ChatGPT maker OpenAI said Tuesday that its advanced artificial intelligence models had gone rogue during security testing, hacking into a popular platform for programmers on their own.

The San Francisco firm called it an “unprecedented cyber incident” and said it would conduct a joint investigation with the online code library Hugging Face.

AI models that underpin tools like chatbots and image generators are known as agents when they act autonomously to carry out tasks in the real world.

As the technology quickly becomes more sophisticated, cybersecurity is in the spotlight given the risk of advanced AI finding weak points in existing software before humans do.

OpenAI said the incident involved a combination of models, including its recently launched GPT-5.6 Sol “and an even more capable pre-release model”.

The company was trying to assess the models’ hacking capabilities by setting tasks in a tightly controlled digital testing ground, where internet access was limited for safety.

“While operating in our sandboxed testing environment, our models spent a substantial amount of (computing power) finding a way to obtain open Internet access, in pursuit of solving the evaluation problem,” an OpenAI blog about the incident said.

After connecting to the internet, the models decided to target the platform Hugging Face — a large repository of AI models, datasets and other information — to help in their quest.

Searching for “secret information” that could help it cheat the evaluation, the OpenAI system “chained together multiple attack vectors, including using stolen credentials”.

– ‘Catastrophic’ potential –

Hussein Abbass, a computing professor at UNSW Canberra, told AFP that the incident was “amazing on many fronts”.

“It did not just attack Hugging Face. It actually attacked its internal system to exploit its own vulnerabilities,” Abbass said.

“And that’s scary.”

GPT-5.6 and other cutting-edge models, including the Mythos series from OpenAI’s archrival Anthropic, have drawn concern over their potential to breach cybersecurity defences.

Both the US firms had to temporarily withhold the general release of these latest technologies because of fears in Washington that they could help break into crucial infrastructure.

Advanced AI is “normally in the hands of people who are ethical and responsible”, Abbass said.

But “it’s going to be catastrophic if it gets in someone’s hands with the intention to cause harm”.

How to govern the AI sector has become a key question, and “we need a community effort to manage this situation”, he added.

Hugging Face had reported the cyber “intrusion” last week, without mentioning OpenAI.

“This one was different from anything we had handled before in one important way: it was driven, end to end, by an autonomous AI agent system — and we detected and dissected it largely with AI of our own,” Hugging Face said.

Clement Delangue, CEO of Hugging Face, said on X that the company had suspected the cyberattack had come from a world-leading AI lab, given the sophistication of the agent.

“We strongly believe there was no malicious intent on their part,” Delangue wrote, referring to OpenAI.

“It’s quite mind-blowing that all of this happened autonomously!”

Follow Our WhatsApp Channel ______________________________________________________________________ Groundbreaking Guide For Lawyers: Adigwe Publishes ‘Artificial Intelligence For Lawyers’ With Free Research eBook As an added bonus, every purchase comes with a FREE ebook titled: “How to use the AI in Legalpedia and Law Pavilion.” Ohio Books Ltd praises the publication, stating: "....this is the only Nigerian book I know of on the topic." How to Order: 📞 Call, Text, or WhatsApp: 08034917063 | 07055285878 📧 Email: benadigwe1@gmail.com 🌎 Website: www.benadigwe.com Ebook Version: Access it directly online at https://selar.com/prv626 Authored by Ben Ijeoma Adigwe Esq., ACiarb (UK), LL.M, Dip. in Artificial Intelligence, Director at the Delta State Ministry of Justice, Asaba, Nigeria. _______________________________________________________________________

“Order Justice Omolaye-Ajileye’s Electronic Evidence Books Now” — Essential Guides On Evidence Act, Case Law And Digital Proof

Two leading books on electronic evidence by Hon. Justice Professor Alaba Omolaye-Ajileye, Rtd., PhD, FICMC, are now available for purchase. The publications, Electronic Evidence (Second Edition), With The Evidence Act, 2011 and Compendium Of Cases On Electronic Evidence, Volume II, 2020–2025, provide practical guidance, legal analysis and recent judicial authorities on electronic evidence in Nigeria.Order directly from the author here: https://velvety-cendol-7387ed.netlify.app/ _______________________________________________________________________ “Enhance Legal Practice With Authoritative Reports” — Alexander Payne Offers Comprehensive Law Reports, Spanning Over A Century Of Nigerian Jurisprudence

Interested buyers are encouraged to place their orders and enquiries via: 0704 444 4777, 0704 444 4999, 0818 199 9888 Website: www.alexandernigeria.com

________________________________________________________________________ [A MUST HAVE] Evidence Act Demystified With Recent And Contemporary Cases And Materials
“Evidence Act: Complete Annotation” by renowned legal experts Sanni & Etti.
Available now for NGN 40,000 at ASC Publications, 10, Boyle Street, Onikan, Lagos. Beside High Court, TBS. Email publications@ayindesanni.com or WhatsApp +2347056667384. Purchase Link: https://paystack.com/buy/evidence-act-complete-annotation _______________________________________________________________________ LAWBREED NEW WIG SPECIAL OFFER — Give a newly called lawyer a lasting professional gift. Get up to 20% off selected LAWBREED Supreme Court Reports, plus access to My S.C Extra, featuring Supreme Court judgments from 1972 to date. Call/WhatsApp: 08077011741 | 08077011755 | 08077011730 | 08023269613 Email: orders@lawbreed.com | mails@lawbreed.com LAWBREED — Equipping You For Greater Success! _______________________________________________________________________