Interesting links 31 October 2026

Interesting links used to be a weekly post from me. I got away from it for a variety of reasons but I am hoping to bring it back on an irregular basis going forward. I have a bunch of things to share today so let’s get to it.

First off, registration for the CSTA Annual Conference 2027 is open. Already? Yes! And early registration comes with a big cost savings. The conference page is at Home - CSTA 2027 Annual Conference The conference will be in Anaheim California July 8-11 2027.BTW, new this year - Exhibit Hall Only tickets. Get you in the Exhibit Hall, keynotes, and welcome reception.

Next up, several links to LinkedIn posts by David Renton. David is doing a lot of interesting things.

David is teaching a high school course about using AI. Read about how his students are growing beets, using physical computing, and looking at results and actions using AI https://lnkd.in/p/gUfeydeu 

With younger students, David is asking the question “Can a video game teach students how AI is really used on farms?” Check out the game he created that is helping answer that question while teaching students about farming, business, and AI. https://lnkd.in/p/gAA6DBdd

David also introduces Ripplet Racer, a new teaching game that is part of his Ripplet suite of software. Read about Ripplet Racer at https://lnkd.in/p/gV2g9-yY 

BTW, Ripplet Math now includes:
Animal Armada
Ripplet Racer
Math Fluency
Math assessments
Student progress data and feedback
More details: https://ripplet.us/

AI Is Getting Scary

Recently on Facebook, slider puzzle games came up in discussion. I remembered writing a program for playing one of those games and decided to see if I still had one. I did find one. It created a form and let me easily move the "boxes" around. It didn't 1) check to see if everything was in the right place 2) shuffle. So I decided to add those features. Enter GitHub Copilot which is built into Visual Studio.

I started writing an if statement in the appropriate place and Copilot offered the option to call a method called CheckWin. OK I let it finish.

Obviously, I needed CheckWin to be written.  I started writing "private ..." and it offered "bool CheckWin etc." so I let it create the method to see what it came up with. What it wrote works fine although not the same as I would have written it. But ok. CopIlot sure did do a good job of anticipating what I wanted.

My  next step was to add a shuffle method. I started writing "private void Shuffle" and it offered to write the method. That it did pretty much as I would have. So in a few minutes I had everything I needed.

Not sure how I feel about this. How did it figure out what I was up too? Does it have sort of understanding of the words I am using?

Of course, I am working on well-known, established, and simple programming here. There are probably dozens of examples of code on the Internet already that handle these sorts of puzzles. I am not asking AI to do anything new or innovative. Just how useful would AI be if I were working on problems no one has seen before?

None of this is perfect though. Some of the variable names, both that I wrote and that AI wrote, are not particularly informative. I assume I could ask CoPilot to rename things and I may do that. I do believe that the human touch in selecting names may be better than what AI comes up with however.

When if comes right down to it, I will probably not really understand the limits and abilities of AI until I decide to tackle a non-trivial and innovative project. And that is going to take some effort.