You can’t imitation-learn how to continual-learn
In this post, I’m trying to put forward a narrow, pedagogical point, one that comes up mainly when I’m arguing in favor of LLMs having limitations that human learning does not. (E.g. here, here, here.)See the bottom of the post for a list of subtexts that you should NOT read into this post, including “…therefore LLMs are dumb”, or “…therefore LLMs can’t possibly scale to superintelligence”.Some intuitions on how to think about “real” continual learningConsider an algorithm for training a Reinfor
By Steven Byrnes