Formally verifying the Claude Agent SDK with Lean via Opus 5.5 yields 16 bug-fix PRs
hargup13 · x · 2026-09-23
- A developer used Claude Opus 5.5 to formally verify the Claude Agent SDK in Lean: a couple of short prompts produced 16 PRs fixing various bugs and race conditions.
- He doesn't know either language well, but Claude excels at both; TLA+ also works well, and he sometimes combines Lean and TLA+ to probe data flow, concurrency, and state management.
- His takeaway: formal modeling surfaces bugs humans wouldn't spot, and formal verification may be the future of coding — at least of bug finding.
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