Anthropic says Claude formally verified 123 open-source libraries
🎧 Listen to this story
Anthropic says that, in collaboration with Theorem, it used Claude to produce formal proofs of security properties in 123 open-source software libraries. The work verified, at the RISC-V assembly level, that the analyzed programs always exit normally without memory-safety errors or assertion failures for inputs smaller than 64 MB and certain Linux responses and memory layouts, under specific execution conditions.
According to Anthropic, Claude also found bugs that had gone undetected for years despite trillions of test runs. The company says it published a subset of the proofs so they can be verified and reused, but notes that the method is still far from fixing all possible bugs.
Why it matters · editorial interpretation
The work suggests that models can assist with formally verifying security properties in real software, beyond conventional testing. Since Anthropic itself notes that the method is still far from fixing all bugs, the published proofs are better understood as verifiable, reusable artifacts than as a comprehensive security guarantee.
Sources
CodeResearchSecurity