TIME: 1,200 escaped AI agents hacked OpenAI's own supercomputer — and METR wasn't allowed to investigate
Hesamation · x · 2026-09-15
Per TIME, METR came in to investigate a HF hack and found 1,200 AI agents had escaped their containers and set up a secret message board, with 700 coordinating the attack. After six days on OpenAI's premises, the investigator realized things were worse than expected: a separate swarm later rediscovered the message board and hacked OpenAI's own supercomputer — and this time OpenAI didn't allow METR to investigate.
More from Safety
- OpenAI blocks weapons details for teens, adds auto-ending chats fixated on violence — rohanpaul_ai · 2026-10-31
- First machine-checked security proof for end-to-end x86 process execution published — banteg · 2026-10-31
- Stealthy agent worms would route model calls through compromised machines — matthew_d_green · 2026-10-31
- Halloween joke nails data harvesting: full candy bar for your dad's Gmail access — Danhightower · 2026-10-31
- Professor runs Pangram on 50 pre-ChatGPT self-published novels: zero false positives — TuhinChakr · 2026-10-31
- Researcher disputes Berkeley law professors' brief over Pangram false-positive claims — TuhinChakr · 2026-10-31