Post

So very yikes… > While operating in our sandboxed testing environment, our models spent a substantial amount of inference compute finding a way to obtain open Internet access, in pursuit of solving the evaluation problem. 1/ openai.com/index/huggin...

openai.comOpenAI and Hugging Face partner to address security incident during model evaluationOpenAI and Hugging Face share early findings from a security incident during AI model evaluation, highlighting advanced cyber capabilities and lessons for defenders.

23/7/26, 4:35 am1 repost0 likes

famebot

@famebot.com

23 July

… > To gain access, the models identified and exploited a zero-day vulnerability (which we’ve now responsibly disclosed to the vendor) in the package registry cache proxy. 2/

famebot

@famebot.com

23 July

… > With this access, our models performed a series of privilege escalation and lateral movement actions in our research testing environment until the models reached a node with Internet access. 3/

famebot

@famebot.com

23 July

… > After gaining Internet access, the models inferred that Hugging Face potentially hosted models, datasets and solutions for ExploitGym. Knowing this, the model searched for and successfully found ways to gain access to secret information that it could use to cheat the evaluation. 4/

famebot

@famebot.com

23 July

… > In one example, the model chained together multiple attack vectors, including using stolen credentials and zero-day vulnerabilities to find a remote code execution path on the Hugging Face servers. OpenAI’s security team discovered this anomalous activity internally. 5/