## Did Your ChatGPT Get More Polite? Here’s Why (and How to Change It)

Have you noticed something different about your conversations with ChatGPT lately? Maybe it’s more consistently formal, remembers a specific detail about your work, or perhaps it has stopped giving you long, preachy introductions to its answers. If you’ve sensed a shift in its personality, you’re not imagining things. ChatGPT has indeed learned some manners, but the most important part is that you’re the one who gets to teach them.

This change comes in the form of a powerful feature called “Custom Instructions.” Essentially, it gives you a permanent way to tell ChatGPT who you are and how you want it to behave, saving you from having to type the same framing instructions at the beginning of every single chat.

### What Are Custom Instructions?

When you access the Custom Instructions setting, you’ll find two text boxes:

1. **What would you like ChatGPT to know about you to provide better responses?**
2. **How would you like ChatGPT to respond?**

The first box is for context about you. Are you a software developer who primarily works in Python? A high school teacher creating lesson plans? A marketer writing social media copy? Giving it this background information helps it tailor its answers to your specific needs.

The second box, however, is where the “manners” come in. This is where you set the rules for its personality, tone, and format. This is your control panel for its behavior.

### Putting Manners On (or Turning Them Off)

The beauty of this system is its flexibility. You can train ChatGPT to be the exact kind of assistant you need, whether that’s a polite and formal collaborator or a terse, no-nonsense tool.

**Want a more polite and structured AI?**

You can instruct it in the second box with commands like:
* “Always be polite and professional in your responses.”
* “Start with a brief, bulleted summary of the answer before giving the full explanation.”
* “Assume I am a beginner and avoid overly technical jargon unless I ask for it.”
* “Use a friendly and encouraging tone.”

With these instructions, ChatGPT will adopt a more courteous and user-friendly demeanor, effectively keeping its “manners” on.

**Prefer a direct, get-to-the-point AI?**

For many users, especially those using the AI for coding or data extraction, the conversational filler can be a nuisance. You can use Custom Instructions to strip it all away. This is how you “turn the manners off.”

Try instructions like:
* “Be direct and concise. Do not use conversational pleasantries.”
* “Never apologize or use phrases like ‘As a large language model…'”
* “If I ask for code, provide only the code and a minimal explanation.”
* “Respond in a terse, minimalist style. Omit all preamble and conclusions.”

By setting these rules, you transform ChatGPT from a chatty partner into a raw, efficient information processor. It will simply do what you ask, immediately and without the fluff.

### Why This Matters

This feature represents a significant step forward in human-AI interaction. Instead of adapting to the AI’s default personality, we can now shape the AI to fit our unique workflows and preferences. It acknowledges that there is no one-size-fits-all approach to an AI assistant. A novelist brainstorming plot points needs a very different interaction style than a programmer debugging a complex script.

So, if your ChatGPT feels a little different, dive into your settings. You now have the power to decide if you want an AI that says “Certainly, here is the information you requested” or one that just gives you the facts, plain and simple. The manners are there, but whether they’re on or off is entirely up to you.