Nobody Learns to Ride With the Wheels Bolted Down
Last summer I built an AI chatbot almost entirely in Claude Code. It worked. I never pushed it to GitHub. I felt that putting my name on a public repo felt like making a claim I couldn't back up. There is a particular kind of quiet that follows building something you don't feel entitled to. No matter how rewarding the project feels, somewhere behind your ribs a voice says: you didn't actually do…
Last summer, the author constructed an AI chatbot primarily using Claude Code. They chose not to publish the code on GitHub, feeling that attaching their name to a public repository was premature. The author felt a sense of quietness and self-doubt after completing a project that they did not feel entitled to. They argue against the notion that skill comes from struggle, stating that using AI to fix bugs and learn new things can hinder personal growth.
They suggest that relying on AI without fully understanding the process leads to a lack of learning and can be detrimental in the long run. The author identifies passivity as the real failure mode when accepting AI-generated output without critically evaluating it. They compare training wheels to AI support, stating that the latter only helps if it is continuously raised, otherwise, it will limit the developer's growth.
The author provides concrete rules for using AI effectively, such as reading every line before accepting its output, asking "why" and challenging the model's suggestions, writing the hard part first, and implementing the solution from memory later. They also recommend picking a no-AI zone to develop skills without relying on AI assistance.
Ultimately, the author emphasizes that the goal is not to eliminate AI usage but to maintain a responsible and learning-focused approach when utilizing AI tools.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
