Verifying the Claude Agent SDK with Opus 5.5 and Lean yields 16 bug-fixing PRs
TIME · x · 2026-09-23
Developer bcherny used Claude Opus 5.5 to formally verify the Claude Agent SDK in Lean: a couple of short prompts produced 16 PRs fixing bugs and race conditions.
- TLA+ also works well; combining Lean and TLA+ helps surface data-flow, concurrency, and state-management issues
- The author knows neither language well, but Claude excels at both
- The approach is useful for formally modeling your code and finding bugs a human reviewer would likely miss
The reposter adds: formal verification is the future of coding, and the old bottleneck — formally expressing intent in languages like Lean — is gone with frontier models.
More from coding & agent
- As models improve, writing good evals gets harder and more important — amankhan · 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
- Slack's David Hoang: agents beat people on coordination, proposes 'boundary agents' — davidhoang · 2026-11-12
- CS student mourns coding flow states he'll never experience in the AI era — chrissyykat · 2026-11-12
- AI Engineer Code Summit features its first all-female keynote lineup — altryne · 2026-11-12