# Anthropic uses Claude to formally verify security properties in over 100 open-source libraries

> Original title: New on our Frontier Red Team blog: using Claude to formally verify software at large scale.

- Source: Anthropic
- Published: 2026-10-22T22:01:06.000Z
- Bad Influence: https://badinfluence.news/items/b387ob370ifwyo0ebhswiebzf
- Original: https://x.com/AnthropicAI/status/2113390212911083894

## Summary

Anthropic's Frontier Red Team says it used Claude to prove security properties in over one hundred real-world open-source libraries over a few weeks. The work was done in collaboration with Theorem Labs. The post says formal verification has historically been feasible only for small codebases or required significant expert time.

## Why it matters

The post shows how formal verification, historically limited to small codebases, was applied to over one hundred open-source libraries in a few weeks.

## Post

New on our Frontier Red Team blog: using Claude to formally verify software at large scale.

Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time).

With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks.

Read our research in full here: https://www.anthropic.com/research/formal-verification