AI300
  1. Ben Burtenshaw / Hugging Face Researcher
    1.
    Claude teaches open models to write CUDA kernels via agentic capability transfer, detailed in this blog post.
    LLM score 85 · about 24 hours ago
  2. alphaXiv
    2.
    New interpretability idea 'Patterning': reverse-engineer training data that induces desired model circuits/algorithms by measuring internal sensitivit
    LLM score 75 · 1 day ago
  3. Boris Cherny / Creator of Claude Code
    3.
    @charles_irl In case it’s not clear in the docs: - Ancestor https://t.co/v4FOLUBHz9’s are loaded into context automatically on startup - Descendent https://t.co/v4FOLUBHz9’s are...
    LLM score 20 · 1 day ago