ChatGPT Prompting: Useful Patterns And How To Use Them?
Today is Sunday, November 5, 2023. I’m sitting here at the table in my memorable place, which used to be my studying room at my little home back then since I was only a elementary, secondary, and high school student. Such good gold memories are spilling my mind right now and I’m reckoning to writing something that I find it useful for me and for everyone as well. Taking advantage of what I’ve been learning recently on Coursera, which is Prompt Engineering for ChatGPT taught by Dr. Jules White, Vanderbilt University, it’d be a great chance to summarize all of the helpful prompting patterns here for convenient usage when someone is in need. I hope you guys are having a good day.
Pattern 1: The Persona Pattern
Taking Helpful Assistant Pattern as an example. Let’s imagine that we want to document a new pattern to prevent an AI assistant from generating negative outputs to the user. Let’s call this pattern the “Helpful Assistant” pattern.
In this pattern, it’s like you’re giving the ChatBot a characteristic or trait specially owned by this type of subject that you want to ask for. To efficiently use it, your prompt should communicate the following things: