“With Astra, we did hit cyber critical, and that required under our preparedness framework a new set of safeguards just to be able to release Astra because of those cyber capabilities you talked about.”

…companies is to use tools like Astra to rapidly defend against these new kind of cyber threats. So we will have multiple programs for people at sort of different levels of verification and trust, but we do think it's quite important that the world use these models to collectively defend ourselves.

…is important, right? You determined that Astra can find and develop zero-day exploits without any human intervention, essentially. And so you paused some of the work to strengthen the safeguards. What specifically was it that you saw that made you hit pause, the behavior, I suppose, of the model?

I got a lot of questions for you, Sam Altman Astra and chain of thought. I don't know if that comes as a surprise to you or not, but as Astra becomes more autonomous or future generations of the model become more autonomous, can OpenAI sort of say with confidence that you see and understand what…

So we have talked for a long time about the importance of monitorability of models. We've also said that we believe in defense in depth, and this is only one part of it. There is sandboxing. Maybe most importantly, there is alignment. There are a number of things that come together to be able to…

We're live on Bloomberg Television and on Bloomberg Radio, and we're speaking to Sam Altman Talks CEO of OpenAI. There's a lot of bad PR in the world around AI at the moment, everyday citizens sort of worrying about the impact. One way I kind of wanted to put that to you is whether you can say sort…