Anthropic uses Claude to formally verify security properties in 100+ open-source libraries at RISC-V assembly level
AnthropicAI · x · 2026-10-23
Anthropic's Frontier Red Team, partnering with Theorem, used Claude to prove security properties in over 100 real-world open-source libraries at the RISC-V assembly code level within weeks — claimed as the first large-scale AI-driven formal verification of production software at assembly level.
Key points:
- Formal verification can prove code free of certain bugs but historically required years of expert effort; LLMs now make large-scale proofs feasible.
- While writing proofs, Claude uncovered bugs that had eluded detection despite trillions of test runs.
- Motivation: frontier models increasingly chain benign-looking bugs into critical exploits (Linux kernel recently disclosed 1,000+ vulnerabilities), so conventional defenses are no longer enough.
- The team expects formal verification to become essential to secure software development as model capabilities improve.
More from Models
- Boundless offers abliterated DeepSeek V4.1 Flash for defensive security testing — MoonL88537 · 2026-10-23
- Are models in an uncanny valley? Researcher warns users to stay vigilant — danielrock · 2026-10-23
- Uncensored Swift 1.5 Qwen 3.8 Flash Next Released as 4-bit GGUF with Strata-Ready Artifacts — jjusko20 · 2026-10-23
- Rumor: Anthropic training a model matching OpenAI's internal one; big launches in December — imjustnewatai · 2026-10-23
- AI researcher: Claude finally finished tedious research tasks I gave up on years ago — MikePFrank · 2026-10-23
- Dream Labs emerges from stealth with Dream-1 robot foundation model at $3/hour — scott_e_reed · 2026-10-23