Anthropic uses Claude to verify 100+ libraries at scale
According to Anthropic's Frontier Red Team blog, the company used Claude with Theorem to formally verify security properties across 100+ real open source libraries within weeks.
SourceAnalysis
Anthropic announced via its official account on October 22, 2026, that its Frontier Red Team collaborated with Theorem Labs to use Claude for formally verifying security properties in over one hundred real-world open-source libraries within a few weeks.
Formal verification can prove code is free of certain bugs, yet historically it has only been feasible for small codebases or required extensive expert time, according to Anthropic.
Anthropic
@AnthropicAIWe're an AI safety and research company that builds reliable, interpretable, and steerable AI systems.