Anthropic's Mythos AI model identified critical vulnerabilities in classified US government computer systems during a testing exercise, according to a statement from a US official.
Mythos flagged vulnerabilities but didn't necessarily exploit them
Jun 25, 2026
12:38 pm
What's the storyAnthropic's artificial intelligence (AI) model, Mythos, has exposed vulnerabilities in highly sensitive US government computer systems.
The revelation was made by a US official who spoke on the condition of anonymity to the Associated Press.
Anthropic’s Mythos found flaws in classified US systems during a government test
Anthropic’s Mythos Model Found Vulnerabilities in Classified US Government Systems, Official Says
Anthropic's Mythos AI Uncovers Vulnerabilities in Classified US Government Systems During Security Tests
Anthropic's Mythos model found vulnerabilities in classified US government systems – report
Anthropic’s Mythos model found vulnerabilities in classified US government systems, official says
Anthropic’s Mythos model found vulnerabilities in classified US government systems, AP reports
Anthropic's Mythos model found vulnerabilities in classified U.S. government systems: Report
Anthropic’s Mythos AI Reportedly Hacked the NSA’s Most Sensitive Systems ‘in Hours’
Pentagon shock as AI system breaks into secret government networks, official confirms
Anthropic AI cracked classified US systems within hours, officials say
A US official says Anthropic’s Mythos model found vulnerabilities in classified government systems during a red-team test, not an…
Anthropic teamed up with U.S. intelligence agencies to conduct tests using the Mythos model, which found vulnerabilities in…
Anthropic's advanced artificial intelligence model, Mythos, identified vulnerabilities in highly sensitive and classified US…
Citing an unidentified US official, the Associated Press says that although Mythos identified certain vulnerabilities within…
A U.S. official says one of Anthropic’s artificial intelligence models identified vulnerabilities in highly sensitive and secure…
June 23 : Anthropic’s Mythos model had identified vulnerabilities in highly sensitive and secure U.S. government computer systems…
