DeepLearning.AI, in partnership with OpenAI, is currently offering free training into a key new skill that developers are keen to acquire in order to build applications on top of ChatGTP.

On the whole developers are enthusiastic about the potential of large language models (LLMs) ChatGPT API and over half of those in a recent survey intended to incorporate the ChatGPT or Whisper API in their projects. This free course, that has around an hour and a half of content, will provides help and guidance with the key skill to getting useful output from ChatGPT - asking the right questions or providing the right input, so-called "prompt engineering". While the course is "beginner-friendly" and intended for developers new to AI, it is also useful to those suitable for advanced machine learning engineers wanting to approach the cutting-edge of prompt engineering and use LLMs. 

With the title, ChatGPT Prompt Engineering for Developers, the course sets out to share best practices for developers wanting to build applications using API access to Large Language Models or LLMs. It is presented by Andrew Ng, founder of DeepLearningAI, co-founder of Coursera and known to many of us for his Machine Learning course. The core material comes from Isa Fulford, a member of the technical staff at OpenAI.

This short video outlines what to expect from the course:  

The course starts with the two important principles for creating prompts which boil down to giving clear and specific instructions and allow the model time to think. A second lesson is then devoted to iteratively refining prompts. Then Isa looks at each of four common use cases:

• Summarizing - taking a long text and distilling it
• Inferring - taking a text and doing some analysis on it
• Transforming - taking a text and converting in into a different language or format
• Expanding - taking a short prompt and generating a longer output

Finally there's a lesson on using a language model to build a custom chatbot.

Isa rounds out this lightning overview saying:

We just hope to spark your imagination about new applications you can build. Many applications that were previously very hard to build can now be built quickly and easily using large language models and some good prompting.

and Andrew Ng adds:

So when you complete the course you'll have a good sense of what applications can be build on top of large language models. And you'll also understand how to go about building them. I hope you also come away with some cool news ideas for things you can build.

No previous experience with AI is required to embark on the course, but you do need a basic understanding of Python so that as the follow along you can try things out by running the live Jupyter Notebooks that are provided. 

Everything you need to try things out is already there but there's also information on how to access the ChatGPT API. 

This course comes from AI's top experts, it is really well thought out and produced - and at the moment it is free, but this will be for a limited period only.

More Information

ChatGPT Prompt Engineering for Developers

Related Articles

What Devs Think About AI

Runaway Success Of ChatGPT

Stack Overflow Traffic Slumps As Devs Turn to ChatGTP

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