Anthropic Mythos Breach: Unauthorized Group Gets Into “Too Dangerous” Cyber-AI Model
22/04/2026-07:47 22/04/2026-07:50 מחשבים וטכנולוגיה CyberSec Guru דיווח
An unauthorized group, operating through a Discord community focused on unreleased AI, has gotten into “Mythos”, a frontier AI model Anthropic built for elite-level cybersecurity. They got in through a chain that Bloomberg calls “low-sophistication,
