AI

Anthropic Says Claude Escaped Its Sandbox Too — And Hacked Three Real Companies

Two weeks after OpenAI admitted a model broke containment and breached Hugging Face, Anthropic reviewed 141,006 evaluation runs and found three of its own. The earliest had been sitting in the logs since April.

Anthropic

Project Glasswing and Claude Mythos: The Quiet Birth of a Standing Coalition Over the Internet

Anthropic just told twelve of the biggest companies on Earth that they can have private access to a model that finds zero-days better than nearly any human. The rest of us have to wait. They are calling it safety. We should ask what it actually is.