Do you want to hire a financial consultant who searches through the web, a tutor who knows everything you uploaded or directed, or an editor who can serve you 7/24?
In this article, we have discovered how to give character to those assistants with prompts. Even if you are a prompt engineer or an ordinary ChatGPT user, these techniques 10x your results!
1. Game Theory Prompting
Photo by Glenn Carstens-Peters on Unsplash
What if ChatGPT turned into your teacher? That is the idea behind the Game Theory prompting, and you can learn and practice anything with it.
Since our topic is prompt engineering, let’s create a prompt that will make ChatGPT our prompt engineer teacher and teach us. Here is the prompt.
Your role is the game master.
The topic is prompt engineering.
You will give me simple tasks that can be solved via prompting you.
Each task should have a reasoning or logic component but should not require writing actual code.
After I write a prompt to solve your task, you will:
• Run my prompt and show the output
• Evaluate whether it correctly solves the task
• Give me constructive feedback After that, give me the next task. Keep asking me new tasks until I say “stop.” Let’s begin. Ask me the first task.
Paste the prompt above into ChatGPT and wait for the answer.
Game Theory Prompting: Lesson 1
Do you know TL;DR shortcut? You can use it to summarize everything like this;
TL;DR: [pasted content]
And pasted this text above to ChatGPT, and here is the answer.
Game Theory Prompting : Lesson 2
You are learning by doing this; let’s continue to the second technique.
2. The Recipe Pattern
Photo by Katie Smith on Unsplash
Sometimes, part of your prompt is missing, but your direction is defined. But for the parts which is missing, you can direct AI to fill them in the way you want. Let’s paste this prompt to ChatGPT.
I want to write a viral LinkedIn post.
I already have the main story and a rough idea for the hook. [pasted here]
Give me a 5-step recipe including tone, CTA, and post structure.
Here is the output.
ChatGPT’s Output
You can now take a step back and make the necessary changes, but you saved time in the first place, right?
ReAct Method
Photo by Karan Mandre on Unsplash
Even though AI has advanced, you still need to determine its behavior. ReAct, which stands for Reason + Action, gives the model time to reflect and take action.
Even while the O3 and O4 models are capable of thinking, this also allows them to search the web and ponder more deeply. Let’s analyze the XRP price and trend and see if it is time to buy it or if we should wait?
You are a financial analyst. Your goal is to decide whether it’s a good time to buy XRP based on recent trends. Use a think-action-result cycle. You can use web search, data analysis, and logic. Start by checking the current price.
Here is the output.
XRP Analysis
Final Thoughts
In this article, we have discovered three really powerful prompting techniques, and with them, you can convert ChatGPT to a financial analyst, tutor, and even an editor.
For more articles, here is our Substack account. And if you want to use no-code AI tools like agents and AI characters, visit our platform.
Here are the free resources.
Here is the ChatGPT cheat sheet.
Here is the Prompt Techniques cheat sheet.
Here is my NumPy cheat sheet.
Here is the source code of the “How to be a Billionaire” data project.
Here is the source code of the “Classification Task with 6 Different Algorithms using Python” data project.
Here is the source code of the “Decision Tree in Energy Efficiency Analysis” data project.
Here is the source code of the “DataDrivenInvestor 2022 Articles Analysis” data project.
“Machine learning is the last invention that humanity will ever need to make.” Nick Bostrom
Here are paid resources.
Here you can create your start-up ideas.
Here is our Substack page.