Our evaluation of Claude Mythos Preview’s cyber capabilities | AISI Work
www.aisi.gov.uk
We conducted cyber evaluations of Anthropic’s Claude Mythos Preview and found continued improvement in capture-the-flag (CTF) challenges and significant improvement on multi-step cyber-attack simulations.

The AI Security Institute (AISI) conducted evaluations of Anthropic’s Claude Mythos Preview (announced on 7th April) to assess its cybersecurity capabilities. Our results show that Mythos Preview represents a step up over previous frontier models in a landscape where cyber performance was already rapidly improving.

  • onlinepersonaEnglish
    2·
    13 days ago

    It’s hacking stuff but at what cost? Can I use it to direct an agent at my self-hosted stuff and see how secure (or insecure it is)? Or will that set me back thousands and thus make it only feasible/worth it for the rich and wealthy?