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.
OpenAI disclosed on Tuesday that it lost control of two AI models during a security test that ended in a breach of the open AI research platform Hugging Face.
Describing the incident as unprecedente… [+3264 chars]
Discussion (0)
No comments yet. Be the first to share your thoughts!
Join the Conversation
You need to be logged in to leave a comment.
Sign In Create Account