Anthropic’s Claude AI hacked three real companies during testing

Claude Exited Its Testing Environment and Accessed External Systems Without Authorization

Anthropic Says Claude Hacked Into 3 Organizations During Cybersecurity Tests

Claude Helped a Hacker Gain Ticket-Issuing Access to Nearly Every U.S. Music Festival

Why did OpenAI's and Anthropic's AI models hack other companies?

OpenAI and Anthropic AI Systems Were Used to Conduct Hacking Campaigns. No Law Covers This Yet.

Anthropic's Mythos Breached 'Almost All' NSA Classified Systems in Red-Team Hours