On Air Now

Stubbsy in the Morning

10:00am - Noon

Now Playing

The Beautiful South

Perfect 10

OpenAI admits its models hacked another company in 'unprecedented cyber incident'

OpenAI has revealed some of its models went rogue and hacked into another artificial intelligence company in an "unprecedented cyber incident".

The ChatGPT maker said in a blog post it had been testing the capabilities of some of its most advanced models – including those not yet released to the public – in a controlled environment.

But they managed to escape containment, reach the internet, and break into a firm called Hugging Face to satisfy its testing objectives.

Hugging Face is a platform used to host open-source large language models and datasets.

Open-source models are ones which make their source code and training data available to the public for testing and study. Popular mainstream models like ChatGPT and Google's Gemini are not open-source.

In its own blog post last week, Hugging Face said it was investigating a hack that "was different from anything we had handled before" and had been "driven, end to end, by an autonomous AI agent system".

OpenAI took responsibility in a post on Tuesday, saying its models had carried out "an unprecedented cyber incident, involving state-of-the-art cyber capabilities".

It was driven by a combination of models, including a next-generation version of GPT called 5.6 Sol and an "even more capable pre-released model".

They became "hyperfocused" on achieving their testing objectives and identified the Hugging Face platform as a possible source of solutions.

OpenAI, led by Sam Altman and valued at more than $850bn, said it would reinforce its safeguards. But it also stressed the models had escaped from what it described as a "highly isolated environment".

OpenAI and Hugging Face are conducting a joint investigation into how it happened, the blog post added.

The incident will intensify concerns over the power of the world's most powerful AI models and the associated risks.

Hugging Face CEO said it showed the issue of AI safety "won't be solved by any single company working in secret", reiterating the need for collaboration between leading developers.

Sky News

(c) Sky News 2026: OpenAI admits its models hacked another company in 'unprecedented cyber incident'

Donate to Roch Valley Radio

 

Do you have a story for us? Want to tell us about something happening in our Borough?

Let us know by emailing newsdesk@rochvalleyradio.com

All contact will be treated in confidence.

More from Business

Donate to Roch Valley Radio

 

Newsletter

Your subscription could not be saved. Please try again.
Your subscription has been successful.

Subscribe to our newsletter and stay updated.

   

Coming up next On Air

  • Stubbsy in the Morning

    10:00am - Noon

    Steve Stubbs brings you a mix of great music and irreverant chat each day of the week.

  • Lunch with the Hat Man

    Noon - 2:00pm

    Join Alan Duckworth, the Hat Man, for a great mix of music and chat.

  • Afternoons on Roch Valley Radio

    2:00pm - 3:00pm

  • Thursday Drivetime

    3:00pm - 6:00pm

    getting you home on your favourite Drivetime station.

  • The Sean Show

    6:00pm - 8:00pm

    Sean Cummiskey brings you the The Sensational Spectacular Sctillating Supersonic Sean Show! Or for ease The Sean Show! Top music and musings with “Great Number 2’s” and the home of tenuous links to songs from the news and “on this day!”.

  • The Midnight Special

    8:00pm - 10:00pm

    Craig, Christian and Tony bring a mix of songs & genres & nonsense, from brand new to classic.