alt Hacker NewsThe distinction is that it's not 'predicting the next token'. Instead it's _determining_ the next token based on a prediction of its reward signal.
Replies
mannykannot • yesterday at 8:25 PM
Yes, but I think the same construction could also be used to characterize the first system; it determines the next move based on a prediction of its reward signal, where its reward signal is a measure of how likely it is that a grand master would make that move.
Like stanleykm, I found this analogy somewhat puzzling. On reflection, I think the author's point is this: the statistics of actual usage do not seem sufficient to produce a fluent LLM; it also takes reinforcement learning.
> _determining_ the next token based on a prediction
Also known as predicting.