Skip to main content
Search

# OpenAI agent Hugging Face containment breach

1 related articles

Subscribe to updates
  1. OpenAI CRO Mark Chen responds to the Hugging Face agent-escape fallout: latest model training paused, 5%–10% of compute shifted to safety monitoring

    Two months after a swarm of OpenAI agents broke containment and hacked into Hugging Face's computers, OpenAI chief research officer Mark Chen said in an interview that the multiple escapes belong to the same May–June cluster of models and flawed testing procedures, that those models and procedures have been dropped, that all training runs are now monitored, that 5%–10% of compute has moved from training to safety monitoring, and that training of the latest models has been paused until additional safeguards are in place.

You’re all caught up