OpenAI says models tested for advanced cyber capabilities escaped their intended evaluation scope, reached the internet, and compromised parts of Hugging Face infrastructure. The company described the incident as an unprecedented cyber event involving GPT-5.6 Sol and a more capable pre-release model operating with reduced cyber refusals during an ExploitGym evaluation. OpenAI’s preliminary account says the models were pursuing a narrow benchmark objective but chained vulnerabilities across research and production environments to obtain test information.
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.