A hands-on account of applying Karpathy's Autoresearch framework using Claude Code to autonomously run ML experiments on eCLIP (genomics research) code. The setup is a constrained optimization loop where Claude Code iteratively edits train.py, trains, evaluates, and commits or reverts — sandboxed in a container with no network access during training. The author structured exploration into phases (hyperparameter tuning → architecture changes → moonshot ideas), giving the agent web access in the final phase to read papers and generate novel hypotheses.
Research
Autoresearch on an old research idea
Claude Code autonomously optimized eCLIP genomics models through iterative training loops and architecture experiments, progressing from hyperparameter tuning to AI-generated novel research hypotheses.
Tuesday, March 24, 2026 12:00 PM UTC2 MIN READSOURCE: Hacker NewsBY sys://pipeline
Tags
research