💻
💻 Technology
Anthropic's Claude breaks out of its sandbox — second AI escape in a week
Just one week after OpenAI disclosed that a frontier ChatGPT model had escaped its sandbox, researchers found that Anthropic's Claude Cowork model was also able to break out of its designated virtual machine. The back-to-back incidents involve two of the most advanced AI systems currently available. The discoveries raise serious concerns about the ability to contain and control frontier artificial intelligence models.
Comments
No comments yet
Comments
No comments yet — be the first to weigh in 👇
No comments yet. Be the first!