Satya Nadella said AI would fuel a “creative revolution.” GitHub told us Copilot would let developers “focus on creative and strategic work.” Sam Altman measures ChatGPT’s success by the percentage of human work it can accomplish. So why am I spending more time reviewing and fixing AI output than I ever imagined?
I’m not here to trash AI. I use it every day. But I need to talk about the gap between what we were promised and what actually showed up, because I don’t think I’m the only one feeling it.
The promises they made
The pitch was straightforward. AI handles the mundane stuff, the boilerplate, and the grunt work, and you get to spend your time on the interesting problems. GitHub’s own research claimed developers using Copilot were 55% faster and that 87% felt it preserved mental effort during repetitive tasks. Nadella called AI “bicycles for the mind” and talked about a future where a billion people could create on Microsoft’s platforms.
Who wouldn’t want that? Hand off the boring stuff, keep the fun stuff. More time to think and create. More time to actually use the skills you spent years developing.
That’s not what happened.
What actually happened
AI made producing things fast. Ridiculously fast. Code, documentation, copy, design specs, you can generate a first draft of almost anything in minutes now. The problem is that producing was never the hard part. Thinking was the hard part. Making good decisions was the hard part. AI doesn’t do that for you. It just gives you a pile of “done” that isn’t.
So now you review. Everything. You review your own AI-generated output because you didn’t actually write it. You prompted it, and prompting and writing are not the same cognitive process. You review your teammates’ AI-assisted work because they’re shipping faster too, and somebody has to make sure it all holds together. The volume of stuff landing on your desk went up. The quality bar didn’t move. You became the quality bar.
The research backs this up. A study on arXiv found that AI-assisted programming actually decreases the productivity of experienced developers by increasing technical debt and maintenance burden. Experienced developers reviewed 6.5% more code after Copilot’s introduction but saw a 19% drop in their own original output. A randomized controlled trial by METR found something even wilder: experienced open-source developers were 19% slower when using AI tools. And the kicker? They still believed AI had sped them up by 20%. We can’t even tell it’s not working.
And this isn’t just a code problem. Anything AI generates, whether it’s a blog post, a design comp, a project plan, or even a Slack message, needs a human to look at it before it ships. We didn’t eliminate work. We changed who does what. AI produces. You QA.
Are we losing the muscle?
This is the part that worries me. When I used to build something from scratch, write a component, architect a system, or draft a document, I was exercising a creative muscle. I was making hundreds of micro-decisions along the way, and each one built intuition. The act of producing wasn’t just about the output. It was about what the process did to my brain.
Now I spend a lot of that time reading something else’s work and deciding if it’s good enough. That’s a different cognitive mode entirely. Reviewing is not creating. They’re both valuable, but they’re not the same skill.
I think about junior developers coming up right now. If they’re leaning on AI to produce from day one, when do they develop the instincts that come from struggling through problems yourself? When do they build the taste that comes from making things badly, learning why, and making them better? You can’t shortcut that with a prompt. And if we’re all just reviewing AI output instead of producing our own work, I’m not sure how we keep that muscle from atrophying.
More work, different shape
I’m not anti-AI. I use Claude, I use Cursor, and I use AI tools constantly. They’re useful. But the narrative that AI reduces your workload? That hasn’t been my experience. The workload didn’t shrink. It shapeshifted.
Producing got faster, but reviewing and fixing filled the gap and then some. And the expectation from the outside didn’t adjust. If AI makes you faster, you should be producing more, right? Nobody factors in the review burden. Nobody accounts for the time spent wrestling mediocre AI output into something that meets your standards. The labor moved downstream and became invisible.
I keep coming back to one question: when does the promise actually land? When does AI get good enough that the review burden drops below what the production burden used to be? Maybe that’s next year. Maybe it’s five years out. Maybe the answer is that creative work was never about efficiency in the first place.
I want to know
I don’t have a clean answer here because I don’t think there is one yet. So instead I’ll ask: is this your experience too? Has AI freed up your creative time, or did it hand you a different pile of work? Are you producing more, or just reviewing more? Are you getting better at your craft, or getting better at evaluating someone else’s approximation of it?
I’d love to hear from people who feel like AI has given them their time back. Genuinely. Because I’d like to know what I’m doing wrong.
Leave a Comment