Everyone and their grandma is a prompt engineer apparently.

Everyone has that one cool trick to get the AI to produce better prompts.

At Midflip, we can just collaboratively combine our notes and ideas on the process.

Social media is full of guides like these:

Its hard to know whether one prompting strategy is better than another. Like did some guy just make this up? Why are these prompts better? What tests did you perform?

Regardless just the idea to prompt in these directions may improve your content. So perhaps these guides are good just to prompt you to prompt the AI. So hell throw them in here if you have more of them.

Better Prompting Techniques with creditability

This is about the most creditable prompting guide i have found. How I Won Singapore’s GPT-4 Prompt Engineering Competition | by Sheila Teo | Towards Data Science (medium.com)

It’s by someone who won a “prompt engineering competition” - yeah apparently that’s a thing now.

She suggests this framework when prompting.

Her example:

# CONTEXT # I want to advertise my company’s new product. My company’s name is Alpha and the product is called Beta, which is a new ultra-fast hairdryer.

# OBJECTIVE # Create a Facebook post for me, which aims to get people to click on the product link to purchase it.

# STYLE # Follow the writing style of successful companies that advertise similar products, such as Dyson.

# TONE # Persuasive

# AUDIENCE # My company’s audience profile on Facebook is typically the older generation. Tailor your post to target what this audience typically looks out for in hair products.

# RESPONSE # The Facebook post, kept concise yet impactful.

Add more prompting notes here if you got any good ones.