Formally verifying the Claude Agent SDK with Lean yields 16 bug-fix PRs from a few prompts
dyn___ · x · 2026-09-24
@bcherny describes using Claude (Opus) with the Lean theorem prover to formally verify the Claude Agent SDK: a couple of short prompts produced 16 PRs fixing bugs and race conditions.
He notes TLA+ works well too, and he often combines Lean and TLA+ to probe data flow, concurrency, and state management issues — despite not knowing either language deeply. He also cautions that without language expertise, a safer claim is 'somewhere between better than me and probably decent — building an eval.'
More from coding & agent
- User automates entire video clipping workflow with Nous Research's Hermes agent — Teknium · 2026-11-12
- As models improve, writing good evals gets harder and more important — amankhan · 2026-11-12
- Prime agent ships with day-one multi-agent communication, runs in Minecraft unmodified — sarahcat21 · 2026-11-12
- Autonomous agent edits just 1,024 weights to lift Qwen3.5 0.8B from 7.4% to 37.4% on MATH-500 — VictorSanh · 2026-11-12
- Omarchy 4.6 lets you share local AI models across your tailnet, says DHH — alexcovo_eth · 2026-11-12
- Coding harnesses hand shell access to inference providers — 4-step gateway mitigation — shensi · 2026-11-12