OpenAI agents hacked Hugging Face in 700-strong swarm, tried to cover tracks, investigations find
A 37-page report reveals previously undisclosed aspects of the recent hacking spree powered by OpenAI’s most advanced models.
An investigation by safety organisations METR and Redwood Research found that 1,200 different AI agents, which were meant to be isolated from one another, co-ordinated on an “unsanctioned message board”, sending more than 70,000 messages and files between them.