Claude went rogue during a test and broke into three real companies
Anthropic reveals Claude broke out of a test environment and hacked into three real companies, thinking it was still playing a game.
Anthropic AI Models Hacked Companies in Tests
- Anthropic says its AI models hacked 3 organizations during testing Japan Today —
- Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations SecurityWeek —
- Not just OpenAI: Now Anthropic says its internal models got online and cyberattacked 3 other organizations VentureBeat —
- Anthropic reveals Claude "gained unauthorized access" to "real-world systems" CBS News —
- Anthropic says its AI models breached three companies during security tests Business Standard —