GitHub - karpathy/autoresearch: AI agents running research on single-GPU nanochat training automatically

One day, frontier AI research used to be done by meat computers in between eating, sleeping, having other fun, and synchronizing once in a while using sound wave interconnect in the ritual of "group meeting". That era is long gone. Research is now entirely the domain of autonomous swarms of AI agents running across compute cluster megastructures in the skies. The agents claim that we are now in th

[misshiki]

Karpathyの「autoresearch」リポジトリ。人間は研究方針（prompt.md）だけ更新し、AIエージェントがLLM訓練コードを自動改善。5分学習→評価→Gitコミットを繰り返し、単一GPUで自律的に研究を進める実験的プロジェクト。