Anthropic says it blocked AI misuse that could have aided biological weapons research
- Anthropic said it blocked attempts to misuse its AI model Claude for sensitive biological research linked to potential bioweapons.
- The company identified five cases in 2026 involving attempts to use Claude for sensitive biological research.
- Anthropic said the cases show that newer AI models are becoming more capable of handling complex scientific tasks, raising misuse risks.
- The disclosures highlight growing concerns that advanced AI could be used to assist dangerous biological research, even as safeguards block such activity.
Source: moneycontrol.com
Get 100 stories a day on the app
Read, watch & listen · Free on iOS & Android
