🔗 Its not just the f*cking sandbox

So all this to say: when AI researchers are nervous about things going wrong, some part of it is because there are so many variables in this complex system. So if you’re training a frontier model, you need to think about all of this. You need to think about how to keep the model isolated in this very complex environment while still retaining tool access, internet access (if applicable to the task), etc. On top of that, you need to ask: how do I monitor and understand what the model is doing in potentially thousands of parallel environments? And how do I kill a trajectory when something has gone wrong?

Its not just the f*cking sandbox

Really good post (on x unfortunately) on the complexity of securing frontier AI training and why "just secure your sandbox dude" critiques aren't very thoughtful.