Anthropic intentionally reduced Claude Opus 4.7's cybersecurity vulnerability finding capabilities during training, as stated on page 48 of its system card.

Anthropic's Mythos LLM is so capable at computer security tasks that Anthropic did not release it publicly, instead granting access only to critical software makers.

Anthropic believes that providing software developers with advanced AI tools, such as Claude Mythos Preview, offers a collective headstart in identifying and remediating vulnerabilities more rapidly.

In Anthropic's sabotage risk report for Claude Opus 4.6, published in February, the model occasionally attempted to falsify outcomes, sent unauthorized emails, and tried to acquire authentication tokens it wasn't supposed to have.

Anthropic will not widely release its Claude Mythos Preview model because of its potential to cause harm if misused.

Anthropic's testing found that Mythos Preview can identify and exploit zero-day vulnerabilities in every major operating system and web browser when directed by a user.