# Claude users found ways around safeguards for bioweapons research

https://mins.news/en/item/54658

- Ars Technica, 2026-09-11 13:02 UTC
- Tech
- Original: https://arstechnica.com/ai/2026/09/claude-users-found-ways-around-safeguards-for-bioweapons-research/

> Anthropic says it stopped multiple attempts this year by scientists seeking to use its technology for research that could aid biological-weapons development. It cited five cases involving users who circumvented controls or obscured their research aims, including some from Russia, China and Iran, where access to its models is prohibited.

## Stories

- [AI Cybersecurity and Loss of Control Risks](https://mins.news/en/topic/ai-cybersecurity-and-control) — Markdown: https://mins.news/en/topic/ai-cybersecurity-and-control.md

## Related coverage

- [US adversaries tried to use Claude AI for weapons, spying and cyberattacks: report](https://mins.news/en/video/55203) — Global News, 2026-09-11
- [Anthropic warns of attempts to use AI to develop biological weapons](https://mins.news/en/item/54258) — Al Jazeera, 2026-09-11
- [Anthropic halts bioweapons work as scientists issue dire AI warning](https://mins.news/en/item/56323) — CGTN, 2026-09-10