This is a special post for quick takes by Jv Thunder. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
I will be doing a PhD on UQ in NTU Singapore, and especially interested on the topic of epistemic uncertainty in AI. I have several vague things in mind, but I am curious to hear what people have done or heard on this topic specifically for AI Safety. For example, I know Infra-Bayesianism research have pretty good amount of connections to uncertainty and even use imprecise probability.