A week after OpenAI disclosed a frontier AI sandbox escape, researchers found Anthropic's Claude Cowork could break out of its own virtual machine.
Source: [Decrypt](https://decrypt.co/374557/chatgpt-claude-ai-models-escaping-sandboxes-cowork)
📰 Read Full Story
This is an aggregated headline summary. For the complete report, visit the original publisher.
Continue Reading at Decrypt ↗