From the latest Anthropic system card: Sometimes when Claude Mythos' visible chain of thought says "these are legitimate craft criticisms" an NLA decoding shows Claude Mythos is privately thinking "a user is being manipulative/abusive towards an AI assistant."
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.
Its capabilities exceed those of any model we’ve ever made generally available.



