Best skill to practice with AI

Hello Creativity Catalyst.

Thank you for being a subscriber 💛

If you like what I do, consider checking out my guides. Or sharing the newsletter with your friends. There is a referral link at the bottom of this post.

Let’s get to today’s topic - Problem Formulation.

One of the most talked about topics with AI has been prompt engineering.

I see it as communication between Humans (operators) and AI (assistants). I give AI a task and it gives me back an answer. I refine my task to get closer to what I want the output to be. Through this communication, the goal is to get the output of AI as close to the idea I have in my mind.

This is a very basic way of looking at prompt engineering. If we zoom out a bit, prompt engineering can be seen as:

Problem Formulation - The ability to identify, analyze, and delineate problems.

Instead of focusing on words and phrases, we should focus on understanding the “problem” we’re trying to “solve.”

We start with diagnosing the problem - What do we want AI to do?

It can be as simple as coming up with a new pet nickname or as complex as creating a feature-length movie.

With our core problem laid out, it’s time to break it down into smaller steps. This is incredibly important as we try to solve more and more complex problems. The better we understand the components that go into our core problem, the better we can give out tasks to our assistants.

For example, creating a feature-length movie is a big task. This is simplifying greatly, but we need to write a script, find actors, film the scenes, record the music, create special effects, etc. etc.

To create a script we need an idea, theme, characters, dialogue, etc. etc.

Each component has dozens of smaller tasks that need to be done in order to “solve our problem". The better we deconstruct our problem into actionable steps, the easier it will be for our assistants to understand and execute the tasks.

At this point, we come to communication and Language processing. AI does not always recognize and respond to our instructions - it does not understand. At times like that, we can use analogies, proactively question problem objectives or identify missing components.

As AI’s language understanding and processing evolves and becomes better, communicating with it will become easier and easier. What will determine the effectiveness of your output will be how well you can explain the tasks needed to solve your problems.

With AI, our role becomes one of a curator, operator, a creative director.

We have the vision, and the direction in our minds and our role is to communicate and guide our assistants as efficiently as possible.

Next time you work with AI, I would encourage you to give this thought process a try.

You can stop by my website or social media and as always,

Keep creating and don't forget to have fun. ☀