You Have to Type It Out — Sympolymathesy, by Chris Krycho

The Mental Model FAQ

A summary of the conclusions from my Putting Mental Models to Practice series. What are mental models? How did mental models become so popular?

A Framework for Putting Mental Models to Practice

A Framework for Putting Mental Models to Practice is a series that examines the idea of putting Charlie Munger's Elementary Worldly Wisdom to practice in one's life in the pursuit of better decision making.

How to do hard things

A fully general system for learning to do things you currently find difficult, only somewhat tongue-in-cheek.

Mental Models: How to Train Your Brain to Think in New Ways

You can train your brain to think better. One of the best ways to do this is to expand the set of mental models you use to think. Let me…

The Busy Person's Guide to Thinking

Thinking better isn't about learning more; it's about doing a few simple things that really help create unstoppable progress.

Cognitive Load Theory and its Applications for Learning - Scott H Young

What makes learning hard? How can we make it easier? Cognitive load theory explains how we learn and how to do it better.

Keating — The Hyperteacher

Socratic AI that forces you to reconstruct understanding from memory. No hand-holding. No spoon-feeding. Free and open source.

Book Review: The Math Academy Way

Memorization is just knowing things

Thoughts on thinking | Hacker News

The process of forming expressions just is the process of conceptual and rational articulation (as per Brandom). Those who misunderstand this -- believing that concepts are ready made, then encoded and decoded from permutations of tokens, or, worse, who have no room to think of reasoning or conceptualization at all -- they will be automated away.

machines will never understand language

I thought language was too complicated for machines to understand, until I got sick. a lifelong, meandering journey of parsing, learning, and fixing my broken body.

The Triadic Mind: How Language Reveals the Limits of Human Cognition

Languages are the most complex symbolic systems humans have ever created. Yet children acquire them effortlessly, without formal…

François Chollet on Twitter / X

Eventually, much of AI will converge towards intuition-guided symbolic world modeling, i.e. deep learning-guided program synthesis. It is inevitable. Symbolic modeling lets a system construct a compact, reusable, highly generalizable mental model of a problem space using minimal…— François Chollet (@fchollet) July 2, 2026

Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!

Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thinking traces} -- implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solving a challenging problem, and as such can provide an interpretable window into the operation of the model's thinking process to the end user. In this position paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous -- it confuses the nature of these models and how to use them effectively, and leads to questionable research. We call on the community to avoid such anthropomorphization of intermediate tokens.

Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!

Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thinking traces} -- implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solving a challenging problem, and as such can provide an interpretable window into the operation of the model's thinking process to the end user. In this position paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous -- it confuses the nature of these models and how to use them effectively, and leads to questionable research. We call on the community to avoid such anthropomorphization of intermediate tokens.

afterword

Writing this handbook has been a process of not over-thinking it. In deciding to do it post-by-post, day-by-day, I practiced sharing as I went, posting to a ...