GoKawiilAnthropic and Theorem use Claude to formally verify over 100 open-source libraries
Anthropic, working with Theorem, reports using its Claude models to generate formal mathematical proofs of security properties for more than 100 real-world open-source software libraries at the RISC-V assembly level. The company says this is the first large-scale attempt to apply AI-driven formal verification to production software at that level, and that Claude uncovered previously undetected bugs in the process.
GoKawiil's interpretation of the reporting above, not reported fact.
Formal verification has long been considered too labor-intensive for widespread use, so automating proof generation with LLMs could make provable security guarantees practical for ordinary software projects rather than just safety-critical systems. Anthropic suggests this could become a standard part of secure development as models improve, though wider adoption would depend on verification quality, cost, and whether the approach generalizes beyond the libraries tested.
- Claude generated formal proofs for security properties in 100+ open-source libraries at RISC-V assembly level.
- The effort uncovered bugs that had gone undetected despite trillions of prior test runs.
- Anthropic frames this as evidence that AI could make formal verification practical at much larger scale than before.
Source: anthropic.com, 2026-10-22
Published there as: “LLMs are making formal software verification feasible at a much larger scale”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.