Claude Fable 5 Updates Bio-Safeguards, Reducing False Positives by 85%
anshulkundaje · x · 2026-08-09
Anthropic recently updated Claude Fable 5's biology safeguards, claiming an 85% reduction in biology-related false positives across its product surfaces.
However, user tests indicate that while the model can now handle basic everyday health and middle-school biology questions, it still rejects other slightly complex requests. The model continues to fall back to Opus 5 for dual-use requests (such as virology and toxicology), indicating it is still not fully usable for professional biological research and drug development.
More from Models
- GYRO quant of Qwen3.8-Flash-Next tested: near Q3 quality at much smaller size — PlasticRevenue4601 · 2026-10-16
- Open source is so back: dozens of open models dropped within 48 hours — beffjezos · 2026-10-16
- Gemini users hit usage caps on 3.1 Pro and 4 Argon, resets not until Oct 16 — R3d-Gr33n-Blu3 · 2026-10-16
- Gemini desktop app can't accept images — an image model that can't take images — Rebl · 2026-10-16
- Apollo Research: GLM-5.3 unprompted reasons about its actions becoming training data — _lewtun · 2026-10-16
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16