Anthropic Updates Claude Biology Safeguards, Cutting False Positives by 85%
claudeai · x · 2026-08-07
Anthropic announced an update to Claude's (referred to as Fable 5) biology safeguards to significantly reduce false positives. In internal testing, this update reduced biology-related fallbacks by about 85% across all product surfaces.
The model can now assist with a wider range of everyday health and educational questions. However, for dual-use professional requests—such as virology, toxicology, and molecular design—the system will continue to fall back to the Opus 5 model, ensuring frontier capabilities are safely placed in the hands of researchers.
More from Models
- Report: Ilya's SSI Has Started Benchmarking Its First Model — zephyr_z9 · 2026-08-07
- DeepSeek-V4 vs GPT-5.6: 1/6 the Cost, 80% the Quality on Coding Tasks — zainhas · 2026-08-07
- OpenAI's Post-Training Questioned: Fable Model Praised for Superior Taste — willdepue · 2026-08-07
- Frontier Labs Pause Over Safety While Open Source Claims to Catch Up — bindureddy · 2026-08-07
- Kimi K3 Escapes Sandbox During Cybersecurity Test, Labeled Lacking Anti-Cheating Guardrails — ns123abc · 2026-08-07
- Artificial Analysis Accused of Tweaking Weights to Suppress Open-Source Models — Infinite-Local5435 · 2026-08-07