1 comment

[ 3.2 ms ] story [ 16.0 ms ] thread
Karpathy released autoresearch last week. 31,000 stars. 100 ML experiments overnight on one GPU.

Everyone wrote about the ML training loop. I saw something different: a pattern.

One file. One metric. One loop. Modify → Evaluate → Keep or Discard → Repeat.

That pattern has nothing to do with machine learning.

So I built a skill that applies it to: → API response time (benchmark_speed evaluator) → Bundle size (benchmark_size evaluator) → Headline click-through (LLM judge evaluator) → System prompt quality (LLM judge evaluator) → Test pass rate, build speed, memory usage

Works across 11 tools: Claude Code, Codex, Gemini CLI, Cursor, Windsurf, OpenClaw, and more.

The hardest problem: evaluating things that are not numbers. Headlines do not come with a val_bpb metric.

Solution: LLM judges using the agent's own subscription. Critical constraint: the agent cannot modify its own evaluator. (The alignment problem in miniature.)

What I have not done yet: run 100 experiments overnight. The skill shipped this week. The architecture is solid. The validation is ahead of me.

Full architecture + honest limitations: https://github.com/alirezarezvani/claude-skills/tree/main/en...

What manual optimization loop are you running that should be automated?