Studio711.com – Ben Martens

High School Search

As I mentioned earlier, we’re planning a move to Minnesota in the summer of 2027. During Elijah’s spring break, we flew out there as a family to visit all three of the high schools that our national church body runs: WestSt. Croix, and Minnesota Valley.

It felt a bit odd to be exploring all three of those schools. We knew ahead of time that they were all great and we didn’t want to give the impression that we were shopping them against each other, but it was a big help to see them all and also to drive around the three areas. They have distinct personalities and ministries. Thankfully we left thinking we could see how attending each one of them would be great, and it also got Elijah even more excited about the move.

Before we visited Minnesota Valley, we stopped in for chapel and lunch at Martin Luther College. For being a “random”, tiny college 1500 miles away from us, it’s amazing how welcome we feel when we step on campus. As soon as we got out of the car, one of the staff members saw us and waved, and when we went into the cafe, we were mobbed (in a great way) by so many people welcoming us and giving us hugs. I was especially thankful to the students that got up to come over and say hi to Elijah. It makes such a huge impression on him.

We got a lot of practice explaining our move. I’ve learned to start with “I can do my job from anywhere” and “We’ve lived in this area before”. That gets through most of the initial questions. There was also confusion at MLC because some people knew Tyla and I were coming back the following Friday for a President’s Advisory Council meeting. We thought a lot about combining the trips, but it was simpler to split them up and to do it when Elijah was on break.

That trip the following week did go smoothly as well. We are so thankful to have the opportunity to give feedback on challenges the school is facing and plans for the future. The administration is full of amazing people who put everything they have into making it the best possible training school for every pastor, teacher, and staff minister in our church body. I also got to have a good chat with their IT team to learn how they are adopting AI in their software development process.

I’m sure there will be many more trips in our future as we zero in on a specific place to live, but this was a big checkbox for us!

Quotes

A couple quotes that I heard recently have been floating around in my head.

“I think if you don’t have dreams about what might happen in your life, then how do you know what you want to do next? How do you choose whether I should do this or do that if you don’t really care where you end up? … I think it’s a wonderful gift to reflect within yourself and ask what do I actually hope will happen in my life if my life goes perfectly from now on? What do I dream will happen and what am I doing today and this weekend in order to change who I am deliberately?”

– Astronaut Chris Hadfield on the Mythfits podcast, April 27, 2026

I like this one because it encourages us to have a vision and work towards it. If you just float along letting life happen to you, it’s unlikely that your situation is going to improve.

The next one comes from the creator of a popular open-source project that recently decided not to allow AI generated code submissions. While this is about code, I think it applies to AI generated text even more.

It’s a common misconception that we can’t tell who is using LLM and who is not. I’m sure we didn’t catch 100% of LLM-assisted PRs over the past few months, but the kind of mistakes humans make are fundamentally different than LLM hallucinations, making them easy to spot. Furthermore, people who come from the world of agentic coding have a certain digital smell that is not obvious to them but is obvious to those who abstain. It’s like when a smoker walks into the room, everybody who doesn’t smoke instantly knows it.

I’m not telling you not to smoke, but I am telling you not to smoke in my house.

— Andrew Kelley

You can read more about their rationale for this move here. I’m not sure I totally agree with it because I think source code is becoming a generated artifact and specs are more important, I do think about this comparison to smoking every time I’m writing text and using AI to help me clean it up.

Copilot for the Win!

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!

Gas Prices

For the last ~6 years, I’ve watched gas prices mostly as a curiosity since my truck stayed parked in the driveway most days, but now that I’m driving back and forth to work, I feel the pain of those $100 fill-ups. But how bad is it compared to the past few years?

Since March of 2022, I have been running an app to record a half dozen gas stations close to me every day. I use this to carefully calculate how much money we are saving with the Tesla compared to a gas car. Here’s the chart:

So they are high but not quite as bad as when Russia invaded Ukraine. We live in a nice little pocket of reasonably priced gas, but there are currently some stations at $5.99 for gas and over $7.29 for diesel. Ouch.

I wonder what we’ll think when we look back at this post in 10 years.

Being Good At Things You Dislike

Parenting is an interesting opportunity to think about important personality traits and life skills. Sometimes it feels like it’s hard to communicate anything so if I’m going to pick a few things to focus on, what should they be?

