AInews · 2026-06-30 · 2 min read
Keeping coding skills sharp while using AI
A personal reflection on coding practice, understanding generated code, and staying responsible for the result.
Can relying on AI reduce the amount of coding practice we get? A recent conversation made me think about that question. It is a personal observation, not evidence that AI makes developers less capable.
An experience that made me pause
A good friend of mine, a former C++ developer, has not been writing much code by hand for a while. He writes with AI now. I asked him to write bubble sort from memory, in iPhone Notes, with one condition: no looking things up, no asking anyone, and the code had to compile on the first try. He said, sure, of course. He had learned it at university, used it at work, and he knew it.
He remembered the overall algorithm but missed a condition in the loop. The exercise prompted a conversation about practice: which skills do we still use directly, and which do we now leave to a tool?
The habit worth watching
One mistake in a small exercise cannot tell us why it happened or how capable someone is at their job. The useful question is whether our daily habits leave enough room to understand code, reason through a problem, and debug without accepting the first generated answer.
That does not mean AI is bad. It is useful. It speeds up routine work and gives you room to focus on the parts that actually need judgment. But architecture is still built on your knowledge, not the model’s. System design, tradeoffs, and the shape of the project are still yours. The AI does not own the outcome. You do.
Keep practicing the fundamentals
I still use AI for routine work. I also make time to write and debug code directly, especially when learning a language or working in an unfamiliar system. Being able to explain a change is a useful check before accepting it.
Planning an AI automation initiative? Read the AI automation POC guide.