Reinforcement learning could theoretically continue to improve with scale, but this continued scaling masks a deeper need for more data-efficient approaches.

factualpending

Speaker

Unidentified Speaker — Yann LeCun Says LLMs Have 2 Years Left… [85M0cTnNKCI]

Evidence Quote

“if you continued scaling RL...you get more, you know, you continue getting very impressive results. But there's just got to be some like way more efficient way to do this”

Source

Yann LeCun Says LLMs Have 2 Years Left…— AI Copium
Created: 8/12/2026, 6:06:44 PM

Your notes

Loading notes...