Summary
This chapter explains tokenization and next-token prediction—the core probabilistic mechanism language models use to generate text and why they sometimes hallucinate.

General domain of usage
Automated text generation

You don't need to understand how a car engine works to drive — but knowing 
that it runs on fuel helps you avoid running out of gas. The same logic 
applies to AI. You don't need a computer science degree, but understanding 
one core idea will make everything else in this course click.


## Prediction, The Core Idea

Large language models (LLMs) — the technology behind ChatGPT, Claude, 
Gemini, and others — work by **predicting what comes next**.

Given a sequence of words, the model calculates which word (or phrase) is 
most likely to follow, based on patterns it learned from enormous amounts 
of text: books, articles, websites, code, and more.

It's similar to the autocomplete on your phone — except trained on 
effectively the entire internet, with vastly more sophistication.

## What Are Tokens?

AI doesn't read words the way you do. It breaks text into small chunks 
called **tokens** — roughly corresponding to words or parts of words.

For example:
- *"running"* might be one token;
- *"unbelievable"* might be split into *"un"* + *"believ"* + *"able"*;
- Even spaces and punctuation are tokens.

This is why AI sometimes handles unusual words awkwardly, or why very long 
inputs slow things down — every token takes processing power.

For practical use, the main thing to know is this: **the more tokens in 
your conversation, the more context the model has** — and the more it costs 
to run (which is why free plans have limits).

## Why AI Sometimes Makes Things Up

The model is predicting what **sounds right**, it doesn't always 
produce what is **factually correct**. When it encounters a topic outside 
its training data, or a question it can't answer confidently, it doesn't 
say "I don't know" — it generates a plausible-sounding response anyway.

This is called a **hallucination**.

It's not a bug, and it's not the AI lying to you. It's a fundamental 
property of how prediction works. Knowing this is the first step to 
using AI safely. We'll cover it in depth in Section 3.

AI predicts — it doesn't truly *know*. This one insight explains 
why good prompts matter, why you should verify important facts, and why 
human judgment is never optional when working with AI.

What is the core idea behind how large language models like ChatGPT work?

Why does AI sometimes generate responses that are not factually correct?

AI is no longer optional — it's part of how work gets done in 2026. This course gives you a practical foundation for working with AI tools confidently and responsibly. No coding required. You'll learn how modern AI actually works, how to get useful results from it, what to watch out for, and how to apply it in your specific role — whether you're in marketing, HR, analytics, or development.

Before using any AI tool effectively, you need to understand what it is — and what it isn't. This section demystifies large language models, cuts through the hype, and maps out the current landscape of AI tools so you can make informed choices from day one.

The quality of your output depends almost entirely on how you phrase your input. This section teaches you how to write clear, structured prompts — and how to refine them when the result isn't quite right. The most hands-on section of the course.

Knowing how to use AI also means knowing when not to trust it. This section covers the real risks — hallucinations, data privacy, bias — and builds the critical thinking habits that separate a thoughtful AI user from a reckless one.

The final section brings everything together through the lens of specific job functions. Each chapter shows exactly how AI is being used in a given field — with real examples, tool demos, and a closing chapter to help you build your own AI workflow.

How Language Models "Think"

Prediction, The Core Idea

What Are Tokens?

Why AI Sometimes Makes Things Up

1. What is the core idea behind how large language models like ChatGPT work?

2. Why does AI sometimes generate responses that are not factually correct?