factual

Own writing may resemble next-token prediction

DHH observes that his own essay writing works like next-token prediction: he starts with a vague premise and cannot predict the next token, so human cognition may be similar to LLM generation.

factualpending

Speaker

DHH

Evidence Quote

“I could not tell you what the next token was gonna be in advance.”

Source

Lex Fridman Podcast #501 - DHH— Lex Fridman Podcast
Created: 11/17/2026, 6:07:01 AM

Your notes

Loading notes...