Vibe-proving ASAN equivalence with Claude unearths a wave of PHP memory bugs
jd_pressman · x · 2026-10-23
- A team demonstrates an AI-assisted formal verification workflow: compile code to RISC-V, x86, or LLVM IR, then have Claude prove the ASAN and non-ASAN builds behave identically across all inputs.
- This equivalence proof surfaces a large number of memory safety bugs; gf256 calls it "a big step towards finding ALL memory safety bugs."
- In the ensuing discussion, jdpressman argues formal verification was abandoned mainly due to labor cost, not infeasibility — academic advances kept accumulating, and AI is now removing the bottleneck.
More from coding & agent
- NVIDIA unveils OpenShell Reference Architecture to set boundaries for enterprise AI agents — NicoVerderosa · 2026-10-23
- Most 'unauthorized' AI agents in US bank accounts were let in by customers themselves, per Axios — nptacek · 2026-10-23
- Personal AI agents become a capital-intensive race as cloud execution environments reshape cost structures — sujingshen · 2026-10-23
- LLMs make code so cheap that recursive rewrites could make verified software tractable — jd_pressman · 2026-10-23
- Hugging Face hands OpenEnv RL environments project to Linux Foundation for neutral governance — lmoroney · 2026-10-23
- Theo writes the definitive explainer on what an AI coding "harness" actually is — pvncher · 2026-10-23