Formally verifying the Claude Agent SDK with Lean via Opus yields 16 bug-fix PRs
jfiance · x · 2026-09-24
Boris Cherny used Opus 5.5 to formally verify the Claude Agent SDK with Lean: a couple of short prompts produced 16 PRs fixing bugs and race conditions. He also pairs Lean with TLA+ to probe data flow, concurrency, and state management, noting Claude excels at both languages despite him not knowing them well. The reposter calls it the clearest case yet that formal verification is now a practical engineering tool, with the loop running on production engines.
More from coding & agent
- Boubou: open-source CLI turns your laptop into a fully local voice AI hub — alexcovo_eth · 2026-11-12
- 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