Module 4 of 8 · Working memory · 7 min
The Context Window
A live token meter is the hero. Attach one novel to a 128k model and it answers; attach a second and the window overflows — the first book silently drops out of view; switch to a 1M model and both fit.
Start the lesson → Free · runs in your browser · no sign-up
What you’ll learn
- Watch a live token meter fill, overflow, and recover as you attach documents
- Understand why one novel fits a small model and a second overflows it
- Build the habit: new task, new chat — the window is finite working memory
The one idea you leave with
The window is finite working memory — so start fresh chats often.
How it works
This isn’t a video or a wall of text. You sit inside a working replica of an AI chat interface and click through the lesson yourself — the responses are scripted by design, so the teaching lands the same way every time. About 7 minutes, free, nothing to install.