To make ChatGPT sound less human, ask for neutral, direct wording and remove cues such as small talk, simulated feelings, and claims of personal experience. For a preference you want to reuse, pair that instruction with ChatGPT’s personality and characteristic settings or save it in custom instructions. These controls steer communication style; they do not switch off capabilities or change safety rules. The result can still vary with the task and other instructions.
What “less human” means in practice
“Less human” is an editorial shorthand, not a separate ChatGPT capability or documented switch. It usually means reducing warmth and conversational framing, while keeping the answer clear and useful. It does not mean making the system more accurate, less capable, or exempt from its normal rules.
![Claude AI for Beginners Bible: [5 in 1] The Ultimate Guide to Automate Your Work, Save Hours Every Week, and Use AI for Real-World Results](https://m.media-amazon.com/images/I/415+fSJacsL._SL160_.jpg)
As an Amazon Associate I earn from qualifying purchases.
OpenAI describes personality as the style and tone ChatGPT uses, and says changing it does not change what ChatGPT can do or the safety rules it follows. OpenAI Help Center: Customizing Your ChatGPT Personality
PC Slower Than It Used to Be?
A free scan shows the junk files, broken settings and background clutter dragging Windows down - then fixes them in one click.Free scan · Windows 10 & 11Outdated Drivers Are Slowing You Down
One free scan finds every outdated or missing driver and matches the right update for your exact hardware.Free scan · exact hardware matchWays to steer ChatGPT’s voice
| Control | Best for | How specific it is |
|---|---|---|
| Personality | A broad tone preference | Preset styles such as Professional or Efficient |
| Characteristics | Nudging named qualities | Adjustments such as less warmth, enthusiasm, or emoji use |
| Prompt in a chat | Requirements for one task | Can name behaviors, format, and audience directly |
| Custom instructions | Preferences you want to reuse | Can describe your role, preferred tone, output format, and guardrails |
| Project or custom GPT instructions | A consistent voice within that configured context | Can define role, voice, format, or audience |
OpenAI’s documentation lists Default, Professional, Friendly, Candid, Quirky, Efficient, and Cynical as personality options. It describes Professional as polished and precise, and Efficient as concise and plain. These are product details that may change, so check the current interface for available choices. OpenAI Help Center: Customizing Your ChatGPT Personality
#1 Best Overall
Characteristics offer finer adjustments. OpenAI lists warmth, enthusiasm, formatting, and emoji use, with options to move qualities toward “more” or “less.” The settings work alongside personality, custom instructions, and memories; they are guidance rather than a guarantee that every response will have the same voice. OpenAI Help Center: Characteristics in ChatGPT
Try a direct instruction first
For a single conversation, state the voice you want in the prompt. For example:
Use neutral, direct wording. Do not add small talk, simulate feelings, or claim personal experience. Answer the task fully, and use the format I request.
Special offer. See more information about Outbyte and uninstall instructions. Please review EULA and Privacy policy.
This is a prompt to try, not a documented guarantee. If the answer drifts, point to the specific behavior—such as an unnecessary greeting or a claim of personal experience—and ask for a revision without it.
Rank #3
Save preferences you want to reuse
Custom instructions for general preferences
Use custom instructions for stable preferences, such as your role, preferred tone, output format, or recurring guardrails. OpenAI Academy distinguishes those ongoing preferences from the prompt for a particular task. Its examples include asking for neutral technical language. OpenAI Academy: Custom Instructions
The Help Center says custom instructions can be edited or removed and are available on web, desktop, iOS, and Android. OpenAI Help Center: ChatGPT Custom Instructions
Projects and custom GPTs for a defined context
If you want a voice tied to a particular project or purpose, put the directions in that project or custom GPT’s instructions. OpenAI Academy recommends specifying the role, voice, format, or audience; a project instruction might request neutral technical language, while a chat prompt can still specify what a particular answer needs. OpenAI Academy: Custom Instructions
Quick wins for a faster PC:
Repair Windows errors before they cause bigger problemsFix Now →Fix the driver behind crashes, sound loss and screen glitchesFind Drivers →Why the style may not carry through every answer
The requested artifact has its own conventions
A request for an email, code snippet, social post, or résumé gives ChatGPT task-specific cues. OpenAI says the response may follow the tone and context expected for that artifact rather than visibly reflect the selected personality. If you need a neutral voice in a particular format, say so in that request too. OpenAI Help Center: Customizing Your ChatGPT Personality
Best Value
Other preferences can conflict
Personality works alongside memories and custom instructions, and instructions in the chat can also adjust its visible style. If the answer sounds warmer or more conversational than intended, check for a conflicting saved preference and make the current request explicit. OpenAI Help Center: Customizing Your ChatGPT Personality
Personalization behavior can change
OpenAI’s release notes say that on November 7, 2025, changes to personalization began applying immediately across existing chats as well as new ones. That is a dated product-history detail, not a promise that the interface or behavior will remain unchanged. OpenAI Help Center: ChatGPT Release Notes
Quick Recap
How to judge whether the adjustment is working
- Check for the behaviors you asked to remove: small talk, unnecessary emotional language, or claims of personal experience.
- Check whether the answer still satisfies the task. A flatter tone is not useful if it omits needed explanation, context, or format.
- Test the preference on more than one kind of request. A style that is visible in a plain explanation may give way to the conventions of an email, post, or other requested artifact.
- When the voice misses, revise the instruction to identify the specific behavior rather than relying only on a broad label such as “less human.”
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
Recommended Free Tools
