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
AI
-
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.
-
Text Generation Quality Improvements and Competitive Model Comparisons
By
–
Generación de texto legible. Mejor composición. Muy buena calidad. Además mirad en las imágenes la cantidad de "guiños" a Parti, Muse, Imagen y otros modelos similares de la competencia
-
StabilityAI Unveils IF: Next-Generation Text-to-Image Model
By
–
¿OTRO MODELO MÁS? ¡OJO! De los creadores de Stable Diffusion (StabilityAI) próximamente un nuevo text-to-image. Su nombre parece ser IF… y por estos ejemplos parece que resuelve muchos de los problemas de los modelos del año pasado
-
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: