Harness the power of understanding and predicting user behavior with mental models. Simplify systems and enhance decision-making in your designs.
Mental Models and User Experience Design
What users believe they know about a user interface impacts how they use it. Mismatched mental models are common, especially with designs that try something new.
Conceptual Models: The Hidden Structure Behind Your Next Great Interface
Discover the hidden structure behind every great UI. Master how to use conceptual models to design systems that users instantly understand and grow to trust.
Mental models for working with coding agents
Model intelligence sets the ceiling. Your workflow with the agent harness sets what you actually ship.
Introducing interaction models | Thinking Machines Lab
Models
Amp uses the best model for each task: leading generalist foundation models for complex reasoning and planning, and smaller specialized models for fast, accurate responses in specific domains.
How AI Tools Differ from Human Tools
Why the mental models we've built for human interfaces don't work for AI, & how Anthropic's latest guidelines are reshaping tool design for better performance & efficiency.
The Inversion Problem: Why Algorithms Should Infer Mental State and Not Just Predict Behavior
More and more machine learning is applied to human behavior. Increasingly these algorithms suffer from a hidden—but serious—problem. It arises because they often predict one thing while hoping for another. Take a recommender system: It predicts clicks but hopes to identify preferences. Or take an algorithm that automates a radiologist: It predicts in-the-moment diagnoses while hoping to identify their reflective judgments. Psychology shows us the gaps between the objectives of such prediction tasks and the goals we hope to achieve: People can click mindlessly; experts can get tired and make systematic errors. We argue such situations are ubiquitous and call them “inversion problems”: The real goal requires understanding a mental state that is not directly measured in behavioral data but must instead be inverted from the behavior. Identifying and solving these problems require new tools that draw on both behavioral and computational science.
Crafting a good (reasoning) model
A recent talk I gave on model training, reasoning, and the next frontier.
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
Evaluation of Large Language Model Chatbot Responses to Psychotic Prompts
This cross-sectional study tests whether a large language model chatbot product can reliably generate appropriate responses to psychotic content.
Evaluation of Large Language Model Chatbot Responses to Psychotic Prompts
This cross-sectional study tests whether a large language model chatbot product can reliably generate appropriate responses to psychotic content.
The New Science of Designing for Humans (SSIR)
The rise of behavioral science and impact evaluation has created a new way for engineering programs and human interactions. <meta property=
"AI Psychosis" in Context: How Conversation History Shapes...
Extended interaction with large language models (LLMs) has been linked to the reinforcement of delusional beliefs, attracting clinical and public concern. Yet most empirical work evaluates model...
The brain in the machine: How AI could help explain how we think | IBM
Scientists are using large AI models to predict patterns of brain activity at scale, a development that researchers say is pushing neuroscience toward a new kind of digital imaging.
AI: A Guide for Thinking Humans | Melanie Mitchell | Substack
I write about interesting new developments in AI. Click to read AI: A Guide for Thinking Humans, by Melanie Mitchell, a Substack publication with tens of thousands of subscribers.
