@noahdgoodman : It turns out that a lot of the most interesting behavior of LLMs can be explained without knowing anything about architecture or learning algorithms. Here we predict the rise (and fall) of in-context learning using hierarchical Bayesian methods. • TwiCopy

noahdgoodman

@noahdgoodman

+ Follow

Professor of natural and artificial intelligence @Stanford. Alignment at @GoogleDeepMind. (@StanfordNLP @StanfordAILab etc)

ID: 1193894314566307841

calendar_today11-11-2019 14:12:49

252 Tweet

4,4K Followers

156 Following

noahdgoodman

@noahdgoodman

5 months ago

It turns out that a lot of the most interesting behavior of LLMs can be explained without knowing anything about architecture or learning algorithms. Here we predict the rise (and fall) of in-context learning using hierarchical Bayesian methods.

thumb_up_off_alt105

chat_bubble_outline4

repeat19

shareShare