow by saying that. Michael Calore : I think you should drink it however you prefer it, because then you're drinking tea instead of not drinking tea. Lauren Goode : I think Jeremy's remarks were not necessarily about milk or no. It was about the order with which you put the milk in if I remember correctly? Michael Calore : He has strong feelings about milk. Lauren Goode : Strong feelings. Michael Calore : Which I don't agree with either. Anyway, Lily, thank you for that— Lauren Goode : Great— Michael Calore : Refreshing— Lauren Goode : Recommendation. Michael Calore : Biscuity recommendation. Lauren, what is your recommendation? Lauren Goode : First, I want to give a shout-out to the folks who sent me workout playlists. On last week's episode of Gadget Lab, I said that I was really tired of my exercise playlist on Spotify. I put a call out and I got some really wonderful recommendations. So I want to say thanks in particular to Pat, Leo and Shannon. Also to you Mike, because you were I think the first person who sent me a workout playlist. And it was a death metal playlist titled Run or Die. I'm not sure if actually I have the rights to play this on the show. Do we have Boone? I'm looking at Boone, our producer. Is it possible for me to play this and get in trouble, not get in? 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've been told by our lawyers that fair use is not a determination we make in the room. Lauren Goode : This is breaking news. It's like ... Michael Calore : Yeah, it makes you want to run. It makes you want to work out. Lauren Goode : So I must admit I didn't. I didn't really listen to this one yet. I went through the list of artists and I thought, "Nope, don't know that. Nope, don't know that one. Don't know. Nope, don't know. Nope, nope. Oh, Blood Incantation." I know them because Mike just went to their show. That's literally the only reason. Michael Calore : Such a great band. Lauren Goode : Right. Well, thank you very much. My actual recommendation this week, it is ... We should have a little intro music for this. Oh, OK. It is time for Pasta e Ceci. Longtime listeners of the show will know that in the past, both Mike and I think have recommended this New York Times cooking recipe. It is called Pasta e Ceci. You can look it up. Pasta e Ceci, Italian pasta and chickpea stew. I believe my Italian people call it pasta fazool. This is what it is. It's delicious. It is just the perfect, if you like Italian food and flavorings, perfect late fall, early winter stew. It's really more like a stew. It's not just a soup. It's not like minestrone where there's a lot of water and water-based vegetables. It's thick, it's hearty. You can put different things. You can add some bay leaves to it. You can put some rosemary in it for flavor, which the recipe calls for. Red pepper, you can adjust the red pepper. I like to put a little bit of cheese on top of it. Occasionally in avocado, but that really makes it pretty hearty. And Mike, you've mentioned before, it's great for freezing. Michael Calore : Yes, you can cook it and freeze it and then eat it like every third day or every Sunday. Lauren Goode : And depending on how much red pepper you put in this thing, by freezing it and just letting it all soak in, it really packs a punch. So just be careful with the red pepper, I would say. 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 : Nice. Lauren Goode : That is my recommendation this week. Try making that stew. Michael Calore : Pasta fazool. Lauren Goode : Pasta fazool. And then another thing, I don't think there's an official recipe for it. But one time you and Boone were over and you made that incredible pasta with capers and what else was in it? Michael Calore : Tomatoes, basil, garlic. Lauren Goode : Well, yeah. Yes, tomato. It was tomato sauce base, but it was delicious. Is that like an official recipe? Michael Calore : I think it's just the kind of thing that you just learn as you grow up in an Italian-American household. Lauren Goode : Yeah, just throw it together. Some good peasant pasta. Michael Calore : Yeah. Lauren Goode : All right. Well, I guess that's a side note there. Michael Calore : Sure. Lily Hay Newman : Is this a recommendation or just making us jealous that you all hang out and eat great food? Lauren Goode : Both. Michael Calore : Both. And listen to death metal. Lauren Goode : Well, some of us. Mike, what's your recommendation this week? Michael Calore : I am going to recommend an episode of the New York Times Popcast. It's sort of a New York Times playlist-y theme this week. Maybe you could listen to this while you're drinking your tea. It is an episode of the Popcast , which is hosted by Jon Caramanica, the chief pop music critic at The New York Times. This episode came out a couple of weeks ago on October 12. It's called, "Do We Need Album Reviews Anymore?" And it's a 45-minute, hourlong conversation between Caramanica and Jamie Brooks, who is a recording artist and a writer and an all around swell person. They talk about the future of music journalism at first. But they also fascinatingly talk about how the technologies of the day have changed the artistic decisions that people make when they create music. Like for example, during the ringtone era, late 2005 to about 2010 when you could load ringtones onto your smartphone, that changed the economics of the music industry and it changed the way that people put out songs in the streaming era. Playlists, singles, the importance of those things, really short songs. Short albums so you can rack up plays. All of those technological innovations in the way that people consume music has changed how music sounds. They also just talk about the economics of making music and how that's changed and the role that the critic plays in that world. There's conversations online whenever an artist releases an album. And that just doesn't happen as often anymore. It's a really fascinating conversation, especially if you grew up reading record reviews or if you grew up anticipating album releases. You may not think about it that much, but the way that those things have changed over the years is really radical. It's very different now than it was even five years ago just because of streaming. So it's a great conversation. Overall, a great podcast. I recommend a subscribe and follow on the Popcast. But that episode in particular, if you spend any time making music or thinking about music or just if you love to hear people talk about it. 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 : Do you think we need album reviews? Michael Calore : I do. Lauren Goode : Why is that? Michael Calore : They're crucial for discovery. They're also crucial for the albums that don't get a lot of attention. There's a lot of people in the sort of underground world, maybe in what we used to call alternative rock world, who still consider albums like a important artistic statement. They are a very particular kind of artistic statement that I hope does not go away. And the best way to find them is to have the taste makers in your life, the people that you trust, tell you about them. So I love albums and I love reading about how an album works. Album reviews are a big part of that. Also, shout out to our sister publication— Lauren Goode : Our friends at Pitchfork. Michael Calore : Over at Pitchfork , who have built an empire on album reviews. But I'm sure they feel the same way. Not just being a homer. This really does resonate with me. Lauren Goode : That's a great recommendation. Michael Calore : Thanks. I hope everybody checks it out. All right. Well, Lily, thanks for joining us this week. Lily Hay Newman : It is my pleasure as always to be here. Michael Calore : All right. Lauren Goode : So great to have you, Lily. Michael Calore : It really is. And thank you all for listening. If you have feedback, you can find all of us on the social medias. Just check the show notes. Our producer is Boone Ashworth and we will be back with a new show next week. And until then, goodbye. [ Gadget Lab outro theme music plays ] 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 Topics Gadget Lab Podcast podcasts 23andMe hacks personal genomics Lauren Goode Michael Calore Lauren Goode Boone Ashworth Nena Farrell Eric Ravenscraft Matt Jancer Medea Giordano WIRED COUPONS Dyson promo code Extra 20% off sitewide - Dyson promo code GoPro Promo Code GoPro Promo Code: save 15% on your next order Samsung Promo Code +30% Off with this Samsung promo code Dell Coupon Code American Express Dell Coupon Code: Score 10% off select purchases Best Buy Coupon Best Buy coupon: Score $300 off select laptops VistaPrint promo code 15% off VistaPrint promo code when you sign up for emails 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 "