Hugging Face's logo

Smol Community

community
s3nh
Activity Feed Request to join this org

AI & ML interests

The SmolTuners group is a community dedicated to the development of small-scale Large Language Models (LLMs) using consumer-grade GPUs.

Recent Activity

s3nh  new activity 19 days ago
SmolTuners/README:Gh organization
AnA202  new activity 20 days ago
SmolTuners/README:Gh organization
TheDrunkenSnail  new activity about 1 month ago
SmolTuners/README:Gh organization
View all activity

SmolTuners's activity

rubenroy 
posted an update 2 days ago
KnutJaegersberg 
posted an update 3 days ago
view post
Post
749
Anthropomorphic reasoning about neuromorphic AGI safety

Summary of "Anthropomorphic Reasoning About Neuromorphic AGI Safety"
This paper explores safety strategies for neuromorphic artificial general intelligence (AGI), defined as systems designed by reverse-engineering essential computations of the human brain. Key arguments and proposals include:

1. Anthropomorphic Reasoning Validity:
- Neuromorphic AGI’s design and assessment rely on human cognition models, making anthropomorphic reasoning (using human-like traits) critical for safety analysis. Comparisons to human behavior and neural mechanisms provide insights into AGI behavior and risks.

2. Countering Safety Criticisms:
- The authors challenge claims that neuromorphic AGI is inherently more dangerous than other AGI approaches. They argue all AGI systems face intractable verification challenges (e.g., real-world unpredictability, incomputable action validation). Neuromorphic AGI may even offer safety advantages by enabling comparisons to human cognitive processes.

3. Motivational Architecture:
- Basic drives (e.g., curiosity, social interaction) are essential for cognitive development and safety. These pre-conceptual, hardwired drives (analogous to human hunger or affiliation) shape learning and behavior. The orthogonality thesis (intelligence and goals as independent) is contested, as neuromorphic AGI’s drives likely intertwine with its cognitive architecture.

4. Safety Strategies:
- **Social Drives**: Embedding drives like caregiving, affiliation, and cooperation ensures AGI develops prosocial values through human interaction.
- **Bounded Reward Systems**: Human-like satiation mechanisms (e.g., diminishing rewards after fulfillment) prevent extreme behaviors (e.g., paperclip maximization).
- **Developmental Environment**: Exposure to diverse, positive human interactions and moral examples fosters

https://ccnlab.org/papers/JilkHerdReadEtAl17.pdf
KnutJaegersberg 
posted an update 7 days ago
view post
Post
1821
Evolution and The Knightian Blindspot of Machine Learning


The paper discusses machine learning's limitations in addressing Knightian Uncertainty (KU), highlighting the fragility of models like reinforcement learning (RL) in unpredictable, open-world environments. KU refers to uncertainty that can't be quantified or predicted, a challenge that RL fails to handle due to its reliance on fixed data distributions and limited formalisms.


### Key Approaches:

1. **Artificial Life (ALife):** Simulating diverse, evolving systems to generate adaptability, mimicking biological evolution's robustness to unpredictable environments.

2. **Open-Endedness:** Creating AI systems capable of continuous innovation and adaptation, drawing inspiration from human creativity and scientific discovery.

3. **Revising RL Formalisms:** Modifying reinforcement learning (RL) models to handle dynamic, open-world environments by integrating more flexible assumptions and evolutionary strategies.

These approaches aim to address ML’s limitations in real-world uncertainty and move toward more adaptive, general intelligence.

https://arxiv.org/abs/2501.13075
KnutJaegersberg 
posted an update 9 days ago
view post
Post
2037
Artificial Kuramoto Oscillatory Neurons

Artificial Kuramoto Oscillatory Neurons (AKOrN) differ from traditional artificial neurons by oscillating, rather than just turning on or off. Each neuron is represented by a rotating vector on a sphere, influenced by its connections to other neurons. This behavior is based on the Kuramoto model, which describes how oscillators (like neurons) tend to synchronize, similar to pendulums swinging in unison.

Key points:

Oscillating Neurons: Each AKOrN’s rotation is influenced by its connections, and they try to synchronize or oppose each other.
Synchronization: When neurons synchronize, they "bind," allowing the network to represent complex concepts (e.g., "a blue square toy") by compressing information.
Updating Mechanism: Neurons update their rotations based on connected neurons, input stimuli, and their natural frequency, using a Kuramoto update formula.
Network Structure: AKOrNs can be used in various network layers, with iterative blocks combining Kuramoto layers and feature extraction modules.
Reasoning: This model can perform reasoning tasks, like solving Sudoku puzzles, by adjusting neuron interactions.
Advantages: AKOrNs offer robust feature binding, reasoning capabilities, resistance to adversarial data, and well-calibrated uncertainty estimation.
In summary, AKOrN's oscillatory neurons and synchronization mechanisms enable the network to learn, reason, and handle complex tasks like image classification and object discovery with enhanced robustness and flexibility.

yt
https://www.youtube.com/watch?v=i3fRf6fb9ZM
paper
https://arxiv.org/html/2410.13821v1
  • 2 replies
·
KnutJaegersberg 
posted an update 10 days ago
KnutJaegersberg 
posted an update 14 days ago
KnutJaegersberg 
posted an update 15 days ago
view post
Post
1764
Understanding and Benchmarking Artificial Intelligence: OpenAI's o3 Is Not AGI

It's an interesting paper that argues "new approaches are required that can reliably solve a wide variety of problems without existing skills."
"It is therefore hoped that the benchmark outlined in this article contributes to further exploration of this direction of research and incentivises the development of new AGI approaches that focus on intelligence rather than skills."

https://arxiv.org/abs/2501.07458
s3nh 
in SmolTuners/README 19 days ago

Gh organization

8
#3 opened about 1 month ago by
s3nh
AnA202 
in SmolTuners/README 20 days ago

Gh organization

8
#3 opened about 1 month ago by
s3nh
KnutJaegersberg 
posted an update 21 days ago
TheDrunkenSnail 
in SmolTuners/README about 1 month ago

Gh organization

8
#3 opened about 1 month ago by
s3nh
CaioXapelaum 
in SmolTuners/README about 1 month ago

Gh organization

8
#3 opened about 1 month ago by
s3nh
s3nh 
updated a Space about 1 month ago
Delta-Vector 
in SmolTuners/README about 1 month ago

Gh organization

8
#3 opened about 1 month ago by
s3nh
s3nh 
in SmolTuners/README about 1 month ago

Optimizers
#2 opened about 1 month ago by
s3nh

Datasets

3
#1 opened about 2 months ago by
s3nh
Delta-Vector 
in SmolTuners/README about 1 month ago

Datasets

3
#1 opened about 2 months ago by
s3nh
KnutJaegersberg 
posted an update about 2 months ago
s3nh 
posted an update about 2 months ago
view post
Post
1831
Welcome back,

Small Language Models Enthusiasts and GPU Poor oss enjoyers lets connect.
Just created an organization which main target is to have fun with smaller models tuneable on consumer range GPUs, feel free to join and lets have some fun, much love ;3

https://huggingface.co/SmolTuners
·
KnutJaegersberg 
posted an update about 2 months ago