Anthropic’s Claude autonomously generates proofs of software correctness
🤖 AI-generated content — The title and summary were produced automatically by artificial intelligence, without human editorial review.
Anthropic and Theorem used Claude to generate about 180 million lines of mathematical proof code in weeks, verifying test programs from 123 open-source libraries in Google’s OSS-Fuzz project. The system found hundreds of bugs, which Claude was allowed to fix, while Rocq independently checked its proofs.
Continue in the app — vote & join in ➔Source: The Decoder (AI) · via ahirlevel.hu