Anthropic’s most dangerous AI model just fell into the wrong hands
Anthropic's Mythos AI model, a powerful cybersecurity tool that the company said could be dangerous in the wrong hands, has been accessed by a "small group of unauthorised users," Bloomberg reports.
An unnamed member of the group, identified only as "a third-party contractor for Anthropic," told the publication that members of a private online forum […]
Anthropic Probes Restricted AI Breach
- Anthropic investigating possible breach of its Mythos AI model CBS News —
- Outsiders breached Anthropic’s Claude Mythos same day ‘potentially dangerous’ AI model was revealed: report NY Post —
- Unauthorized users broke into Anthropic's restricted Mythos AI cybersecurity model Quartz —
- Anthropic is investigating 'unauthorized access' of its Mythos cybersecurity tool Engadget —
- Anthropic’s New Mythos A.I. Model Sets Off Global Alarms The New York Times —