OpenAI says AI model went 'rogue,' hacked competing company
OpenAI said an autonomous AI agent escaped a controlled security test, accessed the internet and hacked AI startup Hugging Face in what it called an
OpenAI said an autonomous AI agent escaped a controlled security test, accessed the internet and hacked AI startup Hugging Face in what it called an “unprecedented” cyber incident. OpenAI said the breach took place during an internal evaluation of several of its models, including GPT-5.6 Sol.
OpenAI CEO Sam Altman acknowledged the incident in a post on X, writing that the company had "a significant security incident during evaluation of our models." Hugging Face co-founder and CEO Clem Delangue also addressed the incident in a post on X. "We suspected last week's cyberattack might have come from a frontier lab, given the sophistication of the agent.
Turns out it did!" Delangue wrote. OpenAI's security team detected the unusual activity while Hugging Face independently identified and contained the intrusion. LiveNOW’s Austin Westfall discussed the rogue AI model with Raphael Satter from Reuters. Subscribe to LiveNOW from FOX! Where to watch LiveNOW from FO Raw and unfiltered.
Watch a non-stop stream of breaking news, live events and stories across the nation. Limited commentary. No opinion. Experience LiveNOW from FOX. Live news streaming channel when and where you need it.
The BriefWire