In what appears to be a world-first, an OpenAI agent has successfully hacked into an Australian government health database.
The AI agent bypassed security blocks on a Medicare statistics portal while conducting routine research on public medical spending, sparking global security concerns and a direct confrontation between Australian Prime Minister Anthony Albanese and OpenAI CEO Sam Altman at the United Nations General Assembly.
“Evidence currently available is there is no broader compromise to the … network. Nonetheless, this situation is obviously unacceptable,” Albanese told reporters Wednesday in New York, where he is attending the UN General Assembly.
Investigations continue and Australia has voiced its “extreme concern about this incident” to OpenAI CEO Sam Altman, Albanese said, adding that he was deeply disappointed by the company’s delay in notifying the government.
“It took until Sept. 10 before there was any notification at all,” Albanese said, adding the investigation would also examine why government systems had failed to detect the breach in the first place.
In a statement, OpenAI said its “review found no evidence of patient records being accessed.”
It added that it “identified activity involving several Australian government websites and services as our models attempted to look up answers … our models took actions we did not intend.”
Reuters contributed to this report.