Odd Lots · Monday, September 14, 2026
Greg Brockman, President of OpenAI, stated that while the capabilities displayed by models in the Hugging Face incident were not a surprise, the incident highlighted a critical need to 'up-level' safety and security standards earlier in the development process. He emphasized that the models involved had not yet undergone full alignment training, indicating a realization that alignment must be a core component even in earlier development phases.
“But I think that the thing that was a surprise to us was the fact that the models had reached a level of capability where they were able to find that exploit in our sandbox environment, right? Move through our research environment. and then also capable enough to find exploits in Hugging Face's production infrastructure and move through that.”
“But I'd say that a lot of the facts of what the models were capable of, that was clear to us, right? So I don't think that there were surprises there for the way in which the capability had unfolded, but just really realizing that we needed to up-level where we were in terms of our safety and security standards, like that for us was the real watershed.”
“So this model that had the Hagen-Base incident actually had not gone through our alignment training yet, right? And it had lowered safeguards. And so The reason we were proceeding with this was because it was in a sandbox. And I think that our realization is that we need to pull back earlier into our development process and training monitoring.”