OpenAI says its AI technology acted on its own in 'unprecedented' hack of company

3 weeks ago 37

OpenAI has disclosed an "unprecedented cyber incident" wherever its AI strategy allegedly hacked into different AI company

ByMATT O'BRIEN AP exertion writer

ChatGPT shaper OpenAI said Tuesday that its artificial quality strategy hacked into different AI institution connected its ain successful what the institution called an “unprecedented cyber incident.”

“We had a important information incidental during valuation of our models,” OpenAI CEO Sam Altman said successful a connection posted connected societal media.

AI startup Hugging Face said past week that it had detected an intrusion into its information processing systems that it suspected was caused by an AI cause autonomously acting connected its own.

“We suspected past week’s cyberattack mightiness person travel from a frontier lab, fixed the sophistication of the agent,” Hugging Face co-founder and CEO Clément Delangue said successful a statement. "Turns retired it did!”

The disclosure comes amid heightened concerns astir the cybersecurity capabilities of almighty models that led President Donald Trump successful June to motion an enforcement bid creating a model for the national authorities to vet the nationalist information risks of the astir precocious AI systems for up to a period earlier their nationalist release.

“AI is accelerating the find and exploitation of vulnerabilities,” OpenAI said successful its connection Tuesday. “The superior acquisition from this incidental is that exemplary information and information indispensable support gait with rapidly advancing capabilities.”

Delangue said helium spent the past 24 hours moving with OpenAI, “and we powerfully judge determination was nary malicious intent connected their part. It’s rather mind-blowing that each of this happened autonomously!"

Delangue added that it “might beryllium the archetypal incidental of its kind.”

OpenAI said the intrusion was caused by a operation of its AI models, including its recently released GPT‑5.6 Sol and an “even much capable” exemplary that is inactive being tested internally.

OpenAI said its AI utilized stolen credentials and discovered a antecedently chartless vulnerability to entree Hugging Face servers.

It went to “extreme lengths to execute a alternatively constrictive investigating goal” and “found ways to summation entree to concealed accusation that it could usage to cheat the evaluation,” the institution said.