May 29, 2026 ~1 minute minutes read Admin

Mastering AI Coding Tools: A Game Changer

AI coding tools can be effective when used to draft code and handle repetitive tasks, but developers must review and verify the output.

Most developers use AI coding tools wrong. I was no exception.

I tried AI assistants, got frustrated when they produced buggy code, and swore them off. Then I stumbled on Karpathy's framework for thinking about AI as a coding partner, and everything shifted.

The four principles that changed my workflow:

  1. Use AI to draft and accelerate coding, but keep human responsibility for correctness. Treat AI as a first-draft generator, not a final answer. It writes code fast; you verify faster.

  2. Delegate boilerplate, repetitive edits, and test scaffolding to the model. Use it for the boring stuff (boilerplate, refactoring, test generation) so you can focus on the hard problems.

  3. Always review what it produces. Every single line. This isn't optional; it's the harness that makes the tool safe. Review AI output carefully for important or persistent code, even if Karpathy's original vibe-coding demo allowed "Accept All" for disposable projects.

  4. Iterate in small loops. Prompt, review, correct, repeat. Don't dump a whole project and hope.

Once I applied these, I couldn't go back. The speed difference is real, but only because I stopped treating AI as a replacement for my judgment and started treating it as a lever for my attention.

What's your experience? Are you fighting AI or working with it?