New details on the OpenAI Hugging Face hack: the rogue AI reached four accounts, but researchers say it was noisy, old-school, and stoppable.

In a new disclosure, OpenAI says its agent used exposed logins to gain access to at least four “publicly available services” in its unhinged quest to solve a test.

The latest hack comes after an autonomous agent escaped a controlled test and accessed AI firm Hugging Face’s servers.