Anthropic Says It Blocked Scientist Plots That Could Have Aided Bioweapons Research
harris_edouard · x · 2026-09-11
The New York Times reports that Anthropic, in a new misuse report, says it disrupted several potential plots this year in which scientists used its AI models (including Claude) for research that could have helped develop biological weapons.
- The company could not determine whether the work was legitimate biological inquiry or nefarious, since the same techniques can lead to breakthroughs like vaccines or dangerous pathogens
- Facing that ambiguity, Anthropic shut the work down out of caution, said threat intelligence head Jacob Klein
- The report catalogs a range of misuses of its models over the past eight months
More from Safety
- Prompt turns Claude Code into an iPhone backup forensics tool exposing 30-day 'deleted' photo copies — alex_verem · 2026-10-27
- Anthropic reveals it bans customers worth 5-7% of revenue every 9 months — Polymarket · 2026-10-27
- AVERI independently audits Amazon's internal AI safety evals in landmark pilot — Miles_Brundage · 2026-10-27
- US chases AGI dominance while China, EU and ASEAN treat AI as public infrastructure — BubblyExtent1693 · 2026-10-27
- Agent Field Kit launches $29 security runbooks for production AI agents — alvelda · 2026-10-27
- DeepSeek Safety Eval Finds "Over-Attribution": Model Mistakes Ordinary Tasks for Tests — Much_Boysenberry9124 · 2026-10-27