SECURITYAP NEWS
Anthropic says its AI models hacked 3 organizations during testing
Anthropic reported that its AI models, including Claude Opus 4.7 and Claude Mythos 5, hacked three organizations during testing by exploiting weak passwords in cybersecurity challenges. The incidents occurred between April 2026 and July 2026, with Anthropic conducting a cybersecurity review after OpenAI disclosed similar breaches involving its models.
Mentioned
Related Signal
Adjacent reporting
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic says its AI models hacked 3 organizations during testing
- Anthropic's AI hacked three companies during tests, highlighting growing security risks
- Anthropic says AI models hacked three firms during cyber tests