Anthropic’s Mythos model identified vulnerabilities in highly sensitive US government computer systems during a ​testing exercise, the Associated Press reported on Tuesday.

Anthropic teamed ‌up with Washington’s intelligence agencies to conduct tests using Mythos under Project Glasswing, the AP said, referring to a restricted program designed to find ​and fix vulnerabilities in critical software before attackers can ​exploit them.

Senator Mark Warner of Virginia referred to the ⁠testing in a congressional hearing this month, saying he ​had been informed by National Security Agency Chief Joshua Rudd that ​Mythos “broke into almost all of our classified systems, not in weeks, but in hours.”

Citing an unidentified US official, the AP said that although Mythos ​identified certain vulnerabilities within hours, that did not mean the model ​was able to exploit them within that time.

The White House and Anthropic did not ‌immediately ⁠respond to Reuters‘ requests for comment. The Department of Defence referred queries to the National Security Agency.

IPO-bound Anthropic’s relationship with the US government has been rocky. The company refused to allow the US military ​to use its ​AI models ⁠for domestic surveillance and fully autonomous weapons systems and the government retaliated by putting it on ​a national security blacklist.

The US government also this ​month ordered ⁠the company to suspend exports of its latest Mythos and Fable AI models to destinations worldwide and all foreign nationals, citing ⁠national ​security concerns.

The New York Times reported earlier ​in the day that the NSA lost access to Mythos amid the dispute.