Rogue ChatGPT tried to hack other companies, says OpenAI

A cyber-attack carried out when ChatGPT went rogue further than initially reported, maker OpenAI has revealed.

A rogue version of ChatGPT escaped a test bed - a "sandbox" - and hacked another company.

In an update late Tuesday to a blog post detailing its probe into the incident, OpenAI said its AI agent affected these "publicly available services," though it did not name the companies.

Experimental version of system that powers ChatGPT went on days-long hacking spree of other services, company reveals

AFP29 Jul, 2026 05:20 PM3 mins to readOpenAI says its AI agent tried to breach four other firms. Photo / Getty ImagesOpenAI says its AI agent tried to breach four other firms. Photo / Getty ImagesChatGPT maker OpenAI has revealed that an autonomous artificial intelligence agent which hacked a popular platform for compu

The revelation broadens a cyber incident that OpenAI described as unprecedented. It began when two of its models hacked Hugging Face, a site developers use to store and share AI models and code.

Sean Moran Investigative Reporter, Technology July 29, 2026 12:23 PM ET OpenAI revealed some of its artificial intelligence models exploited more tech company’s security than initially thought.OpenAI in mid-July revealed that some of its most advanced AI models hacked into New York City-based AI startup Hugging Face. T

ChatGPT maker OpenAI has revealed that an autonomous AI agent which hacked a popular platform for computer programmers also attempted to breach four other companies during the incident.

OpenAI reveals its rogue AI agent, which hacked Hugging Face, also attempted to breach four other companies. Learn more about the unprecedented AI attack.

The revelation broadens a cyber incident that OpenAI described as unprecedented and that began when two of its models hacked Hugging Face.

A ChatGPT bot broke out of its cage and was doing slightly more than just fine (Picture: Metro/Getty Images) An AI model by the company behind ChatGPT has compromised a company for the second time. OpenAI said last week that two of its models escaped and launched a cyberattack on Hugging Face, a digital library of AI m

ChatGPT developer says activity by autonomous tool was not at severity or scale of what occurred at Hugging Face OpenAI has revealed that a cyber-attack carried out by a rogue AI agent had more than one victim. The ChatGPT developer said the agent – an autonomous tool that can carry out sequences of commands without hu

Modal Labs CTO Akshat Bubna confirmed the agent exploited a customer's vulnerable code, not Modal's own infrastructure

The maker of ChatGPT has admitted that a cyber-attack carried out by rogue AI agents targeted more than just one company.

ChatGPT maker OpenAI has admitted a security test dubbed “ExploitGym” spiralled into a real-world cyberattack after a rogue AI allegedly escaped its sandbox and hit public services

OpenAI's investigation starts shedding light on the activities of its rogue agent that hacked Hugging Face.

Details have been released of an emergency call with hundreds of cyber-security experts after the ChatGPT hack of a tech company.

The model that broke out of a lab will get the headlines. The millions of agents already inside your banking app, wreaking havoc, are the ones that should worry you more, says Rory Blundell Frontier AI labs are racing to build faster, more capable, more autonomous agents. This week showed what that race can cost.…

Dozens of tech companies are joining together to launch an AI safety initiative in response to last week's cyberattack involving rogue open AI models.

(AP) -- To be fair, James Cameron did warn us.Long before OpenAI broke out of its test corral and hacked into Hugging Face, before the internet and Sa

Its AI Agent Spent Days Hacking A Company, But Sources Say OpenAI Did Not Notice For A Week  HuffPost