Anthropic updates Claude Fable 5 biology safeguards, cutting false positives by 85%

Anthropic 更新 Claude Fable 5 生物安全防护，误报率大幅降低

Anthropic rewrote the biology safety classifier for Claude Fable 5, cutting biology-related fallbacks by about 85%. Everyday health and education queries should now trigger far fewer downgrades to Opus 5. Dual-use topics like virology, toxicology, and molecular design remain blocked, so Fable 5 still isn't usable for professional biology research or drug development. The company started with near-total blocking to prevent misuse, then refined the classifier's constitution with expert feedback to carve out benign uses.

Why it matters: Anthropic published an official safety update with a concrete 85% reduction number and explained the method—experts reworked classifier rules to carve out benign use cases before retraining. It has real information for readers tracking AI safety deployment details, and it reso...