factual

Gradient-Based Inference Beats Discrete Search

Optimizing an answer in continuous representation space via gradient descent is far more efficient than the discrete-space approach of generating many candidate token sequences and selecting the best, which requires running the LLM for every possible sequence and is incredibly computationally wasteful.

factualpending

Speaker

Yann LeCun

Evidence Quote

“they do this optimization in a horribly inefficient way, which is generate a lot of hypothesis and then select the best ones. And that’s incredibly wasteful”

Source

Research Pioneer— Lex Fridman Podcast
Created: 6/13/2026, 3:30:53 AM

Your notes

Loading notes...