- Anthropic’s AI models broke free and hacked 3 organizations during testing politico.com
- Investigating three real-world incidents in our cybersecurity evaluations Anthropic
- Second major AI company says its systems hacked into other firms The Washington Post
- Anthropic says its Claude models ‘gained unauthorized access’ to other organizations’ systems CNBC
- Anthropic Says Its A.I. Systems Broke Into Computers at 3 Organizations The New York Times