What to expect
In this session we'll walk through the core ideas behind large language models (LLMs) — the technology behind tools like ChatGPT, Claude, and Gemini.
We'll cover:
- What is a language model? — the intuition behind predicting the next token
- Tokens and embeddings — how text becomes numbers
- The Transformer architecture — a plain-English explanation of attention
- How LLMs are trained — pre-training, fine-tuning, and RLHF
- Hands-on demo — playing with a small model in the browser
Who should come?
Anyone curious about AI, regardless of background. We'll assume you know what a neural network is in vague terms, but nothing more.
Bring
Your laptop if you have one — we'll do some interactive exercises via a web interface, no setup required.