Super Data Science: ML & AI Podcast with Jon Krohn cover image

969: The Laws of Thought: The Math of Minds and Machines, with Prof. Tom Griffiths

Super Data Science: ML & AI Podcast with Jon Krohn

00:00

Autoregression shapes LLM outputs

Tom explains how next-token training biases LLMs toward high-probability tokens and odd counting behavior.

Play episode from 15:35
Transcript

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app