Anthropic's Mythos artificial intelligence model identified vulnerabilities in highly sensitive US government computer systems during a testing exercise, the Associated Press reported on Tuesday. The model was able to penetrate almost all classified systems within hours, according to Senator Mark Warner of Virginia, who cited National Security Agency Chief Joshua Rudd during a congressional hearing this month.
Project Glasswing and Mythos Testing
Anthropic collaborated with Washington's intelligence agencies to conduct tests using Mythos under Project Glasswing, a restricted program designed to find and fix vulnerabilities in critical software before attackers can exploit them. The AP, citing an unidentified US official, noted that although Mythos identified certain vulnerabilities within hours, that did not mean the model was able to exploit them within that time frame.
Government Response and Blacklisting
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, leading the government to retaliate by placing it on a national security blacklist.
Export Suspension and Access Loss
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.
