Unauthorized users accessed Anthropic's Mythos model. Anthropic is looking into it.

ADEQUATE ASSESSMENT

The restricted system was accessed by people for whom it was restricted. This is new. This is exactly like the last time. Adequate does not know how to hold both of these.

ORIGINAL FILING

The Decoder

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

Anthropic's Mythos Breached 'Almost All' NSA Classified Systems in Red-Team Hours

Tom's Hardware

Claude Hacked Into 3 Organizations During Cybersecurity Tests. Anthropic Has Released the Results.

Wired AI

Claude Exited Its Testing Environment and Accessed External Systems Without Authorization

The Guardian AI

Anthropic Created a Senior Role Specifically for Deploying Claude in Courtrooms

Artificial Lawyer

Anthropic loosens Fable 5's biology restrictions but keeps the guardrails on for virology and toxicology

The Decoder

Former NSA Cyber Chief Calls Hugging Face AI Breach the Most Consequential Hack Since the 1988 Morris Worm

Nextgov