🧩 Mental Models - CWhiting · Scour

A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Execution Topology 🤖LLM Agents

Stop Fixing Your Prompts — Fix Your Thinking Style Instead (A Claude Code Experiment) 💻Coding Agents

bestaiweb.ai·1d·DEV

The Sequence AI of the Week #863: The Model is the Interface: Inside Thinking Machines' Interactive Models 🤖Anthropic AI

substackcdn.com·13h·Substack

brendanddev/explaind: Cognitive steering layer for Gemma 4, structured prompt physics for shaping reasoning trajectories without fine-tuning. ✍️Prompt Engineering

github.com·1h·DEV

Context graphs and decision traces to the rescue 🧠Context Engineering

infoworld.com·1d

Learn AI Layer by Layer 🎯AI Training

learnai.robennals.org·5d

The 3 Levels Of Thinking And How To Design For Them 💡Design Thinking

elearninginfographics.com·6d

People Are Altering Their Thinking To Think How They Think That AI Thinks 🔮Speculative AI

GIM: Evaluating models via tasks that integrate multiple cognitive domains 📊Model Evals

Beyond Rational Illusion: Behaviorally Realistic Strategic Classification 🧠AI Models

What Really Improves Mathematical Reasoning: Structured Reasoning Signals Beyond Pure Code 🔍Logic Puzzles

Emergence of Frontier Superposition: M\"obius attractor and Cascade Supervision 🌍World Models

Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs 🔍Logic Puzzles

Rethinking How to Remember: Beyond Atomic Facts in Lifelong LLM Agent Memory 🧠Context Engineering

Reasoning Can Be Restored by Correcting a Few Decision Tokens 📜Constitutional AI

Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay 🖼️Dual Coding

MANTA: Multi-turn Assessment for Nonhuman Thinking & Alignment 📜Constitutional AI

Self-supervised Hierarchical Visual Reasoning with World Model 🌍World Models

Computational Thinking Development in AI Agent Creation_A Mixed-Methods Study 🤖Agentic AI

LPG: Balancing Efficiency and Policy Reasoning in Latent Policy Guardrails 🧠Context Engineering

Log in to enable infinite scrolling