normative

Optimal model size for RL is a Pareto frontier balancing learning and inference

You must drink the bitter lesson and pay for a bigger model and more inference to get AGI, but there is a Pareto frontier: a one-parameter model is useless despite running fast and a 100T model is too slow with insufficient marginal learning benefit, so the optimal model size depends on current capabilities and RL environments, with inference cost now a major factor in the old training-data-vs-model-size allocation since RL requires generating many tokens.

normativepending

Speaker

Sholto Douglas

Evidence Quote

“What's the optimal model size of your current class of capabilities, and your current set of RL environments”

Source

Is RL + LLMs enough for AGI? — Sholto Douglas & Trenton Bricken— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:28:51 AM

Your notes

Loading notes...