- Cyber Corsairs 🏴☠️ AI Productivity Newsletter
- Posts
- 🏴☠️ Prompting 101
Most people create prompts for ChatGPT wrong.
People waste so much time typing terrible prompts. It's sad. Mostly, they ask vague, open-ended questions and get poor results.
I'm here to fix that.
Most prompts are trash because they lack structure. You need frameworks to get quality outputs. Let's go through three of my favorites:
The RTF Framework
This system forces you to be specific. You break down requests into:
- Role: Who are you asking ChatGPT to be?
- Task: What should it do?
- Format: How should it structure the output?
Template 1
Adopt the persona of [specified role]. Provide a [specified task] in [specified format].
Chain of Thought
Tell ChatGPT to "think step-by-step" at the end of the prompts. It will walk through the problem logically instead of guessing.
Template 2
[insert your prompt instructions]. Let's think through it step-by-step.
How many tennis balls can fit in a mini-van?
Let's think step-by-step:
Chain of Density
This recursively improves existing text over multiple iterations. You identify gaps and fill them in repeatedly.
Like sharpening a dull knife over and over. Simple but powerful.
In partnership with
The secret to growing on LinkedIn in 2024
The secret to growing on LinkedIn in 2024
There's a rising demand for high-quality video content on LinkedIn. This presents a major opportunity for brands (and thought leaders) ready to step in.
Here’s how you can capitalize:
Grab your company's existing video assets, like interviews or webinars
Generate dozens of clips using OpusClip
Schedule your whole month’s worth of video clips on LI using our new Calendar feature
Reply to comments on your videos to foster your new connections
Want the full breakdown, with examples from companies like SaaStr and Chili Piper? Read it for free here
Template 3
Instructions:
1. Here is the content I want to improve: [insert content].
2. Your task is to generate increasingly better versions of this content.
Recursion:
Repeat the following two steps for a total of five iterations:
1. Identify 1-3 points missing from the current output.
2. Write a new, improved version of the content of identical length, incorporating the missing points.
Benchmark:
Refer to this information on what makes a good XYZ: [insert information].
Additional Guidelines:
Follow these specific guidelines: [insert guidelines].
Ready for better AI outputs? Rethink your prompting approach. These frameworks transform vague requests into focused, high-quality results.
Give them a shot - your mind will be blown. Reply if you need any prompt examples!
Click below to chat with your AI wellness hacks now👇
In partnership with
85% of all AI Projects Fail, but AE Studio Delivers
If you have a big idea and think AI should be part of it, meet AE.
We’re a development, data science and design studio working with founders and execs on custom software solutions. We turn AI/ML ideas into realities–from chatbots to NLP and more.
Tell us about your visionary concept or work challenge and we’ll make it real. The secret to our success is treating your project as if it were our own startup.
Click below to check out the awesome newsletters👇
Stay curious, stay ravenous. For the greatest treasures are yet hidden! 🍺
Set sail,
Captain Yar