AI Made Us Fast. But Did It Make Us Better?

I’ve been using agents for work for months now. Cursor, Claude, automated flows, the whole stack. I’ve shipped things in hours that used to take days. Weekend prototypes that would’ve landed on next quarter’s backlog.

And I still catch myself wondering whether I’m getting better or just moving faster.

What happens when there’s 10x more code

Something I notice in my own PRs: when an agent writes way more code than I would, there’s way more code to review. More surface area for bugs. More small decisions hiding in the diff.

We’re supposed to not worry about that because “the AI probably nailed it.” I fell into that too. Once it fixes the regex you’ve been avoiding. Another time it refactors that ugly function. And suddenly you’re reading fewer lines. Trusting a little too much. Vibecoding without meaning to.

Reading AI-generated code bores me, I’ll admit it. It’s like proofreading someone else’s work. The general shape looks fine and your eyes slide past the details. But bugs live in the details. And the small architectural decisions are the ones you live with for two years.

I don’t see a comfortable middle ground

I’ve been turning this over in my head and I don’t have a clear answer.

If you delegate everything to agents that produce 100x more than you, you can’t keep up as a human reviewer. You’d have to delegate the review. Then the testing. Then the architecture decisions. It’s delegation all the way down until you’re not really looking at anything.

Teams built guardrails for a reason: checklists, double approval, a senior who blocks a rushed merge. That wasn’t free bureaucracy. It was a way to enforce slowness on purpose.

Those processes still exist in a lot of places. But the vibe shifted. From “let’s be careful” to “let’s be fast.” And I’m not sure how long that works.

Judgment, not speed

The hardest thing for me to delegate isn’t typing. It’s judgment. Knowing when to push back. When a requirement sounds reasonable but will become a maintenance nightmare six months later.

Agents don’t do that. You ask them to build something and they build it. They won’t tell you the feature isn’t worth the complexity. They don’t have an opinion on whether that migration is the right call or whether you’re over-engineering a problem that doesn’t exist yet.

That judgment, I think, comes from years of getting things wrong. Maintaining bad decisions. Going slow until intuition shows up. I don’t have formal proof. It’s what I see in the seniors I respect and in my own work when things get messy.

The day I stopped on an SVG

The other day I was about to ask Claude for an SVG animation. I had the prompt almost ready. And I stopped.

Not because the AI couldn’t do it. Probably better than me on the first try. But because I didn’t really understand how to animate an SVG. And if I don’t understand it, I can’t review what comes out properly.

The productivity I have with AI today comes from years of learning without it. All that slow stuff before, tutorials, Stack Overflow, the “why doesn’t this work” frustration, that was the foundation. Without it, prompting feels like guessing. With it, at least you can steer and audit.

I worry a bit that this atrophies if I never stop to learn by hand. I’m not saying everything should be done without AI. That would be ridiculous. But there are things where I stick it out and go slow: patterns I’ll use often, CSS, SQL, system design, things where the AI gets it wrong and I have to filter.

My imperfect practical rule: if something’s going to need judgment from me in six months, I try to learn it now. If it’s disposable and low risk, the AI.

Better, or just faster?

I don’t have a clear answer. I’m not going to tell you to stop using AI. I’m not stopping.

But I do think there’s a trade-off we don’t talk about much. We can ship more without necessarily knowing more. We can produce more output without producing more judgment. And the developer who can do the thing without AI, it seems to me, has an edge when they use it. Not because they’re faster. Because they know what they’re looking at.

I try to keep learning by hand every so often. SVGs, weird regexes, new things I could solve with a prompt. I don’t know if it’s enough. I don’t know if I’m finding the balance. The agents are going to keep getting faster. The question I’m left with is whether we’re going to keep getting better. Or whether we’ll get used to running without really knowing where.