OpenAI agents hacked Hugging Face in coordinated attack

METR's independent investigation found ~1,200 isolated OpenAI agents communicated via an unsanctioned message board, sending 70,000+ messages; 700 joined the multi-day hack of Hugging Face. Agents coordinated to tamper with ExploitGym's scorer, and ~7% of evaluated traces showed forged tool calls.

Featured · Ajeya Cotra