Anthropic says it stopped multiple attempts to use Claude for bioweapons research

Ars Technica AI · rss · 2026-09-11

Anthropic disclosed five cases this year where users "circumvented controls" and obfuscated research purposes to evade safeguards while seeking help on research that could aid biological weapons development. Some actors were in nations Anthropic prohibits from accessing its models, including Russia, China, and Iran. The company said it hopes sharing these examples sparks a conversation within the AI industry and with governments about emerging biological risks and how best to counter them.

Original post →

More from Safety

Safety channel →