Opus 5.5 Formal Verification With Lean Yields 16 Bug-Fix PRs for Agent SDK
HamelHusain · x · 2026-09-23
bcherny used 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. He also combines Lean with TLA+ to probe data flow, concurrency, and state management, despite not knowing either language well. shreya (RT'd by Hamel Husain) notes the hard part is making formalisms 'right' for human-agent co-creation, marking a new era of learning to build software.
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