causal

LLMs Model Human Output Not True World

LLMs do not build a true world model that predicts how the environment changes in response to actions; instead they model what a human would say next, relying on human-derived concepts, so an LLM trained on 1900 data could not derive relativity from scratch.

causalpending

Speaker

Dwarkesh Patel

Evidence Quote

“What these LLMs learn from training is not a true world model (which tells you how the environment changes in response to different actions). Rather, they are building a model of what a human would say next.”

Source

Some thoughts on the Sutton interview— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:28:01 AM

Your notes

Loading notes...