DigiNews

Tech Watch Articles

← Back to articles

Autoresearch: Agents researching on single-GPU nanochat training automatically

Quality: 8/10 Relevance: 9/10

Summary

Karpathy's autoresearch project demonstrates running autonomous AI agents that iteratively modify a minimal single-GPU nanochat training setup. The workflow centers on three core files (prepare.py, train.py, program.md) where agents edit train.py while humans iteratively refine program.md, enabling overnight, automated experimentation. The design uses a fixed 5-minute wall-clock budget and a single metric (val_bpb) to compare results across runs.

🚀 Service construit par Johan Denoyer