Large language models

ChatGPT, Claude, and Gemini all run on the same kind of technology. It is called a large language model, or LLM. This page explains what that means.

What is a large language model?

Imagine someone who has read most of a giant library. Books, websites, articles, and code. They didn't memorize every page, but they picked up how language works and a lot about the world.

A large language model is a computer version of that reader:

• Large means it learned from a huge amount of text.
• Language means it works with words: reading and writing.
• Model means it is the trained "brain" that does the work.

Because it learned from so much text, an LLM can answer questions, write stories, translate, summarize, and even write code.

The big three

In this course, you will use three popular LLM families. Each one is made by a different company.

They all work in a similar way, but each has its own strengths. Later in the course, you'll try building small apps with each of them.

Chat app vs model vs API

People often mix up three different things. Think of a restaurant:

• The model is the chef in the kitchen. It does the real work.
• The chat app is the dining room. It is the friendly website or phone app where you type and read answers, like chatgpt.com or claude.ai.
• The API is the takeout window. It lets other apps send requests to the chef directly, without the dining room.

An API (Application Programming Interface) is a way for one program to talk to another. For example, an online shop's AI shopping assistant uses an API to talk to a model behind the scenes.

Try it yourself

Ask an LLM to describe itself. Paste this into ChatGPT, Claude, or Gemini:

In simple words, what are you?
Who made you, and what are 3 things you are good at
and 3 things you are not good at?

Try the same prompt in two different apps. Compare the answers. You'll notice they are similar but not the same.

Common mistakes

• Thinking ChatGPT and GPT are the same thing. ChatGPT is the app. GPT is the model inside it.
• Thinking a free chat account gives you API access. The API is usually a separate account with its own billing. Check the provider's pricing page.
• Chasing version numbers. Models change often. Learn the ideas, and they will still apply next year.

What's next?

You know what an LLM is. Now let's peek inside and see how it actually writes an answer, one word at a time.