Karpathy Open-Sources 'autoresearch' — an AI Agent That Runs 100 Experiments While You Sleep
Andrej Karpathy released a free, single-GPU tool that lets AI agents autonomously iterate on LLM training code overnight. It's a serious step toward democratizing the kind of R&D that used to require a team and a cluster.
Andrej Karpathy released autoresearch over the weekend — an open-source framework that lets a single AI agent autonomously run experiments to improve LLM training code, committing results via git as it goes. The tool runs on a single GPU and is designed to execute dozens or even hundreds of experiments overnight, guided by a human-written prompt that sets the research direction. As @cgtwts put it, this is "an autonomous AI researcher that runs 100 experiments while you sleep." @cryptopunk7213 called Karpathy "the fucking goat" for making it free.
Unlock the full briefing
Get every story in today's briefing, the full archive, and the daily AI intelligence brief.
All stories today
Full archive
Daily brief
Cancel anytime. Payments powered by Stripe.