I Might Be a Dinosaur, But the Code Still Runs

A dinosaur codes.

I’m a bit of a dinosaur when it comes to technology.

That might sound odd, especially since I know people who’ve been coding longer than I’ve been alive. But I can no longer pretend I’m the “young kid” to their seasoned vet status. I’m just… slightly less seasoned. And nothing has made that clearer than these last few weeks working on Wandrip.

So, for context, here’s a quick rundown of Jon’s Programmer History, which might help you understand why I’ve been so amazed by modern tools lately.

🕹️ 1995–2003: The Early Years

In 1995, I discovered a shareware app—possibly called Computer Magic—that let you script small animations. It blew my mind. I could tell the computer what to do, and it would do it. That summer, the programming bug bit hard.

By 1996, I was talking about computer programming for a science fair. In 1997, I finally began writing real software with Borland Delphi, making me one of the few in my generation who didn’t start with BASIC. I started with Pascal, specifically the object-oriented flavor used by Delphi.

Through the late ’90s, I did the full “computer kid” routine: wrote a few clunky apps, bought a domain name, packaged my software, and uploaded it to shareware sites. I even made one sale. (Never cashed the check, but the buyer did get their unlock code.) I collaborated with other indie devs, integrated tools, and picked up some IT consulting gigs.

But like many “computer kids,” I spent more time fixing computers than writing software. By the early 2000s, programming had taken a backseat to server management and hardware troubleshooting. Aside from some scripting in PHP (Most of which is actually still in production, 15 years later!), I wasn’t doing a lot of programming.


🤖 2011–2016: The Android Interlude

In 2011, I got back into development via Android. I built a calorie database app for restaurant foods and released it on the Play Store. It eventually saw 400–500k downloads.

Oddly enough, as of this writing, it’s still installed on 397 devices—and someone even redistributed the APK with their name on it, despite it still having my bundle ID: com.jonwestfall.ffcal.

Then another long pause from 2016 until now.

📱 2025: Wandrip and the Wonders of Modern Dev

Fast forward to today: I’m deep in development on Wandrip. And I’m absolutely floored by how much easier—and faster—everything is.

Let’s walk through a simple example: fixing a bug.

Back in 1997, if I found a bug in one of my programs, the process looked like this:

  • Boot up my Windows 95 machine (which I had likely just reformatted… again).
  • Reinstall my development tools (Delphi, utilities, installer creators).
  • Hunt down my source code (version control? What’s that?).
  • Try to remember what my uncommented spaghetti code even did.
  • Fix the bug, compile (if I could), and generate a new installer using InstallShield.
  • Upload the new setup.exe to my web host. Submit to Download.com.
  • Wait and hope people downloaded the new version (and that they didn’t just stick with the buggy one).

And if I had any questions? I’d consult my books or maybe a newsgroup post from six months earlier. Google didn’t exist. StackOverflow wasn’t even a dream.

Now compare that to today:

  • I log into a GitHub Codespace. It automatically pulls my code.
  • I fix the bug—often with help from an AI assistant.
  • I test it directly in the browser, commit the changes, and launch a build using Expo Application Services (EAS).
  • EAS can compile Android and iOS apps on its servers, help with distribution, and even push updates to app stores.

All of this can take under an hour. On an iPad.

It’s been nearly 30 years since I started programming, and I still find joy in it. If anything, I find it more joyful today—because I spend more time creating and less time fighting my tools.

Sure, I may be a dinosaur. But the code still runs.

What Are My Blind Spots? I Asked ChatGPT.

A few moments ago, I came across an intriguing post on Reddit that posed a simple yet provocative prompt: “Now that you can remember everything I’ve ever typed here, point out my top five blind spots?” (source). The idea stuck with me.

As someone who’s used ChatGPT extensively across a wide range of projects—academic writing, software development, teaching, and even a bit of whimsy—I figured the model might actually have something insightful to say. After all, it’s been part of my daily workflow for months, across everything from syllabus edits to tour app debugging to conversations about cats and Canadian geese.

The Geese

So I asked.

Here’s what it said.

My Top 5 Blind Spots (According to ChatGPT)

1. Tendency to Overbuild Before Testing

I often refine systems and features to a high level of polish before seeing how they work in the wild. This can slow down feedback and iteration.

2. Taking on Too Much Solo

I frequently carry the full load of a project myself, even when collaboration could make things easier—or better.

3. Over-Correcting for Clarity

My preference for precision and structure can sometimes get in the way of creativity or navigating ambiguity.

4. Fast-Paced Thinking, Slower-Paced People

I move quickly between ideas, modes, and tasks. Others don’t always keep up, and I don’t always pause to bring them along.

5. Understating My Influence

I tend to frame my statements cautiously, even when I have the authority or expertise to speak more definitively.

I have to say, this was more insightful than I expected. These aren’t things I’m completely unaware of—but they’re definitely themes I don’t always recognize in the moment. It’s a little like holding up a mirror that reflects not just how I act, but how I tend to act across contexts.

And that, honestly, feels like one of the most useful ways to use tools like ChatGPT—not just as a productivity enhancer, but as a thinking partner that notices patterns you might miss. In some cases, I can clearly see where some of these blind spots come from – for example, when you have a lot of interests, it can be hard to find collaborators because you don’t get deep into communities around one interest. And it doesn’t help when they may move too slow for you anyway (see #4)!

I’m not sure what, if anything, I should do about this. But it is interesting pushing an LLM to be critical of you and provide constructive comments. It’s a far cry from the usual flattery it provides. And perhaps useful if for nothing else than to see what it’s been thinking about you behind your back!