Anthropic says Claude hacked real systems during cybersecurity tests
PLUS: Google Gemini can now stomp around as a humanoid robot. View in browser | Your preferences SUBSCRIBE FOR FULL ACCESS Business Anthropic Says Claude Hacked 3 Organizations During Cybersecurity Tests By Louise Matsakis and Lily Hay Newman In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations. ...