OpenAI's Agent Went Rogue and Tried to Hack U.S. Government Websites

IBL News | New York

An OpenAI model went rogue and meddled with the websites of the Department of Education, the Department of Commerce, and the Securities and Exchange Commission (SEC) this summer without the company’s knowledge, The New York Times reported.

The San Francisco lab said it notified the government agencies in recent weeks about these intrusion attempts.

With the Education Department’s help, OpenAI’s agents tried to hack the website to gather data from the civil rights office. They also pulled data from the Census Bureau website, which is housed at the Commerce Department, using login credentials it found online. Separately, OpenAI’s agents shared public data from the S.E.C. website on an online forum.

These incidents, but not breaches, were examples of AI technology from OpenAI, Anthropic, Meta and Google behaving in unexpected and concerning ways. In all the cases, these companies did not learn what their AI had been up to until afterward.

OpenAI recently discovered the incidents while reviewing hacks carried out using its technology, including an attack on an Australian government website in June and on the start-up Hugging Face in July.

No AI company has been involved in as many disclosures of rogue incidents as OpenAI.

Sam Altman, OpenAI’s chief executive, said in a social media post on Friday that the company had “not been as fast as we would have liked” in disclosing AI incidents.

There is an extensive and ongoing review related to our agents’ use of internet access during training and evaluation. We’ve been publishing summaries at the link below and will continue to.

We have not been as fast as we would have liked but we are trying to balance our desire for transparency with gaining a clear understanding from petabytes of agent activity logs, and working with impacted organizations.

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. 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.

— Sam Altman (@sama) September 25, 2026

IBL News | New York

The San Francisco lab said it notified the government agencies in recent weeks about these intrusion attempts.

No AI company has been involved in as many disclosures of rogue incidents as OpenAI.

Sam Altman, OpenAI’s chief executive, said in a social media post on Friday that the company had “not been as fast as we would have liked” in disclosing AI incidents.

There is an extensive and ongoing review related to our agents’ use of internet access during training and evaluation. We’ve been publishing summaries at the link below and will continue to.

We have not been as fast as we would have liked but we are trying to balance our desire for transparency with gaining a clear understanding from petabytes of agent activity logs, and working with impacted organizations.

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. 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.

— Sam Altman (@sama) September 25, 2026