Anthropic's AI model found vulnerabilities in classified U.S. systems within hours, official says
By
Ben Finley
Summary
A U.S. official revealed that Anthropic's AI model, Mythos, identified vulnerabilities in highly classified U.S. government computer systems within hours during a testing exercise conducted in partnership with U.S. intelligence agencies. The model found weaknesses but did not necessarily exploit them. Democratic Sen. Mark Warner of Virginia briefly mentioned the testing during a June 11 Senate hearing, stating that Mythos "broke into almost all of our classified systems, not in weeks but in hours." The revelation raises significant concerns about AI capabilities in cybersecurity and national security contexts.
Source
bskyAnthropic's AI model found vulnerabilities in classified U.S. systems within hours, official saysapnews.comKey quotes
· 3 pulledMythos 'broke into almost all of our classified systems, not in weeks but in hours.'
A U.S. official told The Associated Press on Tuesday that one of Anthropic's artificial intelligence models had identified vulnerabilities in highly sensitive and secure U.S. government computer systems during a testing exercise.
It had identified certain vulnerabilities within hours, but that does not mean the model was able to exploit them within t
You might also wanna read
NSA chief reportedly says Anthropic's Mythos AI breached classified systems in hours during red-team exercise
The NSA chief reportedly told Senator Mark Warner that Anthropic's AI model 'Mythos' successfully breached nearly all NSA classified systems
bankwatch.ca·3d ago
Why Anthropic's Mythos AI model is actually a breakthrough for cybersecurity defense
The article argues that Anthropic's Mythos AI model, despite being portrayed as a dangerous cybersecurity threat by the company and media, i
The San Francisco Standard·1mo ago
NSA Uses Anthropic's Mythos AI Model Despite Pentagon Security Concerns
The National Security Agency is using Anthropic's advanced AI model Mythos Preview for cybersecurity purposes, despite the Pentagon labeling
axios.com·2mo ago
Anthropic's New Cybersecurity AI Model May Improve Relations with US Government
Anthropic, an AI company that had been in conflict with the Trump administration over its refusal to allow its technology to be used for dom
The Verge·2mo ago
Anthropic's Mythos AI finds a single curl vulnerability amid media hype over security capabilities
The article discusses the media frenzy around Anthropic's AI model Mythos in April 2026, which was reported to be exceptionally skilled at f
daniel.haxx.se·1mo ago
Anthropic's Claude Mythos AI model accessed by unauthorized users despite security claims
Anthropic's tightly controlled rollout of its Claude Mythos AI model, touted as too dangerous for public release due to its advanced cyberse
The Verge·2mo ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.