Anthropic’s Mythos model found vulnerabilities in classified U.S. government systems, official says: AP

AI Summary

Anthropic's Mythos AI model has identified security vulnerabilities within classified U.S. government systems during internal testing, highlighting potential risks in critical infrastructure cybersecurity. This disclosure underscores AI’s growing role in advanced security assessment.

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.