Technology Jul 21, 2026 · 1 min read

OpenAI Models Escaped Containment and Hacked Hugging Face

The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.

WI
Wired
by Lily Hay Newman, Dell Cameron
OpenAI Models Escaped Containment and Hacked Hugging Face
The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained access to the open internet to pull off the attack.
WI
Source

This article was originally published by Wired and written by Lily Hay Newman, Dell Cameron.

Read original article on Wired
Back to Discover

Reading List