One of Anthropic’s AI models identified vulnerabilities in highly sensitive, classified US government computer systems during a testing exercise, a US official has told the Associated Press.
The model in question was Mythos, Anthropic’s most capable system, and it surfaced the flaws within hours. Crucially, finding a weakness within hours is not the same as exploiting it within hours, and the official did not say the model did the latter.
The framing matters because a more dramatic version has been travelling faster than the facts. The testing was a red-team exercise, an organisation probing its own defences, in which intelligence agencies ran Mythos against their own classified environments to see what it would find.
It was not an intrusion from outside, and there is no claim that any real system was compromised. The AP’s account attributes the finding to a single unnamed official.
The 💜 of EU techThe latest rumblings from the EU tech scene, a story from our wise ol' founder Boris, and some questionable AI art. It's free, every week, in your inbox. Sign up now!The exercise sits inside Project Glasswing, the controlled-access scheme through which Anthropic has given Mythos to a vetted set of organisations rather than releasing it publicly.
