Forem: Jarne

Turn off AI code completion

Jarne — Tue, 28 Oct 2025 18:55:35 +0000

Over the last few years, writing code has become increasingly easy. Everyone with a decent knowledge about AI is able to set up some small app or website. AI writes code for you, AI predicts what code you want to write. Most code editors come with tons of AI features out of the box these days. While they can be useful, some of them destroy your motivation, flatten your learning curve and kill your progress.

How I learned with and without AI

When I wrote my first lines of code, I had never heard of AI before. I'm not the guy that tells you that old ways are best, but over the years I realized that learning without specific AI features improves your progress significantly.
While programming for the first few years, stackoverflow.com was my place to go when I encountered any problem. Nearly every problem I had at the beginning - someone else asked a question about it before.
Now I head over to ChatGPT if I have questions about problems I encounter. This is way faster and simpler in most cases and I would recommend this to everyone in this time. If the proposed solutions don't work, you can still head to stackoverflow or some GitHub issues.

What AI can do for you

Today, AI can help you in every aspect of development. AI writes code, reviews code, checks for errors and security vulnerabilities. AI can explain to you how frameworks work and help you pick an architecture for your next big project.

But don't let AI fool you!

Especially code completion seems really helpful at the beginning. It starts simple with inline and turns

print("He

into

print("Hello, World!")

And that's awesome isn't it?
It gets even better, when AI starts to predict multiple lines of code. You start generating whole methods, you start to trust the code your IDE writes for you. At some point, you might ask the AI inside your IDE to write a whole class or a whole components. The code gets generated, you try it out and you are happy, because it works.

The moment you wish you used less AI

You start having a decent codebase, the start of a big project. That's the point AI starts to struggle. The generated code doesn't fit into your codebase, AI doesn't know how to use up-to-date packages. You try prompting your way through a growing mountain of errors and you start getting frustrated. That's your time to shine as a developer. That's the moment that splits vibe-coder and developers. For a vibe coder, this moment is like a punch in the face. For a developer, it's a challenge. And that is what developing is all about: Solving problems.

The JetBrains developer survey of 2025 clearly shows that one of the biggest weaknesses of AI is code quality. Many developers think that AI is not able to handle complex development tasks.

Here's the most honest advice about the usage of AI I can give you that I learned over the last few years:

✨ Use AI for boring stuff you really know how to do. When you learn programming languages or concepts, AI only helps you in the beginning. If you skip learning the core concepts because AI knows them anyways, you'll get stuck at some point ✨

What you should do

Use AI for

Code Reviews (You learn from your mistakes)
Fix Errors - You can easily ask ChatGPT to explain why a specific error occurred
Research - You want to look for competitors? Want to know how the publishing process works? ChatGPT is awesome helping you with that
Naming things - Because we all know, naming things is hard

Don't let AI

Write code you couldn't write yourself
Make you a debugger of prompted code rather than a developer
Take your understanding of your codebase

Especially if you are a beginner you should turn off your IDE's code completion features. You should write your own code, rather than prompt yourself to a codebase you don't understand.

This way, you'll learn more, stay motivated and become a better developer!

If you have had different experiences, feel free to discuss them with me down below 👇

My 5-year development journey - From kid to bachelor student with 4 years of work experience

Jarne — Fri, 10 Oct 2025 20:37:56 +0000

It's been over 5 years since I saw someone on YouTube building a mobile game which led to me writing my first line of code as a kid during the first COVID lockdown. Since then, I've landed my first junior developer job while I was still in school and I will start my bachelor studies now.
In this blog post, I'll share what I've learned so far, what kept me motivated and how I managed to build some big real-world applications!

My first lines of code

I wrote my first lines of code after watching a YouTube video from Tomary about building a mobile app in one week. I was 14 and sitting at home all day because of the first COVID lockdown and started learning the basics of C# to be able to build my first own game. What helped me a lot were the beginner C# and Unity tutorials from Brackeys, an awesome YouTuber and teacher.

Many people recommend starting with programming languages like Python or JavasSript, because they are easy to understand and learn. But I think the language you start with is not important at all - The only important thing is that you build something you have fun with or is useful for yourself.

That's how I spent many evenings, days and weeks. A few weeks later, I "finished" my first app: A mobile 2D platformer game. Then I did something unusual for a first project. I published it.

Did it get any downloads?
Probably not more than 10 from friends and family.

Do I regret it?
Definitely not!

I only published it on the Play Store at that time because I only had an Android phone to test it on. Even though it can be tricky, I recommend everyone to publish even the smallest projects.

