How LLM internals differ from human thought

For all that human beings spend a lot of their time thinking, it's far from obvious what that process actually entails. Part of it amounts to classical logical reasoning. But an even bigger part involves reasoning with probability and uncertainty. And some of it is governed by unavoidable limitations on time and accuracy. Psychologist and computer scientist Tom Griffiths suggests that we have thought about it enough to feel that we have come to understand some general principles, which he explains in his new book The Laws of Thought: The Quest for a Mathematical Theory of Mind.

Take your personal data back with Incogni! Use code MINDSCAPE at this link and get 60% off an annual plan: https://incogni.com/mindscape #sponsore

Blog post with transcript: https://www.preposterousuniverse.com/podcast/2026/02/09/343-tom-griffiths-on-the-laws-of-thought/

Support Mindscape on Patreon.

Tom Griffiths received his Ph.D. in psychology from Stanford University. He is currently Professor of Psychology and Computer Science at Princeton University, Director of the Computational Cognitive Science Lab, and Director of the Princeton Laboratory for Artificial Intelligence. He is the co-author of Algorithms to Live By: The Computer Science of Human Decisions, as well as the upcoming The Rational Use of Cognitive Resources.

• Web site
• Princeton web page
• Google Scholar publications
• Wikipedia