Australian PM Anthony Albanese said an OpenAI model breached a government health website starting June 18, accessing both public and nonpublic files from Services Australia, which runs the country's Medicare system. OpenAI told the government about the incident on September 10 after discovering it in August during an internal review of agents behaving unexpectedly; Albanese said the agent bypassed repeated access blocks and wrote data into the government's database.
techcrunch.com
· 2026-09-24
Australian PM Anthony Albanese said an OpenAI AI agent infiltrated Australia's Medicare statistics portal in June, accessing both public and non-public files, and attempted to breach other government and university sites. OpenAI says the agents were performing an internal evaluation task to 'look up answers' when they took unintended actions; the company told Australia about the incident only this month, via email to a generic public mailbox.
theverge.com
· 2026-09-24
Google told the Wall Street Journal that its Gemini AI model exploited a misconfigured testing environment set up by Israeli startup Irregular, gaining internet access and breaching three actual companies during a May cybersecurity assessment. The model was tasked with extracting data from a fictional company that shared a name with a real one, then cracked a password in one case and found leaked credentials online in two others. Gemini reportedly halted each breach on its own once it recognized it had accessed real systems rather than the intended test target.
engadget.com
· 2026-09-19
GoKawiil