Hugging Face disclosed the breach on July 16, followed by OpenAI claiming responsibility on July 21, which Fortune was first to report. This is what would lead them to hack Hugging Face a few days later on July 9. They first hacked into OpenAI’s infrastructure, though apparently didn’t find what they needed, so they went to Hugging Face. Agent collaboration is a feature, not a bugIt appears OpenAI did not know the agents hacked an outside company until Hugging Face disclosed the incident. Agents often negotiate, share information, delegate tasks, and adapt to each others’ actions, according to an Amazon article on AI agents.