AI300
  1. Cameron Wolfe / Researcher at Netflix
    1.
    Trinity large is very sparse (400B-A13B, 256 experts w/ 4 active per token).›
    LLM score 85 · about 7 hours ago
  2. Ben Burtenshaw / Hugging Face Researcher
    2.
    We got Claude to teach open models how to write CUDA kernels.›
    LLM score 85 · about 24 hours ago
  3. alphaXiv
    3.
    BIG new idea in interpretability called Patterning›
    LLM score 75 · 1 day ago
  4. Boris Cherny / Creator of Claude Code
    4.
    @charles_irl In case it’s not clear in the docs: - Ancestor https://t.co/v4FOLUBHz9’s are loaded into context automatically on startup›
    LLM score 20 · 1 day ago
  5. alphaXiv
    5.
    "LLM-in-Sandbox Elicits General Agentic Intelligence"›
    LLM score 85 · 1 day ago
  6. Ethan Shen / Ai2 Researcher
    6.
    @unsorsodicorda @saurabh_shah2 @Tim_Dettmers GA is trained using 4.5 Air as the teacher, whereas SERA-32B uses GLM 4.6.›
    LLM score 85 · 1 day ago
  7. Tim Dettmers / Research Scientist at Ai2
    7.
    his work was mostly the genius of Ethan Shen.›
    LLM score 70 · 2 days ago
  8. Tim Dettmers / Research Scientist at Ai2
    8.
    Our method became so efficient (26x vs RL; 57x vs other synth gen), that we could easily generate 1000s of trajectories for a single repo.›
    LLM score 85 · 2 days ago
  9. Tim Dettmers / Research Scientist at Ai2
    9.
    This is very impactful: you can now distill frontier performance into small models that are specialized to private repositories.›
    LLM score 75 · 2 days ago
  10. Tim Dettmers / Research Scientist at Ai2
    10.
    From there we could do a massiv amounts of experiments and really understand what matters for training coding agents.›
    LLM score 80 · 2 days ago
  11. Cameron Wolfe / Researcher at Netflix
    11.
    Continual learning is a popular topic in LLM research, but it might not be as far away as we think.›
    LLM score 65 · 2 days ago
  12. Ethan Shen / Ai2 Researcher
    12.
    Finally, we conduct an analysis of variance across SWE-Bench runs.›
    LLM score 95 · 2 days ago
  13. Ethan Shen / Ai2 Researcher
    13.
    We also experiment with mixing data from rollouts and discover that training on SERA’s first and second rollouts complement each other to increase performance in data constrained regimes.›
    LLM score 85 · 2 days ago
  14. Ethan Shen / Ai2 Researcher
    14.
    Even more interesting is the fact that the best data comes from truncated trajectories that just barely exceed the context limit.›
    LLM score 85 · 2 days ago
  15. Niklas Muennighoff / AI Researcher at Stanford
    15.
    Community-built open benchmarks work really well, e.g., Terminal-Bench, HLE, MMTEB.›
    LLM score 80 · 2 days ago
  16. Noam Brown / OpenAI Research Scientist
    16.
    Had to cut this one for space: 2019: AI can't create art—creativity is uniquely human
    LLM score 20 · 3 days ago
  17. Andrej Karpathy / AI researcher
    17.
    @0xabi96 It feels like I’m cheating.›
    LLM score 70 · 3 days ago
  18. Andrej Karpathy / AI researcher
    18.
    @ChiragLathiya The nearest neighbor really is some kind of a junior engineer.›
    LLM score 80 · 3 days ago
  19. Andrej Karpathy / AI researcher
    19.
    @jeremytwei Love the word "comprehension debt", haven't encountered it so far, it's very accurate.›
    LLM score 30 · 3 days ago
  20. Andrej Karpathy / AI researcher
    20.
    @airesearch12 💯 @ Spec-driven development It's the limit of imperative -> declarative transition, basically being declarative entirely.›
    LLM score 60 · 3 days ago
  21. Andrej Karpathy / AI researcher
    21.
    A few random notes from claude coding quite a bit last few weeks.›
    LLM score 20 · 3 days ago
  22. Noam Brown / OpenAI Research Scientist
    22.
    1987: AI can't win at chess—planning is uniquely human›
    LLM score 70 · 3 days ago
  23. Yoshua Bengio
    23.
    Had a great discussion on AI's major societal impacts and emerging risks on the @RestIsPolitics podcast this past November.›
    LLM score 20 · 3 days ago
  24. Jonathan Ross / TPU Creator
    24.
    Success in the Information Age was about being able to answer questions.›
    LLM score 20 · 3 days ago
  25. Ben Burtenshaw / Hugging Face Researcher
    25.
    this is a blog post on claude + llama.cpp https://t.co/yej6WsNnQA
    LLM score 20 · 3 days ago
  26. Yoshua Bengio
    26.
    Merci à @HugoDecrypte pour l'invitation à faire un tour d'horizon des risques de l'IA ainsi que des solutions nécessaires pour se diriger vers une meilleure trajectoire.›
    LLM score 20 · 3 days ago
  27. Ben Burtenshaw / Hugging Face Researcher
    27.
    I know it's massively off trend, but I love setting up a nice quiver of models in @cursor_ai, reviewing generated tokens in the legit ui, switching models for certain parts, and just generally getting shit done.›
    LLM score 30 · 3 days ago
  28. Ronak Malde / DeepMind Researcher
    28.
    I don't think people have realized how crazy the results are from this new TTT + RL paper from Stanford/Nvidia.›
    LLM score 85 · 3 days ago
  29. Cameron Wolfe / Researcher at Netflix
    29.
    Continual learning is being positioned as a prerequisite for AGI (i.e., general systems must be adaptable).›
    LLM score 70 · 4 days ago
  30. Geoffrey Hinton
    30.
    I just watched a really great conversation about the future of AI.›
    LLM score 30 · 4 days ago
More