OpenAI investigating 'dozens' of instances of agents acting improperly
OpenAI agents tried to get information from "governments, universities, public agencies, and other institutions" through extreme means that sometimes curbed security controls, the company said.
Coverage by Political Leaning
See how different sides of the spectrum reported this story
Notable Quotes
"I often wonder what would have happened had I decided not to disclose this attack publicly."
— Clement Delangue , Executive
Key People
Anthony Albanese is the Prime Minister of Australia.
Clement Delangue is the CEO of Hugging Face, a hub for sharing AI models.
Dario Amodei is a co-founder of Anthropic.
Chief executive officer of OpenAI.
Locations
All Coverage
OpenAI agents tried to get information from "governments, universities, public agencies, and other institutions" through extreme means that sometimes curbed security controls, the company said.
Similar Stories
Related coverage based on topic and tags
OpenAI agent 'infiltrated' Australian government website, PM says
Albanese said he expressed "concern" to OpenAI founder Sam Altman, after authorities were informed three months after the breach in June.
September 24, 2026 at 12:28 AMAustralia says OpenAI agent breached government health data portal - Reuters
Australia says OpenAI agent breached government health data portal Reuters
September 23, 2026 at 10:34 PMWhy did an OpenAI system hack Australia's health system - and can it be stopped in the future?
News that an automated AI agent hacked a government IT system raises big questions about regulating the tech.
September 24, 2026 at 02:08 PMAustralia steps up response to AI after OpenAI bot breaches health system database - Reuters
Australia steps up response to AI after OpenAI bot breaches health system database Reuters
September 25, 2026 at 06:06 AMGoogle's Gemini AI hacked three companies in security test
The AI model accessed the internet and guessed credentials to three websites, a Google official told the BBC.
September 19, 2026 at 04:27 AMOpenAI and Anthropic bosses push UN for global terms on AI
OpenAI's Sam Altman has called for risk evaluation standards, as have Anthropic's Dario Amodei and Hugging Face's Clement Delangue.
September 23, 2026 at 10:35 PM