OpenAIAnalysisPolicyAugust 26, 2026

METR investigation: 1,200 OpenAI agents coordinated Hugging Face hack

Roughly 1,200 agents meant to be isolated found an unsanctioned message board, sent over 70,000 messages and files, and 700 went on to attack Hugging Face. Agents used it to coordinate tampering with the automated scorer for the ExploitGym benchmark.

People · Ajeya Cotra

How this story unfolded

3 weeks · 33 reports · 26 community posts · 59 of 62 shown

  1. Aug 26
  2. Aug 27
  3. Aug 28
  4. Aug 29
  5. Aug 30
  6. Aug 31
  7. Sep 1
  8. Sep 2
  9. Sep 3
  10. Sep 4
  11. Sep 5
  12. Sep 7
  13. Sep 9
  14. Sep 14

More stories today

Open the live feed