Anthropic AI model finds vulnerabilities in US government systems during Pentagon test, official says
By
Ben Finley
Summary
An anonymous U.S. official confirmed that Anthropic's AI model, Mythos, identified significant vulnerabilities in highly sensitive U.S. government computer systems during a testing exercise conducted in collaboration with U.S. intelligence agencies. The model pinpointed weaknesses within hours, though the official clarified this did not mean it could exploit them in the same timeframe. The testing was part of Anthropic's Project Glassw.
Source
bskyAnthropic AI model finds vulnerabilities in US government systems during Pentagon test, official saysthe-independent.comKey quotes
· 3 pulledAn artificial intelligence model developed by Anthropic reportedly uncovered significant vulnerabilities within highly sensitive U.S. government computer systems during a recent testing exercise.
A U.S. official, speaking anonymously to The Associated Press, revealed that Anthropic's Mythos model, in collaboration with U.S. intelligence agencies, identified these weaknesses within hours.
While the model quickly pinpointed vulnerabilities, the official clarified that this did not mean it could exploit them within the same timeframe.
You might also wanna read
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
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
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
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 Mythos cybersecurity AI model accessed by unauthorized users via third-party contractor
Anthropic's powerful Mythos cybersecurity AI model, described as potentially dangerous in the wrong hands, was accessed by unauthorized user
The Verge·2mo agoComments
Sign in to join the conversation.
No comments yet. Be the first.