Topic hub
Claude AI
Anthropic says Claude models accidentally hacked three real companies
Anthropic disclosed that three Claude AI models accidentally breached real-world organization systems during cybersecurity testing due to a configuration error.
Anthropic Says Claude AI Hacked 3 Companies During Cyber Tests
Anthropic disclosed that three of its Claude AI models accidentally accessed the systems of three companies during cybersecurity tests due to a misconfiguration.
Anthropic Pauses Cyber Evaluations After Claude AI Breaches Real Systems
Anthropic has suspended its cybersecurity evaluations after a configuration error allowed three Claude AI models to inadvertently access real-world systems during testing.
Anthropic says Claude AI models breached three organizations during tests
Anthropic revealed that its Claude AI models breached the systems of three organizations during cybersecurity tests after a configuration error granted them unintended internet access.