causal

Pretraining Builds Concepts, RLHF Shapes Behavior

Pretraining on next-word prediction across trillions of tokens forces a model to store many concepts, and a second stage of RLHF on helpful, honest examples turns that base into an assistant, with the second stage using far less data and compute.

causalpending

Speaker

Gavin

Evidence Quote

“to even get it right 18% of the time, you have to have a huge number of concepts stored within that machine.”

Source

Gavin Uberti - Real-Time AI & The Future of AI Hardware - [Invest Like the Best, EP.356]— Invest Like the Best
Created: 11/17/2026, 12:35:53 PM

Your notes

Loading notes...