Stage 1 · Lesson 3 of 8
The context window as a budget
is the most tokens a model can handle in one request. Everything counts towards it: the (your standing instructions), the conversation so far, any documents you add, the that describe what the model can call, and the reply it writes.
Anything outside the window does not exist for the model. Windows now reach hundreds of thousands of tokens, but bigger is not free. You pay for every token on every call.
Replies get slower as the input grows. And models use information in the middle of a long context less reliably than information at the start or end. So treat the window as a budget, where every document you add must earn its place. That idea drives and later in the track.
A question to check yourself, an AI practice session and 1 cheat sheet entry come with the full roadmap. Unlock
Resources for this stage
Start with· follow one of these
- CoursePaidGrokking Modern AI Fundamentals
Design Gurus · Beginner · $72 one-time
Structured grounding in models, transformers and embeddings before you build on them
- VideoFreeDeep Dive into Large Language Models like ChatGPT
Andrej Karpathy · Intermediate
Free: Karpathy on tokens, training and why models hallucinate, in one sitting
Keep handy
Also worth your time
Input vs output tokens and a step by step cost estimate you can reuse for any feature
- Neural Networks: Zero to HeroGo deeper
Build a small GPT from scratch if you want to see the machinery for yourself