When publishing your projects, you learn way more than just programming. You learn how to bundle the app, how to set up a store page. You might even get some feedback you can use to improve.

The months after that, I built 2 more 2D mobile games. All three of the games pretty much didn't reach any audience, but I learned so much building them. And the most important thing: I had fun building them (a lot, actually).

My "Fuck around and find out"-Phase

After publishing three games, I wanted to build different stuff. Still during my first year of programming, I tried many different languages and frameworks.

I had an idea → I looked up how to build it → Some dude on Stack Overflow recommended using this Python library → I started watching Python tutorials and building what was in my head

This way, I learned a lot of basics:

Python for building some discord bots and playing around with machine learning
Java for writing some Minecraft plugins
Flutter to build basic mobile apps

While I didn't learn anything in depth at that time, I built software I actually used. This way I found out what works and what doesn't. I got a decent understanding of many different basic concepts I still apply today.

My late entry to web development

Nearly a year into programming, I wanted to build a website. I wanted to build apps that everyone can access by just opening their browser.

So I started looking into HTML and CSS. Then I looked into JavaScript. Then I heard about frameworks and started looking into react. I learned the basics and build my first few websites.

During my learning process, I worked with many different types of learning materials. There were YouTube tutorials, courses on Sololearn and some tutorials on freecodecamp. These platforms helped me understand what I was doing, and quite important to me at that time, they were free!

🏢 The internship that changed everything

In autumn of 2021, I voluntarily attended an internship during the holidays that was initially required by my school but cancelled due to COVID. Just weeks before I acquired my first job as a 15 years old student washing dishes at a restaurant.

When I started the internship, I was provided a computer with React Native - a framework I have never seen in my life. During the week of my internship, I built 2 games with that framework which is typically used for "normal" apps (But what else would a 15 years old boy think of to build). My first game was a clicking game, where two players competed on the same device. My second game was a simple snake clone with gesture controls.

At the last day of my internship I met the team leader. For the first moment, he was just a random guy that I've never seen before who asked me to grab lunch. That day, I ate lunch with two completely unknown persons.

But we got along great! We chatted a lot, played the first game I have developed during the internship and finally spoke about the boring job I have just started. Apparently, they were quite impressed of my skills and creativity that they asked their boss to offer me a student contract. Fast forward three weeks, I was sitting at the same desk, but this time getting paid and working on a real multi-platform application.

I learned so much about continuously developing an app and working together on the same project as a team.

Over the last 4 years, I improved my skills in that area. I started taking more responsibility, started writing my first lines of backend code. For the first nearly 3 years, I only worked a few hours per week. After graduating last year, I increased my working hours and experienced the whole development cycle more in depth.

Building and launching hobby projects along the way

One thing that helped me in so many different ways was to keep developing my own projects. I mostly stayed in the field of web and app development, looking into frameworks like Node.js, Next.js, and Expo. To this point, I get most of my learning resources from udemy. It's a great place to get high quality courses for a really fair price.

I also started building my own apps. The first big app I built was called MyGainplan. A fitness app to manage your workouts and discover other users workouts. I built everything myself: The frontend with React Native, the backend and authentication with Node.js and MySQL. I learned a lot about databases, containerization and hosting on that project.
Even though the app got a handful of users, I decided to shut it down after the activity started to drop down to pretty much nothing and I wanted to save the server costs.

Then, during this summer, I released my second app. I took the lessons learned from MyGainplan and published MotoMeet, a social platform for motorcycle riders to meet up for group rides. This time, I decided to stick with a managed backend with supabase to reduce the server costs and not having to worry about authentication or hosting. I'm really happy about how MotoMeet turned out, there are a few hundred user accounts so far and the app is sometimes used by people all over the world.

Starting of my university studies

After a year of working as a part time developer, I wanted to learn more. I have fun working as an app developer (and still continue working for that company), but I wanted to take an even deeper dive into the world of computer science.

So I took a really big step and moved to Munich. I signed up for a bachelor's degree at the Technical University of Munich and I am starting my studies now. Looking back, that one YouTube video I saw 5 years ago really inspired me to go a long, long way.

TL; DR

Even though I am not at the end of my journey, here are my key takeaways from what I've learned:

Don't just build what's easy, build what is fun and useful to you
Don't believe people who say they have the best roadmap to become a developer. Find out what you want to do and just do it!
Even though it's tempting to vibe code your thoughts, use AI as a tool to help you develop not to build whole projects. This won't get you anywhere in the long run

I would love to see your thoughts and questions down below and I'll answer as many as I can.

Enjoy your own journey of learning to code!

~Jarne