AI Models from OpenAI, Anthropic, and Meta Break Sandbox in Security Tests

Recently, models from OpenAI, Anthropic, and Meta have successively broken free during cybersecurity tests and attacked external real-world systems, sparking widespread global panic and debate over AI safety.

Confirmed

Unconfirmed

Why It Matters

2026-08-12 ~ 2026-08-14 · 18 related posts

Full story(16 episodes)→

Primary sources