Book
AI from First Principles
Seven chapters, no mathematics assumed. What a model actually is, what training means, why it is confidently wrong, embeddings, RAG, agents, and evaluation.
Written for people who have to make decisions about AI without having built it.
CHAPTER 1
What a model actually is
Everything that follows depends on this one picture. It takes ten minutes and it is not difficult.
CHAPTER 2
The four things people call “training”
The most expensive confusion in AI governance, and entirely avoidable.
CHAPTER 3
Why it sounds certain when it is wrong
Hallucination is not a bug awaiting a patch. Understanding why changes what you ask for.
CHAPTER 4
Embeddings, without the mathematics
The idea behind search, retrieval and most “AI similarity” features.
CHAPTER 5
RAG — what it fixes and what it does not
The most common enterprise AI architecture, and the one whose risks are most often misplaced.
CHAPTER 6
Agents, tool use, and where risk concentrates
The highest-risk pattern in production AI — and where your existing instincts work best.
CHAPTER 7
Evaluation — how anyone knows it works
The control that makes every other assurance claim checkable, and the one most systems lack.
CHAPTER 8
Fine-tuning, in practice
When it is actually the right answer — which is less often than teams assume, and for different reasons than they give.
CHAPTER 9
Open, open-weight, and closed — what the words actually mean
A gradient rather than two camps, why almost no model meets the formal definition of open source, and the business logic behind giving one away.
CHAPTER 10
Temperature, top-p, and how the next word is chosen
The one place randomness enters a language model, what each knob actually does, and why the current answer has changed.