Lately, I’ve been thinking that one near the top of the list is the ability to be good at things you dislike. Too many people see a task they don’t like doing and they do the bare minimum required to get it off their list. But successful people are able to be excellent at things even if they dislike doing them. It doesn’t mean that they ever end up liking the task, but you’d never know it by the quality of their work. This advice shows up in the Bible too: “So whether you eat or drink or whatever you do, do it all for the glory of God.” (1 Corinthians 10:31)

Often those things we don’t like doing are the hard things. We’d rather spend our time doing the fun things. Elijah gets tired of hearing me say “Work first, then play” but there are better versions of that quote:

  • “Do what you have to do until you can do what you want to do.” – Oprah Winfrey
  • “Do the hard jobs first. The easy jobs will take care of themselves.” – Dale Carnegie

It’s a straightforward lesson, but it’s one I need to remind myself of too.

Tax Receipt

Happy Tax Day!

As I do most years on this day, I encourage you to view your tax form and look at line 16 of Form 1040. This is how much money you paid the federal government in 2025. I’m not trying to sway your political viewpoint one way or another, but I do feel that most people don’t understand how much tax they actually paid (versus the refund they get).

To take it one step further, visit MyTaxReceipt.org. This site will show you where your dollars were spent. Can you predict the top three in order?

Happy Easter!

The angel said to the women, “Do not be afraid, for I know that you are looking for Jesus, who was crucified.  He is not here; he has risen, just as he said.  Come and see the place where he lay.  Then go quickly and tell his disciples: ‘He has risen from the dead and is going ahead of you into Galilee.  There you will see him.  Now I have told you.”  Matthew 28:5-7

Today we take extra time to celebrate Jesus’s resurrection. He took our place on the cross and died for all of our sins. His resurrection from the dead proved his power over sin, death and the devil. There’s nothing we can do to earn heaven. It’s a free gift available to everyone who believes.

Our church’s online Easter service is available after 8am Pacific time: https://www.youtube.com/watch?v=YY8c_wSBzvg

The Impact of AI

The other day at church, someone asked me if I thought AI was a fad. I was caught off guard. I could tell the person was probably not a fan of AI, and I had to be up front to play the piano in about 30 seconds. So I rattled off a quick answer that probably didn’t land and I headed off to play. It was a quick conversation, but it got me thinking about how people’s opinions of AI are the result of them reacting to a very narrow slice of what they’ve personally experienced.

If I had it to do over again with more time to respond, I would have started by asking what they meant by “AI.” Everyone means something different when they say it and even when they define it, it’s still easy to misunderstand them. In practice, many people mean “the free chatbot I tried.” If that’s your only exposure, I completely understand why you might decide that AI isn’t very impressive.

The free versions of Copilot and ChatGPT might not amaze you, but for coders, it’s incredible. Programming languages are a perfect playground for LLMs because the language is perfectly defined and there are countless examples for it to train on. But for other professions where AI isn’t as good (yet), it can be harder to see the value.

Anthropic (the company behind some of the most impressive AI models) recently published a paper on the labor impacts of AI.

Note that the red area is the impact that is already happening and the blue is the theoretical impact. I don’t know how they judge the theoretical upper bound, but the chart is a helpful way to frame the conversation. Will AI impact all areas of life? Yes. Will it have the same level of impact on all areas? Not even close.

The other big takeaway that is hard to grasp is that we ain’t seen nothing yet. So many areas are going to see enormous growth. For example, someone DNA sequenced their dog, developed a custom cancer vaccine, and cured their dog. It will take a while for this kind of thing to translate to humans, but I think we’ll look back on the next decade and see a noticeable increase in expected lifespan. It’s so much easier to zero in on plausible new drugs for trials when we can feed an agent tons of existing research, all the existing legislation around what can be done, and a series of desired outcomes. We’ve seen similar paths to this at work where we are researching new datacenter technology for physical tasks like improved heat dissipation.

In my area of computer programming, the change has been indescribably large. I’m blessed to have unlimited access to the best models on the planet regardless of cost, and my work life is completely different from what it was even six months ago. I have barely typed a line of code in the last three months, but I have produced more code and more business value than I ever have before. Is it perfect? No, but it is clear that people who know how to use the tools can produce a lot more value than those who don’t.

Areas that rely heavily on the generation of documents are not nearly as far along in their journey, and, according to this analysis, will not see quite the theoretical maximum impact as the more technical areas. This aligns with my personal experience as well. AI is better at summarizing documents and editing them than at creating them. I don’t write documents with AI, but I regularly use AI to review my work, suggest where the document might be confusing for readers, etc.

And finally, areas that are heavily based on physical work have the least impact now and the least theoretical impact. If I’m mowing the lawn, an LLM isn’t going to help me, but it can be valuable when I’m trying to figure out how to repair a broken mower.

