Claude Finds Bugs that Survived Trillions of Software Test Runs
4 Articles
4 Articles
Anthropic's Claude now writes code and proves it safe automatically
Anthropic had Claude generate mathematical proofs that existing code is correct, producing roughly 180 million lines of proof code for 123 open-source libraries. Along the way, the model caught bugs that years of testing had missed. Anthropic's goal: making formal verification with AI as routine as standard testing. The article Anthropic's Claude now writes code and proves it safe automatically appeared first on The Decoder.
Anthropic argues that Claude helped verify security properties in 123 open source libraries in a few weeks, a work that could traditionally require years of specialists. The initiative aims to expand access to mathematical security tests, although its results depend on which properties are defined and the possibility of reproducing the process.
Coverage Details
Bias Distribution
- 100% of the sources are Center
Factuality
To view factuality data please Upgrade to Premium
