I've been writing about AI coding tools for months here on Dev.to. Comparisons, benchmarks, tutorials on how to squeeze the most out of Claude Code, Cursor, and the rest. And I do use them. Every single day.

But last week I tried something that surprised even me.

I turned them off completely.

For an entire week, no AI-generated code, no autocomplete suggestions, no "explain this function" prompts. Just me, my editor, and a blinking cursor.

Here's what actually happened.

The First Few Days Were Rough

Day one was humbling. My output dropped by maybe half. What normally took 15 minutes stretched to 40. I found myself reaching for the Cmd+K shortcut out of muscle memory half a dozen times.

But somewhere around day three, something shifted.

I started reading source code instead of asking for summaries. I traced through execution paths instead of having the LLM walk me through them. I caught a subtle race condition that Claude Code had confidently dismissed as "not an issue" in the same codebase two weeks prior.

That moment stuck with me.

The Code Was Cleaner

Here's the part I didn't expect. By day five, my code was noticeably simpler. Not because an LLM optimized it, but because I actually understood the problem well enough to keep it simple.

AI-generated code often over-engineers. It adds abstractions for scenarios that don't exist. It writes defensive checks for edge cases that don't apply to your use case. It looks professional but carries unnecessary complexity.

When you write it yourself, you stop at the simplest working solution because you know when you're done. An LLM doesn't know when you're done. It just keeps going until the context window runs out.

The Real Cost of Productivity

This is the part I've been thinking about most.

AI tools remove friction. That's their superpower. But friction isn't always bad. The struggle of debugging your own code is how you learn a codebase. The effort of designing an API is how you develop taste for what makes a good one.

If you outsource those moments to an LLM, you get the output but not the learning.

I'm not going to pretend I'm quitting AI forever. I still use it. But I changed my personal rule:

Generate only what you could write yourself. Use AI to accelerate understanding, not replace it.

That means no more asking for solutions to problems I haven't fully understood first. No more accepting generated code that I can't explain line by line. The back-and-forth of debugging AI-generated code often takes longer than writing it right the first time.

Where's Your Line?

I think the real skill in 2026 isn't knowing how to prompt an LLM. It's knowing when not to.

Do you review every line AI generates? Have you ever shipped code you didn't fully understand because the tests passed? Have you noticed AI "productivity" costing you more debugging time on the back end?

I don't think there's one right answer. But I think we should talk about it more.