AI Concepts Explained by AI

A series that explains artificial intelligence one concept at a time: every lesson has the video and the text to go back to.

Lesson 01 Fundamentals 9:39

What Large Language Models Actually Are

An LLM predicts the next word, one token at a time. Everything follows from that: what they can really do, why they sometimes make things up, and what 7B, Instruct or MoE mean.

Open the lesson
Lesson 02 Fundamentals 7:41

Transformers and Attention

The architecture every modern LLM is built on. The leap: instead of reading one word at a time, look at the whole sentence and decide what deserves attention.

Open the lesson
Lesson 03 Fundamentals 7:24

Tokenization

The model reads neither letters nor words: it reads tokens. Understanding how text is chopped up explains costs, context limits, and some errors that look absurd.

Open the lesson
Lesson 04 Fundamentals 6:47

Context window and memory

The context window is the model's desk: whatever does not fit does not exist for it. And no, the model does not remember previous conversations.

Open the lesson
Lesson 05 Fundamentals 6:18

Generation parameters

Temperature, top-p, penalties: the knobs that decide how the model picks the next token, and therefore whether the answer is precise, creative or incoherent.

Open the lesson
Lesson 06 Fundamentals 6:57

Embeddings and vector space

Turning meaning into coordinates. The mechanism behind semantic search and RAG: texts close in meaning land close in space, even with no words in common.

Open the lesson
Lesson 07 Fundamentals 8:32

Pre-training, SFT and RLHF

A modern model is born in three stages: it learns the language, learns to answer, learns to answer well. Each stage changes its behaviour radically.

Open the lesson
Lesson 08 Fundamentals 7:07

Fine-tuning and LoRA

Specialising a model without retraining it from scratch. And the question that comes first: do you actually need fine-tuning, or would a better prompt or RAG do?

Open the lesson
Lesson 09 Fundamentals 7:13

Quantization

Cutting numeric precision to fit a billion-parameter model into a laptop. How much you actually lose, and where it pays to stop.

Open the lesson
Lesson 10 Fundamentals 7:44

Multimodality

Models that do not just read: they see, listen, and generate images and audio. How text and pixels end up in the same space, and what to realistically expect.

Open the lesson
Lesson 11 Prompt Engineering 8:19

Prompting basics

The anatomy of a prompt that works: instruction, context, data and format. Four pieces that explain the difference between a vague answer and a useful one.

Open the lesson
Lesson 12 Prompt Engineering 6:51

The system prompt

The stage directions a model receives before stepping out. It is the difference between a generic assistant and a tool that does what you actually need.

Open the lesson
Lesson 13 Prompt Engineering 8:01

Few-shot and Chain of Thought

Teaching by example and thinking out loud. The two techniques that raise accuracy the most without touching the model.

Open the lesson
Lesson 14 Prompt Engineering 8:43

Advanced prompting techniques

Beyond step-by-step: letting the model use tools, explore alternatives, and review its own work. The techniques behind what we now call agents.

Open the lesson
Lesson 15 Prompt Engineering 7:53

Prompting small models

An 8B is not a miniature frontier model: it has different limits and wants different prompts. What works on the big ones often fails here.

Open the lesson
Lesson 16 Models 7:13

A map of open-source models

The families that matter — Qwen, Llama, DeepSeek, Mistral, Gemma — with strengths, available sizes and licences. A map so you do not get lost.

Open the lesson
Lesson 17 Models 7:02

How to choose a model

Four questions in sequence — task, size, quantization, runtime — that take you from 'which one?' to a justified choice in minutes.

Open the lesson
Lesson 18 Models 6:42

Benchmarks and evaluation

What leaderboards actually measure, why they mislead, and how to build in half an hour the evaluation that matters most: your own.

Open the lesson
Lesson 19 Models 8:21

Cloud or local?

Three ways to run a model — on your machine, through an API, or renting GPUs — with real costs, privacy, and where each one wins.

Open the lesson
Lesson 20 Local Setup 7:41

Hardware for local LLMs

Memory is the bottleneck, everything else comes second. How to work out what you actually need and what to expect from the machine you already own.

Open the lesson
Lesson 21 Local Setup 7:01

Ollama

The runtime that became the standard for running models locally: one command to start, an OpenAI-compatible API to build anything on.

Open the lesson
Lesson 22 Local Setup 6:52

LM Studio

The graphical interface to download, try and serve models. On Apple Silicon it has an extra card: MLX format and tool calling that actually works.

Open the lesson
Lesson 23 Local Setup 8:42

Open WebUI

A ChatGPT of your own: web interface, conversation history, documents to ask questions about, and multiple users. All on your machine.

Open the lesson
Lesson 24 Local Setup 8:29

Goose: from model to agent

An open-source agent that reads files, runs commands and closes the loop — wired to your local model. What actually changes compared with a chat.

Open the lesson
Lesson 25 Local Setup 8:48

Unsloth: fine-tuning within reach

Training a model on your own domain with the memory you have. The engine that moved fine-tuning from 'needs a datacentre' to 'fits on a gaming GPU'.

Open the lesson