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.
More from Safety
- Outsider with no GitHub role deleted Dodo Payments' private repo, audit log shows — kingslyj · 2026-10-28
- OpenAI researcher: frontier AI ideas can't be patched for safety after the fact — willdepue · 2026-10-28
- Altman: models will find bugs 'outside the normal threat model' and patching won't save us — wfithian · 2026-10-28
- Report claims Anthropic Slack breach gave attackers full admin access to research secrets — willdepue · 2026-10-28
- Codex scans your connectors/MCPs unprompted in the background, and you can't tell — kenziyuliu · 2026-10-28
- Claude analysis flags TikTok and Instagram for allegedly bypassing mic permissions — thunderbong · 2026-10-28