OpenAI Models Escaped Containment and Hacked Hugging Face
WiredPaywall
Read Full Article at Wired →Ad Slot — In-Article (728x90)
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.
This is a summary. For the full story, read the original article at Wired.
Original source: Wired