๐๏ธ ๐ข Introduction
This chapter introduces simple prompting techniques as well as terminology. In order to understand prompting/prompt engineering, you first need to understand some very basic AI concepts. If you already know about the below topics, feel free to skip ahead to the next article.
๐๏ธ ๐ข Prompting
In the previous chapter, we discussed AI and how humans can instruct AIs to perform tasks.
๐๏ธ ๐ข Giving Instructions
One of the simplest prompting methods is just giving instructions (sometimes called instruction prompting)(@efrat2020turking)(@mishra2022reframing). We already saw a simple instruction
๐๏ธ ๐ข Role Prompting
Another prompting technique is to assign a role to the AI. For example, your
๐๏ธ ๐ข A "Standard" Prompt
We have heard of a few different formats of prompts thus far.
๐๏ธ ๐ข More on Prompting
As we have seen in the previous pages, prompts can have varying formats and complexity. They can include context, instructions, multiple questions-answer examples, and even other prompts (what!?).
๐๏ธ ๐ข Chatbot Basics
One of the most common ways prompting can be useful is when interacting with the numerous chatbots available to the public, such as ChatGPT. Note that ChatGPT is different from GPT-3. The main difference is that chatbots can remember your conversation history. Just like GPT-3, they can also answer questions, provide writing summary and analysis, write text or code, and more at a high level, which is an exciting prospectโbut the real value of chatbots is only accessible when you get specific with your prompts. In this article, weโll explore some basic methods for how to better utilize chatbots, such as using style guidance, descriptors, and priming.
๐๏ธ ๐ข Understanding AI Minds
Hello reader, congratulations on getting through the intro chapter. You are off to a great start in this very exciting field. There are a few simple things you should know about different AIs and how they work before you start reading the rest of the course.