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 LeCunEvidence 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”
Created: 6/13/2026, 3:30:53 AM
Your notes
Loading notes...