The one-sentence version
An LLM is a very, very good guesser of the next word.
"LLM" stands for Large Language Model — the technology behind ChatGPT, Claude, Gemini and the rest. Strip away the hype and it does one simple thing, fantastically well:
It reads the text so far, and guesses the most likely next word.
Then it adds that word, and guesses again. And again.
Then it adds that word, and guesses again. And again.
You already use a tiny version of this. When your phone suggests the next word as you type a message — that's the same idea. An LLM is that autocomplete, scaled up millions of times, until it can write emails, explain ideas, and hold a conversation.
The big picture: text goes in, text comes out
Before we open it up, here's the whole thing from the outside. You give it words, a lot happens inside, and words come back.
Step 1
Your prompt
"Write a thank-you note to my team."
Step 2
The model
The guessing engine. Everything in the next few lessons lives in here.
Step 3
The answer
"Dear team, thank you for your hard work this week…"
Everything else in this course is just how it makes that guess so well. We'll open the box one piece at a time — starting with what happens to your words the instant you hit "send."