Inference costs dominate training costs when serving models to billions of users or trillions of tokens, and within training itself, reinforcement learning (which is a wrapper on inference) is starting to exceed the compute requirements of pre-training.

factualpending

Speaker

Tanishk

Evidence Quote

“not only are inference costs dominating training costs, but even within training, RL is starting to exceed the compute requirements of pre-training”

Source

Inference, Diffusion, World Models, and More | YC Paper Club— Y Combinator
Created: 8/12/2026, 6:25:34 PM

Your notes

Loading notes...