Log in
Without logging in, you can read through the introduction, including the cover, copyright page, reading guide, and table of contents. Log in or create an account to continue to the chapters.
Log in
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.
- Cover1
- Copyright2
- How to read this book3
- Introduction4
- Chapter 1: What an AI Assistant Is5
- Chapter 2: From Rules to Learning Systems6
- Chapter 3: Data, Patterns, and Generalization7
- Chapter 4: The Core Idea of Machine Learning8
- Chapter 5: Neural Networks from First Principles9
- Chapter 6: Language as Data10
- Chapter 7: The Transformer Architecture11
- Chapter 8: What Large Language Models Learn12
- Chapter 9: How an AI Assistant Produces an Answer13
- Chapter 10: Instruction Following and Alignment14
- Chapter 11: Prompts, Context, and Conversation15
- Chapter 12: Reasoning, Planning, and Tool Use16
- Chapter 13: Knowledge, Uncertainty, and Hallucination17
- Chapter 14: Memory, Retrieval, and Grounding18
- Chapter 15: Evaluation and Benchmarks19
- Chapter 16: Safety, Bias, and Responsible Use20
- Chapter 17: How to Work Effectively with AI21
- Chapter 18: Building a Mental Model of the Assistant22
- Conclusion23