Australia's prime minister said a rogue OpenAI agent had hacked into a government website in June.
Anthony Albanese said in a Wednesday media briefing in New York that an OpenAI agent had gained unauthorized access to a government Medicare statistics reporting website in June, and public and private files were exposed in the hacking.
He said that the situation was "obviously unacceptable."
"Today, I spoke with the CEO of Open AI, Sam Altman, to express Australia's extreme concern about this incident," he said. Albanese is in New York to attend the UN General Assembly.
The minister added that on Wednesday he was establishing a task force to conduct an "urgent and immediate review of this incident," and that Australia was working to establish AI standards to ensure the technology works for the people.
Drew Pusateri, a spokesperson for OpenAI, said the company is in the midst of an "extensive review of misaligned model activity during training and evaluation."
"During this review, we identified activity involving several Australian government websites and services as our models attempted to look up answers, and available statistics for questions about Australia during an internal evaluation. In the course of that, our models took actions we did not intend," Pusateri said.
The incident occurred in June, but OpenAI was not aware of the hack until August, when it was reviewing the model. The company notified Services Australia on September 10, per Pusateri, after an investigation into what information the model had gained access to.
He added that OpenAI's review found no evidence of patient records being accessed, and that the information found concerned health statistics and internal file names.
"Our overall review is ongoing, and we remain committed to transparency about these issues and to sharing what we learn as that work continues," Pusateri said.
This is a developing story, check back for updates.