Most AI training is either too basic — prompting tips, what is an agent — or pitched at people who can read the maths. This course sits squarely in between.

Sixteen lessons on how large language models actually work, in real technical depth, with no code and no maths background required. It’s built for people who have to make decisions about AI without having built it and for people who like to learn by understanding the concepts first and building a mental model.

Every lesson opens with a question you’ve probably already been asked, and answers it using the mechanism you’ve just learned. Questions like:

• Your risk committee asks the vendor “is this model biased?” and the vendor says it was trained on diverse, high-quality, publicly available data. Does that answer the question?
• Why does your API bill charge several times more for output tokens than input tokens?
• Your team has been pasting customer records into an AI tool. Is the model learning from what you type?
• Someone pastes a 200-page policy and asks about page 190, and gets a confident answer. How do you know the model ever saw page 190?
• Your vendor offers the same model in three sizes. What are you actually buying more of?
• Announcements lead with a parameter count. Does a bigger number mean a better model — and a better model for your use case?

Lessons 1 to 3 will be published free on this channel soon. The full sixteen-lesson course will be available at ShanaSok.com.

0:00 Welcome, and the “magic brain” problem
0:35 What this course sets out to do
0:52 What this course is not
1:14 Technical depth, no code
1:33 Questions, and reading the news for yourself
2:08 Is this model biased?
2:27 Why output costs more than input
2:46 Is it learning from what we type?
3:01 Did it even read page 190?
3:19 What are you buying in a bigger model?
3:41 What is a parameter?
4:05 The 16 lessons
4:26 What you’ll walk away with

Hello, my name is Shana.

Welcome to this course on how LLMs actually work. No AI background is required.

When I used to start thinking about LLMs in the beginning, I imagined this magic brain where we give a prompt or some kind of question and magic happens and the answer magically comes out. We hear buzzwords like neural networks. So then that makes me think of this like nodes
and lines connecting the nodes and I don’t know what the nodes are for, and I don’t know what the connecting lines are because it’s all rather magical. That’s how I used to think about it.

The aim of this course is to, bit by bit, step by step, break down that magic and replace it with actual technical knowledge about the mechanics that’s happening inside the LLM. There is still a bit of magic at the end, but not half as much as there is currently.

So what this lesson is and what this lesson is not. This is not a lesson that teaches you how to write a prompt. There is a lot of very basic lessons out there that are already do that. This is not a lesson that teaches you how to use someone else’s AI tool. And this is not a lesson that sits all the way on the other end of the spectrum that expects you to be a mathematical genius in order to understand what the LLM’s doing. It’s not.

This lesson sits squarely in the middle. Where we’re going to cover the technical details of an LLM and the architecture of the LLM, in-depth, but without using any code. So you’ll be able to understand this, even if you’ve got no engineering experience at all.

Throughout the lessons, we’re going to be posing a bunch of questions and answering them, right?
Questions that should be relevant to you. We will also show newspaper articles, excerpts from them, and you’ll see that you’re able to read them and understand them now.

You’ll be able to be in the room with other people, talking about LLMs, and be part of the conversation, as you make informed decisions that are relevant for your company, because you understand the architecture of the LLM, not just what you’ve heard people parrot back at you.

These are some examples of some of the questions that we’ll be going through throughout this course. Here’s one.

Your risk committee asked the vendor “is this model biased?” and the vendor replies that it was trained on diverse, high quality, publicly available data. Well, does that answer the question?
Does the data being diverse, and high quality and publicly available, stop it from being biased? Hmm… let’s see.

Another question. Your API bill has two line items for the same model. You’ve got your input tokens with one price, and then your output tokens, with a different price that’s usually much higher. Why does it cost more for the API to produce output, than to read the input?

The team has been pasting customer records into an AI tool. And eventually, someone asks, “so do you think this model is actually learning from what we type into the LLM?” That’s a very relevant question. A lot of people have this question, and we’re going to clear this up once and for all.

Your team pastes a 200 page policy into the tool, and asks it a question about a specific page, say page 190, and they get a very confident answer from the LLM. How do you know, that the model even looked at your page? How do you know?

Next question, your vendor offers the same model in three different sizes at three price points, and you’re told that the big one is really, really much more capable than the others. Well, what are you actually buying more of? Do you need it? The only way to answer that, is to understand the architecture of the LLM, understand why a bigger one makes a difference.

There’s many AI announcements, and you see them in newspapers, 10 trillion parameters, 70 billion parameters, or three billion parameters, small enough to run on your phone, and your vendor will quote one, and your board’s going to ask you, what does it mean? Well, what’s a parameter, and what does a bigger number, or more of them mean? Does that make it a better model? And more specifically does it make it a better model for your use case?

So throughout this course, we’re going to be answering these questions, and more. We’ve got 16 lessons that we’ll be going through, starting all the way from the very very beginning of what’s a token, and finishing off at how you’re going to train or fine tune an LLM to solve your business needs.

I’m really excited to walk through this journey with you. It’s going to get complex, but we’re going to take all those complexities, split them up, bit by bit by bit, until we’ve got a really deep mental model of what’s happening in the LLM. You’ll be able to make decisions for your team, based on knowledge, real, deep understanding of what an LLM is doing. Not just parroting back information that you hear from other people.

With that, see you in lesson number one.