Prompt Engineering is the latest topic that is proliferating online classes, with providers eager to join in, catch up with and go further than each other. Here is a new offering from a pedigree source.

ChatGPT has been heralded as a tool that can work like a programmer, like a health professional, all the way to like a therapist. The quality of the answers and guidance
you receive by interacting with the bot varies depending on the quality of the questions you feed it with.

Prompt Engineering is key to the art of harnessing ChatGPT to help you be more productive in personal and professional life. It is an emerging skill that could land you you next job as companies look for specialized talent in this area.

Many institutions will be eager to jump on the bandwagon after DeepLearning in collaboration with OpenAI launched ChatGPT Prompt Engineering for Developers, covered by IProgrammer in Free Course On ChatGPT Prompt Engineering. Already Vanderbilt University has followed the trend with its Prompt Engineering for ChatGPT which defines Prompt Engineering, as an increasingly crucial skill as large language models like ChatGPT rise in popularity, as:

the process of crafting high-quality inputs to generate high-quality outputs

During the course student's learn to build basic prompts and gradually move to more involved ones till they master their interaction with ChatGPT. It's hosted on Coursera and free to take, but learners can opt for the verified path with a certificate on completion for $49. It is self-paced and quick to complete with an estimated time of completion as low as 18 hours and while it can conveniently be spread over a period of 6 weeks one motivated student was able to complete over a weekend and gave it a 5-star rating.

It is included in Coursera Plus which currently has a promotion for new users - see Take a Plunge Into Learning -Try Coursera Plus for $1. 

The syllabus outline is:

Week 1 Course Introduction

• Motivating Example: Building a Meal Plan with a Fusion of Food from Ethiopia and Uzbekistan that is Keto
• Overview of the Course
• Motivating Example: Act as a Speech Pathologist
• Setting Up an Account and Using ChatGPT
• What are Large Language Models?
• Randomness in Output

Week 2 Introduction to Prompts

• What is a Prompt?
• Intuition Behind Prompts
• Everyone Can Program with Prompts
• Prompt Patterns
• The Persona Pattern
• Introducing New Information to the Large Language Model
• Prompt Size Limitations
• Prompts are a Tool for Repeated Use
• Root Prompts

Week 3 Prompt Patterns I

• Question Refinement Pattern
• Cognitive Verifier Pattern
• Audience Persona Pattern
• Flipped Interaction Pattern

Week 4 Few-Shot Examples

• Few-shot Examples
• Few-shot Examples for Actions
• Few-Shot Examples with Intermediate Steps
• Writing Effective Few-Shot Examples
• Chain of Thought Prompting
• ReAct Prompting
• Using Large Language Models to Grade Each Other

Week 5 Prompt Patterns II

• Game Play Pattern
• Template Pattern
• Meta Language Creation Pattern
• Recipe Pattern
• Alternative Approaches Pattern

Week 6 Prompt Patterns III

• Ask for Input Pattern
• Combining Patterns
• Outline Expansion Pattern
• Menu Actions Pattern
• Fact Check List Pattern
• Tail Generation Pattern
• Semantic Filter Pattern

By completing it, graduates are expected to have gained a good grasp of how to

• apply prompt engineering to effectively work with large language models, like ChatGPT
• use prompt patterns to tap into powerful capabilities within large language models
• create complex prompt-based applications for your life, business, or education

Having myself experienced the power of ChatGPT in aiding me in my IT/technical endeavors, I'm eager to find out how to tweak my inputs to squeeze the best answers out of the bot, on topics of a much wider scale. Vanderbilt's Prompt Engineering course is right on track for that purpose.

More Information

Prompt Engineering for ChatGPT

Related Articles

Free Course On ChatGPT Prompt Engineering  

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info