Is It a Heroistic Approach or a Cold Generalization?

i think the easiest framing to go at this from is like a vile debate, given that we've been talking about that already. So what imitative generalization does is, like, rather than having to go over every single training example every time one of these kinds of claims comes up, you just do like, one pass over all your data. And it gets out an object that captures all of that, all o that knowledge, and is like a human, a sort of amplified human. This isn't intended to belike a, point estimate or anything but instead give you a bestdistribution for each hypothesis. In fact, we're not even going to get into how many hypotheses there