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.
Story detail
Read the key details here, then continue on the original publisher.
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.
Join our channel to receive the latest headlines and breaking stories as soon as they are published.
Comments (0)
Join the conversation. Comments are rate-limited, secured, and GDPR-compliant.
No comments yet. Be the first to share your thoughts!