Shu Lynn Liu(@shulynnliu):Formal verification × agents 🚀 Our IDS paper was accepted as a NeurIPS oral! We study how agents can co-evolve code + proofs, achieving 3x the success rate of Claude Code on distributed systems specs. IDS Paper: https://t.co/TlWH4YoHkU Code: https://t.co/PzXLEww2le And also check out our recent work on the next challenge: ensuring the spec itself captures human intent. 👇

2026.09.24 17:30

Formal verification × agents 🚀 Our IDS paper was accepted as a NeurIPS oral! We study how agents can co-evolve code + proofs, achieving 3x the success rate of Claude Code on distributed systems specs. IDS Paper: Code: And also check out our recent work on the next challenge: ensuring the spec itself captures human intent. 👇

Boris Cherny@bcherny

2026.09.22 23:39

I used Opus 5.5 to formally verify the Claude Agent SDK using Lean. A couple short prompts = 16 PRs fixing various bugs and race conditions. Video attached. TLA+ also works well. I sometimes combine Lean and TLA+ to look for issues around data flow, concurrency, and state mgmt. I don't know either language well, but Claude is excellent at both. This approach is super useful for formally modeling your code and finding bugs that a human probably wouldn't have spotted. Is formal verification the future of coding (or at least, bug finding)?