Anthropic's most dangerous AI model, Claude Mythos Preview, has been accessed by a small group of unauthorised users through a private online forum. The group, identified only as a third-party contractor for Anthropic, accessed Mythos using their own access to the model. The model is capable of identifying and exploiting vulnerabilities in every major operating system and web browser when directed by a user to do so. However, Anthropic has no plans to release the model publicly due to concerns that it could be weaponized. The unauthorized access was made on April 7th, the same day Anthropic announced it was releasing Mythos to a limited number of companies for testing.