Set up ChatGPT to permanently write like a human. One-time setup, saved to custom instructions, works on everything you write from that point on.
3-step setup in ChatGPT Wikipedia’s full list of AI tells Permanent custom instructions Every AI writing pattern explained Before and after examples Works on all future conversations
2026 Edition
AI detectors don’t read your text for meaning. They look for patterns. The same sentence structures repeated over and over. The same filler phrases. The same punctuation habits. Remove those patterns and the text reads as human.
0%
Al detection score
24+
Patterns to avoid
1x
Setup, works forever
Wikipedia maintains a page called “Signs of AI writing” that catalogues every pattern AI detectors flag. You’re going to tell ChatGPT to read that page, turn it into a strict set of writing rules, and then save those rules to your custom instructions so they apply permanently.
WHY CUSTOM INSTRUCTIONS? Custom instructions are ChatGPT’s permanent memory. Anything you put there gets applied to every new conversation automatically. You set this up once and never think about it again. Every piece of text ChatGPT writes from that point forward follows the humanizer rules.
Open ChatGPT and start a new chat. Paste this prompt to make ChatGPT go read Wikipedia’s full list of AI writing tells:
PASTE THIS INTO CHATGPT
Go to Wikipedia and look up the
page on signs of AI writing:
en.wikipedia.org/wiki/Wikipedia:
Signs_of_AI_writing
Read through the entire page and
list out every single pattern that
gives away AI-generated text.
Include the pattern name, what it
looks like, and a specific example
of each one.
ChatGPT will go read the Wikipedia page and come back with a full list of patterns: em dashes, filler phrases, robotic tone, AI vocabulary words, promotional language, and more. Check the list to make sure it found everything.