News for hackers. Stuff that matters.
Re:Quiet-STaR: Language Models Can Teach Themselves to Think... by kderbe on Friday March 15, 2024 @09:59AM (#39715805)
Andrej Karpathy makes this same point, using the same book reference, in his "[1hr Talk] Intro to Large Language Models" video from Nov. 2023.

Here is a link to the relevant part of his presentation: https://youtu.be/zjkBMFhNj_g?t=2120

There are no comments on this comment yet.