As with almost all hot issues, there is more to this story than “AI is dumb. Look at this ridiculous output!” and “AI is going to solve all problems.” AI for software developers hit an inflection point at the end of November last year when two key models were released (Opus 4.5 and GPT 5.1). My work life changed almost overnight. That hasn’t happened in a lot of other areas yet, and a lot of people are judging “AI” by what they can get for free and applying it to areas where it’s not a great fit. That doesn’t make it a fad. It just means AI isn’t growing at the same pace in every field, and it isn’t equally useful in every industry.

Circuit Python Temperature Sensors

I love collecting data. Temperature is especially interesting to me and my Ecobee thermostat has three satellite temperature sensors spread around the house. I collect all that data in a database, but I’ve always been curious about having a couple more. Sure, I could just buy the extra sensors when they are on sale and have them automatically connect into the infrastructure I already have, but wouldn’t it be so much more work to design one from scratch? Let’s do it!

This is conceptually a v2 of the pool sensor that I built for Dad and Mom last year. While not without its issues, that sensor is now in a state where it works pretty well. It’s good for monitoring water temperature but I wanted something simpler for measuring air temperature and I didn’t want to do any soldering.

Those search parameters led me to the Circuit Python devices (specifically the QT Py ESP32-S2) from Adafruit and SHT40 temperature sensors. Those two easily connect with a Stemma QT cable. So that puts the total price of each device at around $20 plus tax/shipping. That’s much more expensive than this project needs to be, but I was shooting for assembly simplicity.

The code was largely written by GitHub Copilot. It’s very straightforward but the code ended up being fancier since I didn’t have to write it all by hand. Specifically the color changing LED is very informative to help give feedback about what is going on with the device.

Starting with a published 3D model, I modified it heavily to design my own custom 3D printed case for it and voila! I had a working (mostly) device! The image below is with the front cover off so you can see how everything press fits perfectly and there is a cutout for the USB adapter which provides power.

Problems I’ve had so far:

  • Connecting to WiFi was very unreliable during development. I think the tiny WiFi antennas on these devices are very sensitive to having too much or too little power. I added a config setting for adjusting the power levels that helped a bit, but I also built one that had an external antenna. This raised the cost but seems to work more reliably than my other versions.
  • I’m currently battling some mystery errors. Sometimes I’ll walk by and the light will just be solid red which indicates an unknown error. I’ve had trouble figuring out what this is, but I suspect it’s related to the internet connection. I recently added some code to reboot the devices after being in this state for a while. I’ve mitigated this by updating my data collection app to alert me if there haven’t been any new readings in the last 6 hours. When I get that, I just go power cycle the devices. Not ideal but at least I know when it happens.
  • There was a significant learning curve in flashing the firmware and switching between Python mode and Arduino mode. I’ve got it all documented now but there was a lot of frustration involved with that part. One great thing about Python mode is that the device is recognized by Windows as a filesystem over USB so it’s simple to update the code and config files. The downside is that the code itself can’t log to the file system when it is in this mode which makes debugging much harder.

So in the end I spent hours of my life and more money than if I had just bought more Ecobee sensors. But I learned something. Yay?

Store Brands

This is a bit of a weird post (which is saying something on this site) but as I go through the grocery store each week, I’m always looking at the prices for the store brand versus the name brands. I will almost always default to the store brand unless the name brand happens to be on sale for cheaper, but there are some items that I will always buy the name brand regardless of price. That usually gets me wondering if others feel the same way about these specific items or if there are others I should be considering. Reflecting on this is harder than doing it in store, but here are some that immediately come to mind:

  • Kleenex – Raw nose. Ouch. Enough said.
  • Paper towels – I want the smaller sheets and I don’t want them to fall apart!
  • Toilet paper – Raw… you get it. Ouch. The exception to this is Costco. Their generic brand of toilet paper works well and we had a plumber tell us that it’s one of the best ones for not clogging your pipes too.
  • Trash bags – The cheapo ones fall apart too easily. This is another Costco exception. Their generic brand of bags is great.
  • Bacon – Pay for the good bacon. It’s worth it. Locally I like to get Hempler’s center cut peppered bacon.
  • Cream cheese – This is the newest addition. I have always bought the store brand and just assumed that when a recipe says “softened cream cheese” that was just impossible to do well. Then I bought the good stuff and learned that the consistency of good cream cheese is so much easier to work with!

What did I miss on this list?