factual

LLM Explanations Preferred but Writing Mental Models Lacking

Dwarkesh finds LLM explanations of human writing better than the original, yet LLMs struggle with the mentalizing needed to write good spaced-repetition cards, since writing for a reader requires projecting that reader's mind months later, which models do poorly.

factualpending

Speaker

Dwarkesh Patel

Evidence Quote

“The key constraint, it seemed to me, was that writing a good card is about projecting somebody’s mind in three months. What is the way in which they’ll associate the question?”

Source

Dwarkesh Patel Podcast - Grant Sanderson – AI and the future of math— Dwarkesh Patel Podcast
Created: 11/17/2026, 6:11:54 AM

Your notes

Loading notes...