When we have generalization in deep learning models, it results from human researchers sculpting representations; gradient descent will solve the problem but won't make you generalize well to new data.

causalpending

Speaker

Richard Sutton

Evidence Quote

“Gradient descent will not make you generalize well. It will make you solve the problem.”

Source

Richard Sutton – Father of RL thinks LLMs are a dead end— Dwarkesh Patel
Created: 8/11/2026, 6:36:28 AM

Your notes

Loading notes...