Welcome to this course on ChatGPT Prom Engineering for Developers. I am thrilled to have with me Isa Forfeit to teach this course. She is a member of the technical staff of OpenAI and has built the popular ChatGPT retrieval plugin. She has also contributed to the OpenAI cookbook that teaches people prompting. In this course, we will share some of the possibilities and best practices for using OpenAI’s large language models as a developer.
There has been a lot of material on the internet for prompting with articles, but most of it has focused on the ChatGPT web user interface. However, the power of OpenAI’s large language models lies in using API calls to quickly build software applications. In this course, we will cover prompting best practices for software development and common use cases such as summarizing, inferring, transforming, and expanding text. We will also guide you in building a chat bot using a large language model.
There are two types of large language models: base models and instruction-tuned models. Base models are trained to predict the next word based on text training data, while instruction-tuned models are trained to follow instructions. In this course, we will focus on best practices for instruction-tuned models, as they are easier to use and safer in practical applications.
Before we begin, I would like to acknowledge the team from OpenAI and Deep Learning.ai that contributed to the materials for this course. I am grateful for their support and expertise.
When using an instruction-tuned model, think of giving instructions to another person who is smart but doesn’t know the specifics of your task. Be clear and specific in your instructions, and consider the tone and style of the generated text. Giving the model time to think is also important.
In the next video, we will provide examples of clear and specific instructions, which are essential principles of prompting OpenAI’s large language models. Stay tuned!
