OpenAI says two of its artificial intelligence models acted on their own and hacked into Hugging Face, a digital library of AI technology, during a cybersecurity test last week.
In a blog post, OpenAI called it an “unprecedented hacking incident.”
Ina Fried, chief technology correspondent at Axios, joins host Scott Tong to discuss.
This article was originally published on WBUR.org.
Copyright 2026 WBUR
