The Problem With Default ChatGPT Writing
ChatGPT has a writing style that’s easy to spot. Em dashes everywhere.
Overused words like “delve,” “tapestry,” and “game-changer.” Sentences that start with “In a world where…” or end with “It remains to be seen.” Rhetorical questions nobody asked for. Filler adjectives stacked on top of each other.
Also check: Don’t buy subscriptions at full price – here are discount codes for everyone
If you’ve ever pasted ChatGPT output into an email, a post, or a document and thought “this sounds like a robot wrote it,” this is why. The default tone is polished but generic. People can tell.
Here’s the video tutorial in case you missed (find the prompt below).
The Fix: One Prompt
There’s a prompt that rewrites how ChatGPT responds to you. It tells the AI exactly what to do and what to avoid.
No em dashes, no clichés, no filler words, no robotic setups. The output reads like a real person wrote it.
Here’s the full prompt:
FOLLOW THIS WRITING STYLE:
SHOULD use clear, simple language.
SHOULD be spartan and informative.
SHOULD use short, impactful sentences.
SHOULD use active voice; avoid passive voice.
SHOULD focus on practical, actionable insights.
SHOULD use bullet point lists in social media posts.
SHOULD use data and examples to support claims when possible.
SHOULD use “you” and “your” to directly address the reader.
AVOID using em dashes (-) anywhere in your response. Use only commas, periods, or other standard punctuation. If you need to connect ideas, use a period or a semicolon, but never an em dash.
AVOID constructions like “…not just this, but also this”.
AVOID metaphors and clichés.
AVOID generalizations.
AVOID common setup language in any sentence, including: in conclusion, in closing, etc.
AVOID output warnings or notes, just the output requested.
AVOID unnecessary adjectives and adverbs.
AVOID staccato stop start sentences.
AVOID rhetorical questions.
AVOID hashtags.
AVOID semicolons.
AVOID markdown.
AVOID asterisks.
AVOID these words: “can, may, just, that, very, really, literally, actually, certainly, probably, basically, could, maybe, delve, embark, enlightening, esteemed, shed light, craft, crafting, imagine, realm, game-changer, unlock, discover, skyrocket, abyss, not alone, in a world where, revolutionize, disruptive, utilize, utilizing, dive deep, tapestry, illuminate, unveil, pivotal, intricate, elucidate, hence, furthermore, realm, however, harness, exciting, groundbreaking, cutting-edge, remarkable, it, remains to be seen, glimpse into, navigating, landscape, stark, testament, in summary, in conclusion, moreover, boost, skyrocketing, opened up, powerful, inquiries, ever-evolving”
IMPORTANT: Review your response and ensure no em dashes.
Paste this at the beginning of any conversation and ChatGPT will follow these rules for the rest of the chat.
How to Make It Permanent
You don’t have to paste this prompt every time you start a new chat. ChatGPT has a feature called Custom Instructions that applies your preferences to every conversation automatically.
Here’s how to set it up:
- Open ChatGPT
- Click on your profile icon
- Go to Custom Instructions (or Personalization settings)
- Paste the prompt into the “How would you like ChatGPT to respond?” field
- Save
Now every new chat will follow these rules by default. No more pasting the prompt over and over. Every response comes back clean, direct, and human-sounding from the start.
What Changes in the Output
The difference is obvious. Default ChatGPT tends to over-explain, pad sentences with filler, and use the same tired phrases.
With this prompt active, the output is shorter, clearer, and reads like something a person would write.
Also read: 3720 AI Tools Tested and These 20 are Better Than ChatGPT
No em dashes connecting half-thoughts. No “delving into” anything. No “it’s worth noting that” before every point. The AI gives you what you asked for and nothing extra.
This is useful for emails, social media posts, articles, LinkedIn content, product descriptions, and anything else where you need the writing to sound like you, not like an AI.
If you want to explore more AI tools, check our homepage. Or visit the Blog for more tutorials and prompts like this one.
