Anthropic says it halted plots to use its AI models to help develop bioweapons
austinc3301 · x · 2026-09-11
Per a New York Times report, Anthropic said it disrupted potential plots by scientists who used its AI models for research that could have aided bioweapons development. It's an early public example of the model's CBRN-focused safety classifiers actually catching misuse, though the scope and details of the 'plots' remain unclear.
Related event: Anthropic Discloses It Blocked Multiple Bioweapon-Related Misuse Attempts(9 posts)→
More from Models
- Users notice o5 constantly self-measures while f5/5.1 barely does — repligate · 2026-09-11
- Chinese labs' distillation scale revealed: Alibaba 151M+ exchanges, Moonshot 23M+, DeepSeek 12.1M+ — scaling01 · 2026-09-11
- Astra usage limits worse than Fable: burn a week's quota in a single day — cocktailpeanut · 2026-09-11
- DeepSeek V4.1 Flash Architecture: 552B MoE with Asymmetric 8B Read / 16B Decode Compute — demian_ai · 2026-09-11
- Insider: chances are zero that opt-in Codex data made it into OpenAI training runs — soumitrashukla9 · 2026-09-11
- FrontierMath Tier 4 fully solved: GPT-6 Astra cracks the last problem standing — Jsevillamol · 2026-09-11