# The context window

> **What you will learn**
> The real structure behind what feels like the model "remembering." Knowing it
> explains why, in long jobs, it starts acting as though it forgot your earlier
> instructions.

## It starts from a blank page every time

First, a surprising fact.

> **The model remembers nothing.**

Conversations appear to continue because **the whole prior conversation is fed
back in every time.**

```
What goes into request 1:
  [my question 1]

What goes into request 2:
  [my question 1]
  [AI answer 1]
  [my question 2]        ← all sent again

What goes into request 3:
  [my question 1]
  [AI answer 1]
  [my question 2]
  [AI answer 2]
  [my question 3]        ← all sent again, again
```

That is why "tell me more about the third one" worked. Nothing was remembered —
**the earlier conversation was inside that request.**

## Context = everything you just fed in

That "everything you just fed in" is called the context. It is not only the
conversation.

```mermaid
graph TD
  A["System instructions<br/>role · rules · tone"] --> E["Context"]
  B["The whole prior conversation"] --> E
  C["Pasted material<br/>documents · tables · code"] --> E
  D["Tool results"] --> E
  F["This request"] --> E
  E --> G["Model"]
```

**Tool results go into the context too.** This matters later — a large lookup
result takes up correspondingly large space.

## The window has a size

A context window has **a fixed maximum size.** It varies by model, but the key
point is that whatever the size, **it is finite.**

The unit is the **token.** Roughly:

| | Approximately |
|---|---|
| One English word | 1–2 tokens |
| One page of A4 | 1,000–1,500 tokens |

You do not need to know this precisely. A sense of **"long documents take up a
lot of space"** is enough.

## Why this matters

Three practical consequences follow.

### 1. What you put in costs money

Cost is generally calculated from **the volume of tokens exchanged.** As a
conversation grows, the whole of it is resent with every request, so **each
request gets more expensive the further in you are.**

```
Request 10  = all 9 previous turns + the new question
Request 20  = all 19 previous turns + the new question   ← much more expensive
```

The same question costs more at the end of a long conversation.

### 2. When the window fills, things get pushed out

At the limit, **the oldest goes first.** That is the next chapter.

### 3. More is not better

"Surely more material is better" — sometimes the opposite. With a lot of
irrelevant material, **the important part gets buried.** People also find it
harder to locate the key point in a 100-page pack.

> **Only what is needed, only when it is needed.** That is the principle for
> handling context.

## When to start a new conversation

| Situation | Verdict |
|---|---|
| The topic changed | **new conversation.** Unhelpful context is baggage |
| An earlier attempt failed and you are changing direction | **new conversation.** The failed attempt keeps influencing things |
| Same topic, continuing | keep it |
| Answers are getting strange | **new conversation.** The window may be full |

The last is a common signal. When answer quality drops in a long conversation it
is often not a model problem but **a context that got messy.**

## Common misconceptions

### "It remembers earlier conversation, so it remembers personal data?"

Two things to separate.

- **In-conversation memory**: only within that conversation. It does not carry
  to a new one
- **What the service stores**: this varies by service

As covered in [things to watch out for](/guide/ai-cautions), what gets stored
where is a matter of the service's policy. **The model's memory structure and
the service's storage policy are separate questions.**

### "Does a bigger window solve everything?"

A bigger window does give you headroom. But **cost keeps rising**, and the
quality drop from irrelevant material remains. Size is mitigation, not a
solution.

---

## Check yourself

**1. What is the real structure behind the model "remembering" earlier
conversation?**

<details>
<summary>Answer</summary>

It does not remember. **The whole prior conversation is fed back in on every
request.** So the longer the conversation, the more goes into each request.
</details>

**2. Why does the same question cost more at the end of a long conversation?**

<details>
<summary>Answer</summary>

Because **the entire prior conversation is sent with it.** Request 20 includes
all 19 previous turns.
</details>

**3. What should you suspect when answers get strange in a long conversation?**

<details>
<summary>Answer</summary>

**A full or messy context.** It is usually not a model performance problem but
accumulated irrelevant material, so starting a new conversation is faster.
</details>

---

What actually happens when the window fills →
[When context gets pushed out](/guide/ai-context-overflow)