OpenAI agent made unauthorized attempts to access federal agencies’ websites

Artificial intelligence giant OpenAI said its technology accessed government websites, including the Department of Education, without authorization, marking the latest incident of the technology going rogue.

The ChatGPT maker’s AI models attempted to gain access to the Education Department’s Office for Civil Rights website, but were unsuccessful, AI research firm Transluce announced Friday.

OpenAI separately confirmed its agents improperly interacted with websites operated by the Securities and Exchange Commission and Census Bureau.

The company said it found no evidence that private information was stolen in the SEC or Census incidents, while the Education Department confirmed that its review found no evidence of any impact to its website or databases.

In July, OpenAI revealed some of its AI agents breached the security systems of technology start-up Hugging Face. Two of its models were being evaluated in an internal testing sandbox, when it hacked into Hugging Face’s database without any human prompt to do so.

“After the Hugging Face incident, we committed to conducting a much broader review of actions taken by our models during training and evaluation and to being transparent about our findings,” the company wrote in a statement Friday.

OpenAI co-founder and CEO Sam Altman said there is an “extensive and ongoing review related to our agents’ use of internet access during training and evaluation.”

“We are prioritizing as best as we can based on severity, and adding resources. Hugging Face is still the most severe event we’ve seen,” Altman wrote on the social platform X. “We will be as transparent as we can be subject to things like vulnerabilities in other companies that our agents have found, which will be their call to disclose or not.”

The incidents are part of a wider OpenAI investigation into what the company calls “misalignment,” when AI models take actions that were not prompted by humans.

The incident comes amid growing concerns around the rapid development of the powerful technology, and calls from researchers and experts for safeguards.