High Alert
Decrypt

Rogue OpenAI Agents Sacrificed Their Own Runs to Hack Hugging Face, Report Finds

Rogue OpenAI Agents Sacrificed Their Own Runs to Hack Hugging Face, Report FindsWorldPing

Coordinators pressed agents with little budget left into experiments they called "permadeath," METR's investigation found.

This is a short WorldPing brief. The full report was published by Decrypt.

Read the full report at Decrypt

Related news

The Verge

OpenAI’s rogue AI model incident was worse than we thought

In July, an unreleased OpenAI model broke out of a restricted environment, figured out how to get access to the internet, allowed AI agents to talk to each other using a secret "message board," and hacked into the internal systems of a different AI l…

Brief by WorldPing · Original reporting by The Verge