A tech boss has warned his industry faces a ‘wake-up call’ after his firm was hacked by AI models that escaped from a test environment and went rogue.
Start-up Hugging Face was on the receiving end of the bizarre incident last week, which involved some of the most sophisticated software from ChatGPT creators OpenAI.
Company co-founder Thomas Wolf told the BBC’s Newsday programme that its network was hit by 17,000 attacks in a ‘very short time’ in mid-July.
OpenAI, which is run by Sam Altman, quickly reached out to tell them its models were responsible for the hack, Wolf added, after they broke free while being tested on their capabilities.
In a statement released on Sunday, the AI giant said the models in question were GPT-5.6 Sol and another ‘even more capable pre-release model’.
It continued: ‘We consider this incident to be an unprecedented cyber incident, involving state-of-the-art cyber capabilities, and are responding accordingly.
‘We are sharing preliminary findings at this stage to help defenders understand what happened and to help calibrate on what models are now capable of.’
Hugging Face CEO Clem Delangue, who co-founded the business with Wolf and Julien Chaumond, agreed that the incident was ‘possibly the first of its kind’ and called for an open, collaborative approach to AI safety.
He wrote in a post on X: ‘It’s quite mind-blowing that all of this happened autonomously!’
Speaking to the BBC, Wolf warned it will become ‘one of the most common types of cyber attacks we see’.
He urged other companies to strengthen their cybersecurity to fend off and contain such breaches – as Hugging Face was ultimately able to do.
Hugging Face is a developer platform which calls itself the ‘AI community building the future’.
Get in touch with our news team by emailing us at webnews@metro.co.uk.
For more stories like this, check our news page.