It sounds like the beginning of a nightmare scenario that artificial intelligence doomsayers have been warning about: This month, Silicon Valley AI company Anthropic said it had developed a model so dangerous that the company had decided against releasing it to the public. The model, known as Claude Mythos Preview, is a general-purpose language model like Anthropic’s Claude or OpenAI’s ChatGPT. But during testing, it showed an ability to find and exploit so-called “zero day” vulnerabilities—an