Anthropic uses Claude to prove security properties in 123 open-source libraries

The Frontier Red Team says AI can now handle formal verification at the assembly level, a task that once took experts years Anthropic says its Claude models have verified security properties across 123 open-source libraries. The work took a few weeks. That timeline matters because formal verification, the method behind it, has historically demanded years of specialist effort per project. Compressing that into weeks changes who can actually afford mathematical proof that their code behaves. The research comes from Anthropic’s Frontier Red Team, working with a firm called Theorem Labs.

Source: Crypto Briefing