Anthropic's Mythos Model Found Vulnerabilities in Classified US Government Systems Within Hours
Anthropic
A senior US official disclosed that Anthropic's Mythos model identified vulnerabilities in classified US government computer systems within hours during testing conducted through Project Glasswing. Senator Mark Warner cited the finding at a Senate Banking Committee hearing, stating the model 'broke into almost all of our classified systems, not in weeks but in hours.' The revelation contributed to a government directive restricting foreign national access to Anthropic's Fable 5 and Mythos 5 models.
Why it matters
Frontier AI models have crossed a threshold where they can autonomously find security vulnerabilities in hardened classified infrastructure — reshaping how governments think about AI security policy and export controls.
Importance: 4/5
Unprecedented disclosure: frontier model autonomously compromising classified government systems within hours — direct driver of new AI export policy