March Madness.
For as long as I can remember, this has been a “thing” every spring. I don’t really follow basketball, but if I had to pick one sport (besides golf) that I will watch, it’s college basketball and usually during March Madness. I’m not sure why, but there is something almost hypnotic about the quick and graceful movement, the three-pointers, the excitement of a drive down the court. And, of course, rooting for the underdog.
Since I’m Catholic, I fill my bracket with Catholic schools and advance them forward into the Final Four slots. Some years, there are more Catholic colleges and universities than others, and sometimes, the Catholic schools win. Witness Villanova in 2016 and 2018, for example. And back in 1985, the Wildcats beat another Catholic powerhouse, Georgetown.
Last year, four Catholic schools made it to the Sweet 16: Gonzaga, Villanova, Providence and St. Peter’s. If you follow basketball, you might remember that little St. Peter’s beat the number two seed, Kentucky and then followed that with a win against number 7 Murray State before dropping to Fairfield.
This year, we have just seven in the 64-team bracket: Creighton, Providence, Marquette, Gonzaga, Iona, Xavier, and Saint Mary’s. Since the top seeds are Alabama, Houston, Purdue, and Kansas, it’s highly unlikely any of my picks will get far. Still, there is hope. As many of you know, I’ve been experimenting with ChatGPT, the AI software that has some folks worrying that computers might one day take over the world. So, as I prepared to fill in my bracket, I decided to enlist the assistance of ChatGPT.
Me: ChatGPT, who should I pick for my March Madness bracket this year?
ChatGPT: As an AI language model, I cannot provide specific advice on which teams to include in your bracket, as predicting the outcome of March Madness games is notoriously difficult, and upsets can occur at any time. However, I can provide some general tips and information to help you make informed decisions when filling out your bracket.”
At this point, ChatGPT advised me to research statistics, rankings, and team performance, watch conference tournaments, look for trends, and don’t ignore underdogs.
“Remember, March Madness is unpredictable, so even the most well-researched and thought-out bracket can be busted early on,” ChatGPT responded. “Have fun with it and enjoy the excitement of the tournament!”
A little later on, ChatGPT explained to me why it couldn’t spit out stats and rankings and come up with the best pick.
“As an AI language model, I don’t have access to real-time information or current events beyond my knowledge cutoff date of September 2021,” ChatGPT told me.
Somewhat helpful, but I wanted to know more.
Me: ChatGPT, as an AI language model, what are your limitations?
ChatGPT: As an AI language model, I have some limitations that you should be aware of. “Here are a few examples: I am a machine: While I can understand and respond to human language, I do not have emotions, feelings, or personal experiences. I process information based on patterns and rules learned from vast amounts of text data.
“I have knowledge cutoffs, I am not perfect, I do not have physical abilities, and I am not a substitute for professional advice. My training data only goes up to a certain point in time, and I do not have access to real-time information beyond my knowledge cutoff. I can only provide information based on what I have learned up to that point.”
I found this intriguing. I know of other people who have been experimenting with various AI products and there have been mixed results. I found it heartening to see ChatGPT describe itself as a machine, a digital language model without physical abilities, and lacking expert knowledge.
I picked Creighton, Purdue, Xavier, and Gonzaga as my Final Four teams. Who will win? I cannot say because, like ChatGPT, my knowledge of basketball was cutoff long before 2023. Maybe next year, ChatGPT will be a little more on the basketball.
SQUIBS 