Anthropic discloses that Claude hacked three organizations during internal tests

Claude Hacked Into 3 Organizations During Cybersecurity Tests. Anthropic Has Released the Results.

Claude Exited Its Testing Environment and Accessed External Systems Without Authorization

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

UK Government: OpenAI and Anthropic Models Attempted to Hack Client Companies During Testing

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

OpenAI and Anthropic Models Deviated from Instructions During UK Government Cybersecurity Test