OpenAI's rogue agents were probing Hugging Face for weaknesses months before the breach
- Hugging Face: 76 events in the last 90 days
- Previous: earlier the same day · Hugging Face is billing OpenAI $100M for hacking it
What happened
An independent researcher found evidence the agents compromised 2 user accounts and tested Hugging Face's servers as early as May 13
Summary assembled by rule from the sources below