A Prompt for Reducing Familiar AI Writing Patterns

ZUSAMMENFASSUNG

In 30 Sekunden

In this short video, Matthew Berman complains about recurring features of AI writing and describes a prompt based on a Wikipedia list of writing patterns. The video links to the Humanizer project and suggests placing instructions in a prompt or personalization settings; it does not test how reliably the approach works.

1Patterns the presenter dislikesBerman lists em dashes, generic wording, sycophancy and excessive emoji.
2A list of writing patternsHe points to a Wikipedia page cataloguing patterns associated with AI writing.
3Using the promptHe describes a prompt based on that list and suggests adding it to personalization or a system message.

Das Wichtigste

Berman dislikes recurring AI writing patterns such as generic phrases, excessive emoji and sycophantic tone.
He points to a prompt derived from a Wikipedia list of AI-writing patterns.
He suggests using the instructions in a prompt, personalization settings or a system message.
The short presents the method as useful but does not establish a guaranteed result.

ThemenPrompting & in-context learning Communication Generative media

VOLLTEXT

Den bearbeiteten Text nach Kapiteln lesen

Transkript zeigen

Nur das Transkript

Recognizing repeated patterns

Berman describes features of AI prose that he finds repetitive. He points to a Wikipedia list of such patterns.

I’m tired of familiar AI writing habits: em dashes, generic phrases, sycophantic tones and too many emoji. Wikipedia maintains a detailed list of patterns that can signal this kind of generated writing.

Turning the list into instructions

He describes a prompt based on the list. He suggests using it directly or adding it to personalization settings.

FOLIE 1 / 1Humanizer project instructionsThe displayed project page shows installation and usage instructions for a writing skill.

Someone turned that page into a prompt you can give an AI to reduce those patterns. You can use the list in a prompt, or add instructions to your favorite AI’s personalization or system message. The video description links to the Humanizer project; the short does not provide a controlled test of its effectiveness.