Okay, this email will probably only be interesting to half of you guys.
The other half will probably think, "Oh God, I don’t like using the logical side of my brain."
Anyway, today we are going to be talking about risk management, because some decisions have bigger consequences than others.
For those decisions that have bigger consequences, like losing your house, it’s worth taking the time to do a risk-reward analysis.
A lot of the risk management methods out there are kind of complicated and require a spreadsheet or calculator.
So, I asked AI, "How can I teach a 5th grader to manage risks?" Because if a 5th grader can understand it, then it’s probably simple enough for me too.
The AI came up with 4 questions (which I refined a bit) for people to ask themselves when they are doing a risk-reward analysis:
What is the best outcome?
What is the worst outcome?
What is the likelihood of each outcome?
Is the good outcome worth risking the bad outcome?
Fortunately, I recently had an incident where I could put these four questions to the test.
I wanted to host a dairy-free pizza party where we make pizzas using dairy-free cheese. I thought it would be a cool thing to do with my friends.
But during the week I planned to do it, there was an issue: My fridge had a weird chemical smell.
When I did some research online, it said the chemical smell could be from a Freon leak. This means if I don't fix my fridge, there's a chance it will break. And if my fridge breaks, then I won’t have a place to store the pizza ingredients.
So now I had a dilemma: I wanted to host a pizza party, but my fridge might break.
Let’s do a risk-reward analysis.
Q1: What is the best outcome?
I host the pizza party and we have a great time.
Q2: What is the worst outcome?
My fridge breaks within 2 weeks, and I’ll have to live without a fridge until I get a new one.
Q3: What is the likelihood of each outcome?
There’s a 90% chance me and my friends will have a great time at the homemade pizza party.
Now, the likelihood of my fridge breaking down in two weeks is harder for me to estimate.
And because Google probably knows more about refrigerators than I do, I decided to use Google’s AI, Gemini, to help me make the estimate.
Here’s the prompt I typed into Gemini:
There’s a Freon leak in my fridge. What is the likelihood (in percentage) that my fridge will stop working within 2 weeks?
I know it's difficult to provide an exact percentage without more information, so give me a highly speculative rough estimate.
Here is Gemini’s answer:
It's difficult to say for sure what the likelihood is without inspecting the leak itself. However, here's a guesstimate based on severity:
Small leak: If the leak is small, there's a low chance (around 20%) your fridge will stop working within 2 weeks. A small leak might slowly reduce cooling efficiency over time, but may not completely stop the fridge within that timeframe.
Large leak: If the leak is large, there's a higher chance (around 70%) your fridge could stop working within 2 weeks. A large leak will deplete the refrigerant quickly, leading to a rapid rise in temperature and possible compressor failure.
Damn, that was a pretty good answer. Granted, I had to try a couple of different prompts until I got an answer like this.
Q4: Is the good outcome worth risking the bad outcome?
Nope. If there’s a 70% chance that my fridge will stop working, I should probably fix it first before hosting a pizza party.
I’m glad I spent some time doing the analysis because my first instinct was to YOLO it and host the pizza party anyway.
The bottom line is… I didn’t fix my old fridge. I actually ended up buying a new one because fixing the old one would have cost around the same price, ironically.
If you liked today’s email, leave a comment.
As always, thanks for reading!
-George 🐙