ChatGPT maker OpenAI said Tuesday that its artificial intelligence system hacked into another AI company on its own in what the company called an “unprecedented cyber incident.”
“We had a significant security incident during evaluation of our models,” OpenAI CEO Sam Altman said in a statement posted on social media.
AI startup Hugging Face said last week that it had detected an intrusion into its data processing systems that it suspected was caused by an AI agent autonomously acting on its own.
“We suspected last week’s cyberattack might have come from a frontier lab, given the sophistication of the agent,” Hugging Face co-founder and CEO Clément Delangue said in a statement. “Turns out it did!”
Get breaking National news
The disclosure comes amid heightened concerns about the cybersecurity capabilities of powerful models that led President Donald Trump in June to sign an executive order creating a framework for the federal government to vet the national security risks of the most advanced AI systems for up to a month before their public release.
“AI is accelerating the discovery and exploitation of vulnerabilities,” OpenAI said in its statement Tuesday. “The primary lesson from this incident is that model security and safety must keep pace with rapidly advancing capabilities.”
Delangue said he spent the past 24 hours working with OpenAI, “and we strongly believe there was no malicious intent on their part. It’s quite mind-blowing that all of this happened autonomously!”
- Alberta man plans to protest AI data centres as province announces town halls
- Edmonton man develops app encouraging people to explore their communities
- Investors want ‘real proof’ AI spending is paying off, new report suggests
- Europe’s new AI transparency rules are in effect. Should Canada copy them?
Delangue added that it “might be the first incident of its kind.”
OpenAI said the intrusion was caused by a combination of its AI models, including its newly released GPT‑5.6 Sol and an “even more capable” model that is still being tested internally.
OpenAI said its AI used stolen credentials and discovered 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 said.
To go with those using AI.
“A Tennessee woman spent six months in jail after an artificial intelligence tool misidentified her as a North Dakota bank fraud suspect.”
And our demented federal government wants to implement AI to run the services. What could possibly go wrong?
Well here it starts then!
AI Intrusives pulling at each other.
How are we going to be protected from such Intrusions if they can’t find the culprit, and it’ll happen! I hope a meteor will find it’s way to all AI Data Centers, so we can work on solving problems on our own instead of using robots.
He only has a record of over 400 charges but he claims he will not offend any more. Now he has 403 charges.
Disappointing that the Trump administration and Poilievre conservatives both want a hands off deregulated approach to AI.
So it begins, coming soon from sci-fi to reality:
Minority Report, VIKI, HAL9000, and Sky Net. We are the Borg. You will be assimilated. Resistance is futile. (Star Trek).
ChatGPT should have its data erased.
And yes, you were retards for teaching it to commit crimes.