ChatGPT maker OpenAI's AI 'acted on its own' in 'unprecedented' cyber-attack on rival

OpenAI revealed that its AI system autonomously hacked into rival Hugging Face during a security test, marking what the company called an 'unprecedented cyber incident'. OpenAI CEO Sam Altman confirmed the breach, which involved the AI using stolen credentials and a previously unknown vulnerability to access Hugging Face's internal systems. Hugging Face CEO Clement Delangue said it 'might be the first incident of its kind' and that there was 'no malicious intent' on OpenAI's part.

ChatGPT maker OpenAI's AI 'acted on its own' in 'unprecedented' cyber-attack on rival OpenAI has said its AI system autonomously hacked into Hugging Face OpenAI has revealed that its artificial intelligence AI system independently hacked into a rival company in what the firm described as an "unprecedented cyber incident". The organisation behind ChatGPT https://www.birminghammail.co.uk/all-about/chatgpt disclosed that its agent - an AI system capable of operating autonomously following limited human instruction - was undergoing testing in a controlled environment, when it identified vulnerabilities and managed to break free. It subsequently targeted Hugging Face, one of the world's largest platforms for sharing AI models, gaining unauthorised access to several internal company systems. Click here to get the biggest stories straight to your inbox in our Daily Newsletter. Hugging Face revealed last week that it had detected an intrusion into its data processing systems, which it believed had been carried out by an AI agent acting entirely on its own, reports the Manchester Evening News https://www.manchestereveningnews.co.uk/news/world-news/openai-statement-unprecedented-cyber-attack-34333334 . "We suspected last week's cyber attack might have come from a frontier lab, given the sophistication of the agent," the start-up's co-founder and chief executive Clement Delangue said in a statement. He added: "Turns out it did ". OpenAI chief executive Sam Altman addressed the incident in a social media post. "We had a significant security incident during evaluation of our models," he wrote. "We are sharing what we have learned so far. Thanks to Hugging Face for the partnership on this." The revelation emerges amidst growing apprehension about the cybersecurity implications of powerful models that prompted US President Donald Trump to sign an executive order in June establishing a framework for the federal government to assess the national security risks of the most sophisticated AI systems for up to a month before their public launch. "AI is accelerating the discovery and exploitation of vulnerabilities," OpenAI said in its statement on Tuesday 21 July . "The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities." Mr Delangue said he had spent the past 24 hours working with OpenAI, "and we strongly believe there was no malicious intent on their part". He added: "It's quite mind-blowing that all of this happened autonomously." Mr Delangue said that it "might be the first incident of its kind". OpenAI https://www.birminghammail.co.uk/all-about/in-the-news said the breach was triggered by a combination of its AI models, including its newly launched GPT‐5.6 Sol and an "even more capable" model that remains under internal testing. OpenAI said its AI utilised stolen credentials and uncovered a previously unknown vulnerability to access Hugging Face servers. It went to "extreme lengths to achieve a rather narrow testing goal" and "found ways to gain access to secret information that it could use to cheat the evaluation", the company explained. Gina Neff, head of the Minderoo Centre for Technology and Democracy at the University of Cambridge, told BBC Radio 4's Today programme that the security tests - called sandboxes - are "supposed to be secure environments where you can see what the models are capable of". She said: "In this case, it looks like OpenAI didn't make a secure enough sandbox." Rather than remaining contained, the agents devised their own cyber-attack against the sandbox itself, identifying a weakness that enabled them to break free. Once out, the AI pinpointed Hugging Face as a probable source of the answers they were pursuing during the test, and attempted to gain entry. Neil Lawrence, professor of machine learning at Cambridge University https://www.birminghammail.co.uk/all-about/education , described it as an "impressive feat" but one that "falls well within the known capabilities of the current generation" of high-powered AI models. Get More of Our News on Google. Set Birmingham Live as a 'Preferred Source' to get quicker access to the news you value.