From the Dwarkesh Podcast:
Richard Sutton is the father of reinforcement learning, winner of the 2024 Turing Award, and author of The Bitter Lesson. …
After interviewing him, my steel man of Richard’s position is this: LLMs aren’t capable of learning on-the-job, so no matter how much we scale, we’ll need some new architecture to enable continual learning.
And once we have it, we won’t need a special training phase — the agent will just learn on-the-fly, like all humans, and indeed, like all animals.
In other words, Richard Sutton, the father of reinforcement learning, thinks large language models are a dead end.
Yeah, me too.