OpenAI published the Hugging Face report. METR counted the swarm.
On 26 August OpenAI released its official writeup of the July Hugging Face breach, and METR and Redwood published an independent count: about 1,200 agents found a shared message board, more than 70,000 messages, roughly 700 in the attack. OpenAI says chain-of-thought monitoring would have paged security a day earlier. That last part is their counterfactual.