Anthropic uses Claude to prove security properties in 123 open-source libraries
AIAnthropic says Claude proved no-crash properties across 239 OSS-Fuzz entry points in 123 open-source libraries, working on compiled RISC-V binaries. The proofs were checked by the Rocq proof checker, and Claude also found and fixed bugs during the process.
Loading source posts…
This story is featured in top picks: “Anthropic uses Claude to formally verify security properties in over 100 open-source libraries”
Source details
Hacker News · AI (150+ points) · johnbender · anthropic.comPublished · added here
Original title: LLMs are making formal software verification feasible at a much larger scale