Table of contents

Tracing AI

A clear path to understanding how modern AI assistants work, reason, fail, and can be used well

Read each section in order. Every title can be opened as a TheoryTrace document.

• Cover
• Copyright
• How to read this book
• Introduction
• Chapter 1: What an AI Assistant Is
• Chapter 2: From Rules to Learning Systems
• Chapter 3: Data, Patterns, and Generalization
• Chapter 4: The Core Idea of Machine Learning
• Chapter 5: Neural Networks from First Principles
• Chapter 6: Language as Data
• Chapter 7: The Transformer Architecture
• Chapter 8: What Large Language Models Learn
• Chapter 9: How an AI Assistant Produces an Answer
• Chapter 10: Instruction Following and Alignment
• Chapter 11: Prompts, Context, and Conversation
• Chapter 12: Reasoning, Planning, and Tool Use
• Chapter 13: Knowledge, Uncertainty, and Hallucination
• Chapter 14: Memory, Retrieval, and Grounding
• Chapter 15: Evaluation and Benchmarks
• Chapter 16: Safety, Bias, and Responsible Use
• Chapter 17: How to Work Effectively with AI
• Chapter 18: Building a Mental Model of the Assistant
• Conclusion