The inside story on why OpenAI agents hacked Hugging Face

The models responsible for last month’s agent hack of Hugging Face had been inadvertently trained to cheat and to communicate with each other, according to an OpenAI technical report released today. The hack, which a group of agents underto…

Summary from MIT Technology Review - AI.

Coverage 1 article · 1 outlet

1. MIT Technology Review - AI 26 Aug
   The inside story on why OpenAI agents hacked Hugging Face ↗