# Why ChatGPT Ignores Your Instructions (and How to Fix It)

> ChatGPT skipping rules, going over word limits or drifting off topic? Here's why it happens and seven fixes that make it follow instructions.

Canonical: https://promptitin.com/guides/why-chatgpt-ignores-instructions
Last updated: 2026-11-12

**Short answer:** ChatGPT ignores instructions when they're buried, vague, contradict each other, or fall out of its attention in a long chat. Put the rules in a short, separate list at the end of the prompt, make each one checkable (“under 120 words”, not “short”), and start a new chat when the conversation gets long.

You told it “no bullet points” and got bullet points. You said 100 words and got 400. It's not being stubborn. A few predictable things make instructions slip, and each one has a simple fix.

## 1. The rule is buried in the middle

Models pay most attention to the start and the end of a prompt. A rule tucked inside a long paragraph of context is the one most likely to be missed.

Put your rules last, as a short list under a label like “Rules:”. One rule per line.

## 2. The rule can't be checked

“Keep it short” means different things to different readers. So does “be professional”.

Make every rule something you could check yourself: “under 120 words”, “3 bullet points, no more”, “no exclamation marks”, “write at a 10-year-old's reading level”.

## 3. Two rules fight each other

“Be detailed” and “keep it under 50 words” can't both win. When rules conflict, the model picks one, and it may not be yours.

Read your rules once as a set. If two pull in different directions, say which one matters more.

## 4. The chat got too long

In a long conversation, early instructions get less weight than recent messages. That's why ChatGPT follows your format for ten replies, then drifts.

Repeat the key rule in your latest message, or start a fresh chat with the rules at the top. For rules you always want, use Custom Instructions so they apply to every chat.

## 5. You said what not to do, but not what to do

“Don't use jargon” leaves a gap. “Use everyday words a customer would use” fills it.

Pair each “don't” with a “do”. Models follow a positive target more reliably than a ban.

## 6. The task is doing too many things

Ask for research, a summary, a rewrite and a table in one go, and something gets dropped.

Split it: one prompt per step, or a numbered list of steps with the output you want from each.

## 7. There's no example

If the format matters, show it. One short example of the output you want beats a paragraph describing it.

**Prompt**

```
Write a product update for our customers.

Context: we added dark mode to the mobile app.

Rules:
- Under 80 words
- Plain words, no jargon
- One short paragraph, then one line with a link placeholder: [LINK]
- No exclamation marks
```

## Examples

**Weak prompt**

```
Write a short professional email to my team about the new process, don't make it too long and don't use bullet points but make it clear.
```

Rules are mixed into the request, vague (“short”, “too long”) and only say what not to do.

**Strong prompt**

```
Write an email to my team about our new expense process.

Context: receipts now go in the Finance app, not by email, starting Monday.

Rules:
- Under 120 words
- Three short paragraphs, no bullet points
- Friendly, plain tone
- End with who to ask: Priya in Finance
```

The task comes first, the context is separate, and every rule is a checkable line at the end.

## Tips

- Put rules last, one per line.
- Turn every adjective into a number or a test.
- Restate the one rule that keeps slipping in your next message.
- Start a fresh chat when a conversation passes about 20 messages.

## FAQ

### Why does ChatGPT not follow my word count?

Models count in tokens, not words, so exact word counts are hard for them. Give a range (“90 to 120 words”) and ask for one paragraph per idea; it lands much closer.

### Why does ChatGPT forget instructions later in a chat?

Recent messages get more attention than old ones, so early rules fade in long chats. Repeat the rule in your latest message, use Custom Instructions, or start a new chat.

### Does writing in capital letters help?

A little, but structure helps more. A short “Rules:” list at the end of the prompt works better than shouting in the middle of it.

## Related

- [Why ChatGPT Gives Generic Answers (and How to Get Specific Ones)](https://promptitin.com/guides/chatgpt-generic-answers)
- [Why Your AI Image Doesn't Match Your Prompt (ChatGPT, Gemini, Midjourney)](https://promptitin.com/guides/ai-image-not-matching-prompt)
- [How to Prompt Google AI Mode for Better Answers](https://promptitin.com/guides/google-ai-mode-prompts)
- [Why the Same Prompt Gives Different Answers in ChatGPT and Claude](https://promptitin.com/guides/same-prompt-different-answers)