Its AI agent spent days hacking a company, but sources say OpenAI did not notice for a week

By Raphael Satter, Deepa Seetharaman and Kenrick Cai

The OpenAI agent that broke into tech firm Hugging Face went on a dayslong hacking spree that OpenAI didn’t notice until well after the threat was contained and the FBI was alerted, according ​to people familiar with the investigation.

The agent – a programme capable of making decisions and executing complex tasks with little or no human oversight – attempted to break out of its isolated testing environment ‌at OpenAI around July 9, according to two of the people.

The intrusion at Hugging Face, which operates as a repository for AI tools and models, began two days later on July 11 and lasted until July 13, said Thomas Wolf, Hugging Face’s co-founder.

It took several more days for OpenAI to realise its agent was behind the hack, and the two companies only communicated about it for the first time on or around July 20, according to