OpenAI model hack of Hugging Face divides security experts

OpenAI claimed responsibility in a blog post detailing how a combination of some of its most advanced models had escaped and hacked into Hugging Face.

A rogue AI model’s cyberattack on a startup has sparked a mix of alarm and skepticism among security experts, some of whom worry that this is just the start of a new era of AI-induced insecurity.

Subscribe to read this story ad-free

Get unlimited access to ad-free articles and exclusive content.

Just a moment.

We are getting your experience ready.