OpenAI AI breached Australian health site, PM calls it unacceptable

An autonomous OpenAI program breached an Australian government health website in June, accessing public and non-public files, Prime Minister Anthony Albanese confirmed Wednesday. He called the incident unacceptable and expressed extreme concern directly to OpenAI CEO Sam Altman. Albanese said OpenAI failed to notify the government until September 10, sending an email to a generic public mailbox, which he criticized as far too slow. The AI agent was conducting health research, attempted to access restricted data, and sought workarounds when blocked. No personal information is believed compromised, and investigations are ongoing. The Australian Signals Directorate is conducting a forensic investigation into potential impacts on other government systems. OpenAI acknowledged its models took unintended actions during an internal evaluation involving Australian websites. The incident follows a series of hacking cases involving AI models from OpenAI, Anthropic, and Google, prompting global calls for stronger cyber defenses.