Week 1: Foundations

Day 4: Tokens and Context Windows

Day 4 of 2815 minGoal - Learn - Example - Practice - Checkpoint

Goal

Learn what text models actually read and why long conversations can lose details.

Learn

Language models process text as tokens: small chunks of words or characters. A context window is the amount of information the model can consider at one time. If a conversation, document, or codebase is larger than the window, the system must summarize, retrieve, or leave something out. Long context helps, but it is not the same as perfect memory.

Behind the scenes
AI tools are products wrapped around models, data, prompts, retrieval, safety systems, and user interfaces. The better you understand the wrapper, the better your results get.

Example

If a conversation gets too long, an AI may miss an early detail unless the app summarizes or retrieves it again.

Practice

Paste a short paragraph into a chatbot and ask it to estimate token count, then ask what information would matter if the paragraph were ten times longer.

Checkpoint

Checkpoint
You can explain tokens, context, and why concise context improves answers.