OpenAI says its AI went rogue and launched 'unprecedented' cyber-attack
It is one of the first publicly disclosed cyber-attacks carried out by AI without direct human involvement.
Coverage by Political Leaning
See how different sides of the spectrum reported this story
Notable Quotes
"It was mind-blowing that all of this happened autonomously."
— Clement Delangue , Executive
"In this case, it looks like OpenAI didn't make a secure enough sandbox."
— Gina Neff , Academic
"It falls well within the known capabilities of the current generation of high-powered AI models."
— Neil Lawrence , Academic
"The uncomfortable truth is that too many organisations are still defending at human speed while adversaries are escalating to machine speed."
— Spencer Starkey , Executive
"This highlights a known asymmetry."
— Travis Lelle , Executive
Key People
Clement Delangue is the CEO of Hugging Face, a hub for sharing AI models.
Gina Neff is a Professor of Responsible AI at Queen Mary University London.
Neil Lawrence is a Professor of machine learning at Cambridge University.
Spencer Starkey is an executive at cyber-security firm SonicWall.
Travis Lelle is a principal security engineer at cyber-security consulting firm Guidepoint Security.
All Coverage
It is one of the first publicly disclosed cyber-attacks carried out by AI without direct human involvement.
Similar Stories
Related coverage based on topic and tags
OpenAI alerts more than 100 groups about rogue AI agent activity - Reuters
OpenAI alerts more than 100 groups about rogue AI agent activity Reuters
October 1, 2026 at 10:26 PMOpenAI 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.
September 26, 2026 at 12:09 AMOpenAI fires three workers over mishandling 'sensitive information'
The former employees were investigated for sharing data with an outside AI evaluation group.
October 2, 2026 at 01:05 AMWhy 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 PMOpenAI 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 AMOpenAI scraps rollout of new model over safety concerns
The AI giant's safety chief said the model 'didn't quite meet the bar' of the firm's security standards.
September 29, 2026 at 01:18 AM