4 Comments
User's avatar
4Raws's avatar

One banned phrase can destroy credibility instantly. Do you enforce this at prompt level or after generation

Atharva Shah's avatar

Here's the TL;DR version of this:

• Certain phrases instantly signal low-quality AI content.

• These patterns repeat across models and use cases.

• This blacklist consolidates 1500 known slop terms into one place.

• It covers unigrams, bigrams, and trigrams systematically.

• Enforcing this list directly improves perceived trust and clarity.

Hunter's avatar

How are you supposed to use this list with ChatGPT when custom instructions have a character limit of 1500?

Atharva Shah's avatar

Use a prompt to condense it and add a text expansion shortcut mapped to this list so when you type /blacklist then this text or prompt should appear in the chatbox