Module 2 · Prompting — getting a real answer Lesson 4 of 15
How Llama reads what you type
Context, instructions and roles. You control the context window directly — how many tokens the model can see at once — and you pay for it in memory, not in money. Understanding what the model can see — and what it has already forgotten — explains almost every disappointing answer you will get.
The concept
You control the context window directly — how many tokens the model can see at once — and you pay for it in memory, not in money. This is the machinery. A model does not remember your last conversation the way a person does; it is handed text and asked to continue it well. Everything you want it to know has to be in that text, in the same window.
There is a difference between a system instruction — the standing context, set once — and a message, which is this request. Put your standing context in the standing place. "I am a final-year mechanical engineering student applying for data roles" belongs in your profile, not typed again at the start of every chat.
And there is a hard limit. When a conversation gets long enough, the earliest turns fall out of view. Symptoms: it contradicts an instruction you gave ten messages ago, or forgets the file you uploaded. The fix is a new conversation with a written summary of where you got to, not a longer argument.
Worked example
Set too small a context and the model forgets the start of your own document. That limit is a number you chose, which is a very different feeling from a black box.
Your practice task
Ask the same question twice: once on its own, once after a short paragraph of setup about who you are and what you need. Compare the two answers and write down the difference. That gap is the thing you are learning to control.
Do this before moving on. Reading a solution teaches the shape of it; typing it teaches you.
Key takeaway
You control the context window directly — how many tokens the model can see at once — and you pay for it in memory, not in money.
Keep your place in this course
A free account saves which lessons you have finished and unlocks the certificate. The lesson itself stays free to read.
Create free account or sign inCourse complete
You finished every lesson.
Your certificate is ready, and the projects you built are the proof to attach to an application.
Almost there
15 lessons left of 15
Finish every lesson to unlock the certificate. Each one ends in a practice task — do them and the final project brief writes itself.