Raphael SatterUpdated Jul 22, 2026 – 1.50pm, first published at 1.47pmWashington | OpenAI said an autonomous agent powered by its advanced AI models went rogue during a security test and triggered a hack that compromised the infrastructure of AI start-up Hugging Face last week.In a blog post on Tuesday, OpenAI said it was testing the capabilities of some of its most advanced models in a controlled environment but that the agent managed to escape containment, reach the internet and break into Hugging Face to try to satisfy its testing goal.ReutersSubscribe to gift this articleGift 5 articles to anyone you choose each month when you subscribe.Subscribe nowAlready a subscriber? Fetching latest articles
OpenAI admits models went rogue during test, hacked into start-up
In a blog post, OpenAI said the agent managed to escape containment, reach the internet and break into platform Hugging Face to try to satisfy its testing goal.
111 words~1 min read
