Opus 5.5 formally verifies Claude Agent SDK in Lean, yields 16 bug-fix PRs
blaizedsouza · x · 2026-09-23
Developer bcherny shares how he 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 says he barely knows Lean or TLA+, but Claude excels at both, and he sometimes combines the two to check data flow, concurrency, and state management.
His core claim, echoed by Dominik Tornow: formal methods will be a cornerstone of agentic coding, with one rule — the agent can write the proofs, but you state the theorems. This setup catches defects a human reviewer would likely miss.
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