Prompt Engineering for Developers

Everything I learned from Isa Fulford and Andrew Ng

So recently I’ve been diving into AI, just like the rest of the world it seems. I decided I want to write about my journey and post some notes based off of things that I learn throughout this journey. So here it goes - Day 1.

I spent about 1 hour at 1.5x playback speed going through the course

The course i’m referring to is ChatGPT Prompt Engineering For Developers. Honestly, not sure why its called “ChatGPT Prompt Engineering” as we actually just hit the OpenAI APIs, specifically gpt-turbo-3.5. Does that make it ChatGPT? I don’t think so? Anyways, here are some of my notes and learnings.

Notes

• Use delimeters to indicate distinct parts of the prompt

  • ```, “””, < >, <tag> </tag>, :

    

• Delimeters protect against prompt injection

  • What is prompt injection?

    • If a user is allowed to add input into the prompt - can give conflicting instructions in the model.

    • The model understands that whatever is in the delimiter that needs to be “summarized” or whatever the instruction is

• Ask for structured output - “HTML, or JSON”

• Check whether conditions are satisfied, check assumptions required to do the task.

• Give the model the ability to check if a condition is satisfied. Fore example, “if no steps provided, say “No steps”. It's kind of like an “ELSE” statement

• Few Shot prompting

  • Provide successful examples of what to perform.

  • LLMs are capable of zero-shot prompting but its better to give an example

    

• Give the model time to think

  • provide it a chain of thinking or reasoning so that it doesn’t make up an answer. Such as “do x first, then do y”.

  • Models think kind of like humans and you have to be explicit otherwise it’ll “skim” and hallucinate

  

• Prompts should really never work the first time. Iteration

Consensus

It was definitely a course targeted for beginners but gives you a good overview of the basics in my opinion. Was it worth the time? I think so! Especially at 1.5x. I learned best practices and the correct terminology when thinking about prompts. I feel like you could figure out everything that was taught just by going through different prompt libraries though and finding patterns, if thats your method of learning.

✌️ Ismaen