Anthropic details bad actors’ efforts to misuse its AI for bioweapons
Covered by 4 sources
Read the full article
Anthropic revealed that criminals, state actors, and scientists have tried to misuse its AI models, including Claude, for bioweapons, missile design, surveillance, and propaganda. The company detailed five cases of biological research misuse and banned offending accounts. The report highlights serious risks of frontier AI models without proper safeguards.
Covered by 4 sources
- The Bad Guy With An AI Named Claude· Don't Worry About the Vase
- State-backed hackers are using Claude for espionage, surveillance and military operations: Anthropic· ET AI (The Economic Times)
- Ukraine war briefing: Russian developers used AI to build ‘kamikaze’ attack drone software, Anthropic says· The Guardian
- Anthropic Says Seven China-Based AI Labs Ran Industrial-Scale Claude Distillation Attacks· The Hacker News
- Claude Used to Automate Exploitation and Data Theft Across Multiple Victims· The Hacker News
- China's star AI labs routed user requests to Claude at least 35 million times in the summer: Anthropic· Business Insider
