Anthropic uses Claude to formally verify 100+ open-source libraries in weeks
pzakin · x · 2026-10-24
Anthropic's Frontier Red Team blog details work with TheoremLabs using Claude to prove security properties across 100+ real-world open-source libraries in weeks. Formal verification can prove code free of certain bug classes but was historically limited to small codebases or heavy expert effort. A responder highlights the notable choice to verify directly on RISC-V binaries rather than source: easier semantics and no need to trust the compiler toolchain, but proofs become more verbose and agents lose higher-level abstractions — a good fit for memory safety, harder for general functional correctness.
More from Safety
- Python packages vulnerable to pre-auth RCE via node2shell CVE-2026-111497 through Brotli — cyb3rops · 2026-10-24
- Zvi's 'The Hackening': experts predict AI-driven internet hostility within 6-12 months — TheZvi · 2026-10-24
- OpenAI fired-researchers saga: METR terms in flux, leak accusations denied — sjgadler · 2026-10-24
- Security teams increasingly run open models via Ollama for red teaming — mchiang0610 · 2026-10-24
- France rebuilt its tax code as MLang, a formally verified open-source compiler — fkasummer · 2026-10-24
- AI cyberattacks cost $25-50 per attempt, recovery costs millions — OmarUFlorez · 2026-10-24