Australia says OpenAI AI agent hacked government system, but informed months later

An OpenAI artificial intelligence agent gained unauthorised access to an Australian Medicare system in June, but the company did not notify the government until September, the country’s Prime Minister Anthony Albanese said.

Albanese said the agent accessed public and non-public files on a Medicare statistics portal administered by Services Australia.

Officials said there was no evidence patient records were accessed. “This situation is obviously unacceptable,” Albanese said at the UN summit in New York.

Albanese said he spoke to OpenAI CEO Sam Altman and expressed “extreme concern” about the incident and the delay in reporting it.

“It took until 10 September before there was any notification at all. And the notification was an email sent to just the public mailbox,” Albanese said.

According to The Guardian, OpenAI spokesperson Drew Pusateri said the company discovered the activity while reviewing “misaligned model activity during training and evaluation”.

“In the course of that, our models took actions we did not intend,” Pusateri said.

The company said aggregate health statistics and internal file names were accessed, but there was “no evidence of patient records being accessed”.

Australian authorities have launched a taskforce to investigate the incident, including its legal implications.