Anthropic’s testing reveals classified U.S. government systems have vulnerabilities, says anonymous source

Within hours of launching a test on government systems, Anthropic’s Mythos model found security issues.

Anthropic co-founder and President Daniela Amodei, left, speaks with Snowflake CEO Sridhar Ramaswamy during the keynote presentaton at Snowflake Summit 26 Monday, June 1, 2026, in San Francisco. [Photo: Jeff Chiu/AP Photo]

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.The official, who spoke on the condition of anonymity to discuss the matter, said Anthropic had teamed up with U.S. intelligence agencies to conduct tests using the company’s Mythos model. It had identified certain vulnerabilities within hours, but that does not mean the model was able to exploit them within that time, the official said.The official........

© Fast Company