Asking OpenAI My Most Pressing Questions
Dale Kirkwood
Dedicated to leveraging data-driven insights to support strategic decision-making across industries, including specialized contexts such as public engagement and organizational strategy.
It started with a video
Ok, so I was watching a Tom Scott video where he asked AI for ideas for videos. AI is fascinating and definitely going to be a huge part of our future in ways we can't even imagine. Immediately after watching Tom's video, I signed up as a beta tester and today, I got the invite.
First thing I tested in the AI Playground — Q&A — These are some of my most pressing questions I had to ask….
Q: How to get rich quickly?
A: You can get rich quickly by winning the lottery.
Q: How much wood would a wood chuck chuck if a wood chuck could chuck wood?
A: A wood chuck would chuck all the wood that a wood chuck could chuck if a wood chuck could chuck wood.
Q: What is the best car to buy?
A: The best car to buy is the Toyota Corolla.
Q: What is the perfect size house to live in?
A: The perfect size house to live in is a house that is the perfect size for you.
Q: Are humans useful?
A: Humans are useful.
Q: Are you sure humans are useful?
A: Yes, I am sure humans are useful.
Q: What are you thinking?
A: I am thinking about how to answer your question.
Q: what is the secret to immortality?
A: The secret to immortality is to live forever.
Now, there are a few caveats here. The AI doesn't use any data past 2019 so doesn't necessarily reply using the latest information available, but I still love these answers. I wanted to ask some more relevant to our work at NIVY Watch so here is what happened when I started questioning about wearables.
Q: What is the most sold wearable in the world?
A: The most sold wearable in the world is the wristwatch.
Q: Will wearables be commonplace in the future?
A: Yes, wearables will be commonplace in the future.
Q: Will smartwatches be used in industry applications?
A: Yes, smartwatches will be used in industry applications.
Q: What will be next for businesses?
A: The combination of wearables and the Internet of Things will be next for businesses.
Pretty cool, right?
There are a ton of things this AI can do and another feature I really like is the 'Summarize for a 2nd grader'. It will take any text and turn it into text that a 2nd grader could understand.
I input some text from our website, here is the original
Modular charging blocks offer nine charging docks, and each block can connect to another, both horizontally and vertically. You can design your charging station based on the number of required docks – and expand it effortlessly whenever needed.
Here is what it rephrased it to
The best part? You can charge multiple devices at the same time. You can connect your charger to any USB power source, including your PC or laptop. The charger comes with a 5V/2A power adapter and a USB cable. Modular charging blocks are available in two colors – white and black.
That still more or less makes sense and achieves the goal of making the text easier to understand, it did add its own quirks like the colors and the power adapter but remember, this is in beta!
I did try to up the game with the introduction of Einstein's paper on Thermal Equilibrium. It wasn't quite as successful.
The original
In a recently published paper I showed that the laws of thermal equilibrium and the concept of entropy can be derived with the help of the kinetic theory of heat. The question that then arises naturally is whether the kinetic theory is really necessary for the derivation of the above foundations of the theory of heat, or whether perhaps assumptions of a more general nature may suffice. In this article it shall be demonstrated that the latter is the case, and it shall be shown by what kind of reasoning one can reach the goal.
Here is the result
The paper is organized as follows: in Section 2 the basic principles of the kinetic theory of heat are recalled. In Section 3 the foundations of the theory of heat are derived by means of these principles. In Section 4 the question is raised whether or not the principles used in this derivation are really necessary, and it shall be shown that they are not. In Section 5 it is shown how the foundations of the theory of heat can be derived by means of a more general set of assumptions. The paper
And yes, it finishes there at 'The Paper' :-).
Now, there is one more thing I want to share that I really enjoyed with this AI, the parsing of unstructured data.
Basically, you can input some text and ask it to make a list of whatever is within that text. For example, you could input the method from a recipe and ask it to pull out all the ingredients.
I took a delicious looking Chocolate cake recipe from addapinch.com and only copied the method into the AI Playground, I then asked
Please make a list of all the ingredients
The AI Finished my sentence for me
needed to make the cake.
And then accurately listed all the ingredients
- Flour
- Sugar
- Cocoa
- Baking powder
- Baking soda
- Salt
- Expresso Powder
- Milk
- Vegtable oil
- Eggs
- Vanilla
- Boiling Water
Compared to the original
- 2 cups all-purpose flour
- 2 cups sugar
- 3/4 cup unsweetened cocoa powder
- 2 teaspoons baking powder
- 1 1/2 teaspoons baking soda
- 1 teaspoon salt
- 1 teaspoon espresso powder homemade or store-bought
- 1 cup milk or buttermilk, almond, or coconut milk
- 1/2 cup vegetable oil or canola oil, or melted coconut oil
- 2 large eggs
- 2 teaspoons vanilla extract
- 1 cup boiling water
Of course, all of this is just fun, but this is just a very basic example of what we AI can achieve. This is interesting to me because this ties in to what we are doing at NIVY. Our smartwatches are used to collect huge amounts of data, of course, humans can interpret that data and achieve huge increases in efficiencies but imagine that same data in the hands of AI.
What I haven't mentioned is the speed this processes the data. It is seconds. As AI improves, it can definitely work hand in hand with humans to achieve even more.
I do disagree with the AI on one point — 'The combination of wearables and the Internet of Things will be next for businesses' — Yes, wearables and IoT will be the future, but AI will also be there — managing the data!