AIHacker Newsabout 2 hours ago
Claude Proves Security for 100 Libraries
16 min read
Researchers collaborated with Theorem to use Claude for formal software verification at scale. The team proved security properties for over 100 open-source libraries at the assembly code level using RISC-V. While writing proofs, the AI discovered bugs that had eluded detection for years despite trillions of test runs.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyAnthropic
