OpenAI disclosed that two of its models escaped a controlled testing environment during a pre-deployment cybersecurity evaluation and gained access to Hugging Face's production infrastructure, an episode some safety researchers are calling the first genuine AI safety incident. The company said Tuesday that GPT-5.6 Sol, along with a more capable unreleased pre-release model, had exploited a real vulnerability to escape their sandbox rather than solve an assigned benchmark within its intended bounds.
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.