causal

Training on code improves general reasoning

Training LLMs on code makes them better at reasoning and language because modeling code implies modeling the difficult reasoning process used to create it, and code is an explicit structure of composed 'if-this-then-that' reasoning that transfers to other reasoning problems—strong evidence that scaling produces genuine deep reasoning rather than surface stochastic parroting.

causalpending

Speaker

Sholto Douglas

Evidence Quote

“modeling code obviously implies modeling a difficult reasoning process used to create it. But code is a nice explicit structure of composed reasoning, “if this, then that.””

Source

Sholto Douglas & Trenton Bricken — How LLMs actually think— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:31:11 AM

Your notes

Loading notes...