External Publication
Visit Post

Mythos accessed by unauthorized users as Anthropic says 'We’re investigating' — Cracks may be showing in Project Glasswing as unknown users access model via third parties

TechRadar | the technology experts [Unofficial] April 22, 2026
Source
Anthropic is investigating unauthorized access to its Claude Mythos AI model, which is capable of identifying and exploiting zero-day vulnerabilities.

Discussion in the ATmosphere

Loading comments...