BTW — Looking to leap ahead on ChatGPT? Join 430+ of us in my just-released course and AI writing system. Comes with a ton of prompts and techniques way more sophisticated than what you see here: (You can expense this!) http://
aicontentreactor.com
PROMPT ENGINEERING
-
ChatGPT Course and AI Writing System Launch Announcement
By
–
-
Iterate on Your Prompts for Better Results
By
–
Not iterating on your prompts to get better results Your first result might be decent. But usually, you (or your friends) can tweak your prompt to make it better. Keep experimenting and iterating.
-
Bundle Multiple Instructions Together for Better AI Workflows
By
–
Asking it only to do 1 thing at a time Single commands? Boring. Once you’ve found a workflow you like, bundle steps together. In the screenshot below, I give it multiple instructions in one prompt so it will write a tweet thread for me:
-
Managing ChatGPT’s Output: Tips for Getting Concise Responses
By
–
Not asking it to reduce its output ChatGPT might give you way too much information. Did you know you can ask it to help with that? Ask the assistant to reduce, remove, compile, or rewrite.
-
AI Struggles with Negative Prompts: Use Positive Commands Instead
By
–
Prompting in the negative AIs still have a hard time with, “no”. When it sees something like “Write with no hashtags” it also sees Write…Hashtags. When possible, try to give it a positive command that has the same outcome.
-
Providing Examples to ChatGPT for Better Output Quality
By
–
Not giving examples of what you want You can give ChatGPT full examples of the kind of output you're looking for. Word your prompt carefully to have it replicate the aspects of the example that you like.
-
Language Models Fake Math: Why They Sound Convincing But Fail
By
–
Asking a language model to do math The answer will sound convincing. Sometimes parts of it are correct. But, for the most part, it's faking it — just predicting the next word. The math will likely be wrong. (If you have math problems, check out WolframAlpha instead.)
-
ChatGPT Output Specificity: Removing Pretext and Context
By
–
🔸 Not being specific about your output goals
— Rob Lennon 🗯 | AI Whisperer (@thatroblennon) 5 janvier 2023
ChatGPT has been trained to prefer certain outputs.
You can request a change.
A quick hack:
Try asking it to "remove pre-text and context" and "only return" certain results: pic.twitter.com/qd2PIXEXqKNot being specific about your output goals ChatGPT has been trained to prefer certain outputs. You can request a change. A quick hack: Try asking it to "remove pre-text and context" and "only return" certain results:
-
8 Common ChatGPT Mistakes Limiting Your Results
By
–
Most new ChatGPT users are making simple mistakes. (And they don't realize results could be TWICE as good.) 8 problems with your AI prompts to stop right now:
-
Community Improvement of Writing Style Capture Prompt
By
–
UPDATE:
Thank you @rajjha for this better version of my 'Capture your writing style' prompt (see next tweet for Voice-finder 2.0). Having a community to help build and improve these queries is