pacific-design.com · v2 · ongoing
Artificial intelligence,
section by section.
Pacific Design is a working map of AI — how the models actually work, how to use them well, and where the field is going. It grows one section at a time until the whole territory is covered. Six sections are live; the rest are in training.
the pathSix live sections, in reading order
The order is a path, not a pile — each section leans on the ones before it. Jump anywhere; the numbers tell you what's assumed.
- What a neural network is
- How models learn
- The kinds of learning
- Overfitting & generalization
- Evaluating models
- Transformers & attention
- Tokens & tokenization
- How LLMs are trained
- Context windows & memory
- Hallucination
- Scaling laws & small models
- What makes an agent
- Tool use & function calling
- MCP: a standard for tools
- Multi-agent systems
- Evaluating & containing agents
roadmapThe whole territory
This project will address every major section of artificial intelligence. Status is honest: live is published, in training is being written next, queued is committed but not started.
- Machine Learning Foundations
- Large Language Models
- Prompt Engineering
- AI Agents
- RAG & Embeddings
- Generative Media
- Computer Vision
- Speech & Audio
- AI Safety & Alignment
- Reinforcement Learning
- Robotics & Embodied AI
- AI Infrastructure & MLOps
- Policy & Regulation
- History of AI
aboutWhat this is
A reference, not a feed. Entries are short enough to read in one sitting and precise enough to argue with. Illustrations are AI-generated — this is a site about the technology, made partly with it. Plain HTML, no accounts, nothing watching you read.