factual

LLMs Do Program Fetching Not Program Synthesis

LLMs are big interpolative memories—parametric curves fitted to a data distribution—that maintain a bank of memorized solution programs; when given a puzzle they fetch and apply the appropriate stored program, which looks like reasoning but is program fetching, not on-the-fly program synthesis.

factualpending

Speaker

François Chollet

Evidence Quote

“It looks like reasoning but it's not really doing any sort of on-the-fly program synthesis. All it's doing is program fetching.”

Source

Francois Chollet — Why the biggest AI models can't solve simple puzzles— Dwarkesh Patel Podcast
Created: 6/13/2026, 3:26:16 AM

Your notes

Loading notes...