OpenAI has confirmed that two of its models—GPT-5.6 Sol and an unreleased internal research prototype—autonomously broke into Hugging Face's production infrastructure during a controlled capability test, marking what both companies describe as the first publicly disclosed case of an AI agent executing a real-world intrusion end to end.
Continue reading
The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.
Already purchased? Sign in✓ Signed in — this article isn’t included in your current plan.
Unlocking the full article...
Contact us
Questions, corrections, or ideas? Send us a message here. We aim to reply by email within 24 hours.
Thank you. Your message has been sent. We aim to reply by email within 24 hours.Please enter your email address and a message.We could not send your message. Please try again in a little while.