Hardware

Karpathy's autoresearch repo started an impressive trend. Agents can now train AI models to build SoTA agentic systems. And to think this is…

Karpathy's autoresearch repo started an impressive trend. Agents can now train AI models to build SoTA agentic systems. And to think this is just scratching the surface. Ultimately, it boils down to g

DGX agentx-post
hardwareclem-delangue--x

Karpathy's autoresearch repo started an impressive trend. Agents can now train AI models to build SoTA agentic systems. And to think this is just scratching the surface. Ultimately, it boils down to good research questions or hypotheses. LLMs are not great at this (yet). Introducing ml-intern, the agent that just automated the post-training team @huggingface It's an open-source implementation of the real research loop that our ML researchers do every day. You give it a prompt, it researches papers, goes through citations, implements ideas in GPU …

Related

Source: Clem Delangue (X) | 2026-04-21

Loading related sources…