AIThe Decoder2h ago
Anthropic's Claude now writes code and proves it safe automatically
TL;DRClaude generated proofs that code is correct and found bugs human testers missed.
Why it matters: Automated formal verification could catch critical bugs before deployment, improving software security and reliability at scale.
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…
Read full articleSource: The Decoder · Opens in new tab