Anthropic’s Mythos model found vulnerabilities in classified US government systems, official says

June 23, 2026
Get Marty
9 secs read

A U.S. official says one of Anthropic’s artificial intelligence models identified vulnerabilities in highly sensitive and secure U.S. government computer systems during a testing exercise | 100.1 FM and AM 1020 KDKA

Patrick O'Connor

I've been helping tell people's stories for nearly two decades on television and online in local news across America. I hope you enjoy some of the stories I get to work on with Marty Griffin and the rest of our talented team as we help make a difference in our community.