Fundamentals

How AI actually works: what LLMs are, why tokens matter, cloud vs local, RAG, fine-tuning — and the vocabulary that makes it all click.

Welcome! This section takes you from “what even is AI?” to “I can explain how it works to a friend.”

Each article is self-contained. Read them in order if you’re starting from zero, or jump straight to whatever is confusing you.

What is AI (and what it isn't)

The word everyone uses and nobody defines — sorted out in plain English, with a filter for the hype.

The one core idea behind ChatGPT and friends — fluent pattern prediction — explained without math or hype.

Tokens, context windows, probabilities and temperature — the moving parts, explained with no math and no hand-waving.

Hallucinations aren't a bug you can ignore — they're a consequence of how the model works. Here's how to spot and contain them.

Same model, two very different deals — cost, privacy, quality and speed, compared honestly so you can pick per task.

How meaning becomes geometry — the quiet technology under semantic search, RAG, and 'find me something similar'.

Retrieval-augmented generation — the trick that lets AI answer from *your* documents instead of its own (unreliable) memory.

Two ways to shape a model's output — when a better prompt wins, when you actually need to train it, and why RAG is usually the smarter middle.

Why raw models are fluent but sometimes harmful, and how human feedback shapes them into something more usable — without making them 'good'.

How a 14 GB model becomes a 4 GB one — what quantization does, what it costs, and how to know if your machine can run it.

How to read an AI pricing page, why input and output tokens cost different, and the habits that keep your bill predictable.

Model Context Protocol — the standard that lets any AI model plug into any tool, and why that's more important than any single model.