What is an LLM?

Overview

Large Language Models like ChatGPT have captured the world's attention, but what actually are they? How do they work? And how can you use them effectively?

This lecture cuts through the hype and jargon to give you a clear understanding of this technology—where it came from, how it works, and what it can (and can't) do.

What We'll Cover

A Brief History of Machine Learning

From Turing's early questions about machine intelligence to the breakthrough of deep learning, we'll trace the key moments that led to ChatGPT.

How LLMs Work

Is it just fancy auto-complete? We'll use your brain as a model to understand what's happening inside these systems. No math required—just analogies and clear explanations.

Live Demonstrations

See LLMs in action. We'll explore what they're good at, where they fail, and how to get the most out of them.

Practical Tips

Concrete techniques for using AI tools effectively in your daily life and work.

Questions We'll Explore

• What's actually happening when ChatGPT responds to you?
• Why do these models "hallucinate" incorrect information?
• What are they genuinely good at? Where do they fall short?
• How can I use these tools more effectively?
• What makes this moment in AI different from past hype cycles?

No Prerequisites

This lecture assumes no technical background. If you've used ChatGPT once or never at all, you'll be able to follow along. We'll start from the basics and build up understanding together.