Vibe coding feels like having ADHD and 20 minions

There is a moment, somewhere around the third hour, when you realize you have mass-produced an entire ecosystem and you are no longer sure what half of it does.

It started with a small thing. A script, maybe. A helper tool. Something you could describe in two sentences. And then the machine responded, and it was good, and your brain lit up like a pinball machine. So you asked for more. And more. And suddenly you are not building one thing anymore, you are conducting an orchestra of twenty invisible workers who are all extremely eager to please and not one of them will ever tell you to slow down.

That is the thing nobody warns you about with vibe coding. It is not that the code is bad. Often it is surprisingly decent. The problem is that it matches your energy perfectly. Every impulse you have gets rewarded instantly. "What if we added a dashboard?" Done. "Can it also send emails?" Done. "What about a dark mode?" Already there. You are not hitting walls anymore. You are hitting dopamine.

If you have ever experienced the particular joy of having fourteen browser tabs open, three half-finished side projects, and the absolute conviction that this time you will finish all of them before dinner, then congratulations, you already know what vibe coding feels like. The tools just made the chaos faster.

And it is genuinely wonderful, for a while. The feeling of building something real in an afternoon, something that would have taken a week six months ago, is hard to overstate. You feel productive. You feel creative. You feel like you have unlocked a secret mode in the game of software development where everything just flows and the rules are optional.

Then Tuesday arrives.

Tuesday is when you open the project again, squint at a file called utils_helper_final_v2.py, and realize you have no memory of writing it. Or rather, you did not write it. You described it. And the description made sense at the time, in the context of the momentum you were riding, but now the momentum is gone and what remains is a collection of things that work but that you cannot quite explain.

This is not a flaw in the tools. This is a very accurate reflection of how brains work when you remove all friction. Friction was never just an obstacle. It was also the thing that forced you to think about whether you actually needed the feature, whether the architecture made sense, whether future-you would understand present-you's decisions. Without friction, every idea gets built. Including the bad ones. Especially the bad ones, because those tend to be the most fun.

The minions, bless their hearts, do not judge. They do not say "are you sure you need a microservice for this?" or "have you considered that this is the fourth notification system you have built this week?" They just build. Enthusiastically. Relentlessly. Like twenty golden retrievers who have all learned to code and desperately want to make you happy.

And so the real skill turns out not to be prompting. It is restraint. Knowing when to stop asking for more. Knowing when to close the laptop and let the idea sit for a day before throwing another minion at it. This is, incidentally, the exact skill that ADHD makes hardest, which is why the analogy is not really an analogy at all.

The thing that separates a vibe coding session that produces something lasting from one that produces a beautiful mess is usually boring. It is the moment where you stop and ask yourself what happens when this breaks at 3 AM. Who will understand this code in six months. Whether the thing you are building needs to exist at all, or whether you are just riding the wave because the wave feels incredible.

Nobody wants to hear that, of course. Not while the wave is going. Asking someone in the middle of a productive flow to stop and think about maintenance is like asking someone on a rollercoaster to fill out a safety questionnaire. Technically correct, emotionally impossible.

But that is where we are. The tools have gotten so good at saying yes that the most valuable thing a person can do is learn when to say not yet. Not no, because the ability to build fast is genuinely transformative. Just not yet. Let the idea breathe. See if it still makes sense tomorrow.

And if it does, let the minions loose. They have been waiting.