I don’t blog about AI every day, but you can bet I’m using it and discussing it every day. I’m still unable to explain it to non-tech friends. It just sounds unbelievable, and if I wasn’t living through it with a front row view, I wouldn’t believe it either.
I thought it would be worth documenting again some of the projects I’ve done at home with it. Every time I say “Copilot” below, I’m talking about GitHub Copilot with unlimited, full access to everything. (This is extremely different from any free Copilot thing you’ve chatted with on the internet.)
- My main PC was having trouble falling asleep reliably. I knew I could reboot and make it better for a while but it would keep coming back. I fired up copilot.exe and asked it why my machine wasn’t sleeping. It found that one of the apps I use (PowerAutomate) wasn’t being shutdown completely and it was keeping my machine awake. This was a tiny win but it was something I would have just lived with for a long time if it wasn’t so easy to figure it out.
- My file server was rebooting frequently and it would get stuck at the BIOS screen when it started up. Again, I fired up copilot.exe and asked it to analyze my reboots. It analyzed my recent reboots and thought maybe it was an old video driver so I updated that. The next day I had it look again and it identified two of my four hard drives were going bad! It wasn’t enough for Windows to report them as being bad in Storage Spaces yet, but I kept asking for more and more proof and was finally convinced that they really were bad. These were two 8TB drives but thankfully the two 12TB drives were healthy and could handle the full file storage requirements on their own. Hard drive prices are extreme right now so I just removed the bad drives and will live with the 12TB drives (in a mirror configuration) for now. Along the way, Copilot also wrote a Powershell script for me that stores off the SMART data from the drives periodically in a CSV so I can monitor health over time.
- As I was listening to Spotify, I got curious to look at some stats about my listening habits. For example, if I took all my listening over the past year, looked up the year the songs were originally released, and made a histogram, what would it look like? Copilot made quick work of helping me set up a Spotify developer account, connecting to the API, and writing a tool that would periodically pull my usage going forward. It also showed me how to request my previous year of listening history from Spotify. I haven’t gotten around to analyzing it all yet, but I’m collecting the data now.
- When we show videos on the screen in front of church, I usually re-edit them to add a black screen at the start so that I can leave it paused on that black screen throughout the service and not distract anyone until we’re ready for it. I realized that I could probably automate that, and sure enough, in about 15 minutes, I had a powershell script that automates ffmpeg to do this. As a bonus, I did that whole project by chatting with Copilot through the GitHub app on my phone while I was cooking dinner.
- As we think about moving, we’re curious how far various properties are from places we care about (school, Costco, home improvement stores, grocery stores, etc.) Copilot wrote me an app that uses a mapping resource in my Azure subscription to run all this analysis and report it back.
- I was thinking about paying for a ChatGPT subscription to remove the limitations and see how it worked when not in free mode, but then I realized that my Azure subscription can host all of these models. So Copilot wrote me ChatGPT clone that runs on my PC or my phone and uses models hosted in my own Azure subscription. As a bonus, I can use whatever models I want, crank them up as high as I want, and not be limited. (Yes it costs money but I get $150/month for free and that goes a long way.)
It’s a blast being a nerd right now. The cost of experimentation and ideation is approaching zero. You’re only limited by your ambition and imagination and so far that hasn’t been a problem for me!