In your experience, can you take the tech debt riddled code, and ask claude to come up with an entirely new version that fixes the tech debt/design issues you've identified? Presumably there's a set of tests that you'd keep the same, but you could leverage the power of ai in greenfield scenarios to just do a rewrite (while letting it see the old code). I dont know how well this would work, i havn't got to the heavy tech debt stage in any of my projects as I do mostly prototyping. I'd be interested in others thoughts.
I built an inventory tracking system as an exercise in "vibe coding" recently. I built a decent spec in conversation with Claude, then asked it to build it. It was kind of amazing - in 2 hours Claude churned out a credible looking app.
It looked really good, but as I got into the details the weirdness really started coming out. There's huge functions which interleave many concepts, and there's database queries everywhere. Huge amounts of duplication. It makes it very hard to change anything without breaking something else.
You can of course focus on getting the AI to simplify and condense. But that requires a good understanding of the codebase. Definitely no longer vibe-coded.
My enthusiasm for the technology has really gone in a wave. From "WOW" when it churned out 10k lines of credible looking code, to "Ohhhh" when I started getting into the weeds of the implementation and realising just how much of a mess it was. It's clearly very powerful for quick and dirty prototypes (and it seems to be particularly good at building decent CRUD frontends), but in software and user interaction the devil is in the details. And the details are a mess.
At the moment, good code structure for humans is good code structure for AIs and bad code structure for humans is still bad code structure for AIs too. At least to a first approximation.
I qualify that because hey, someone comes back and reads this 5 years later, I have no idea what you will be facing then. But at the moment this is still true.
The problem is, people see the AIs coding, I dunno, what, a 100 times faster minimum in terms of churning out lines? And it just blows out their mental estimation models and they substitute an "infinity" for the capability of the models, either today or in the future. But they are not infinitely capable. They are finitely capable. As such they will still face many of the same challenges humans do... no matter how good they get in the future. Getting better will move the threshold but it can never remove it.
There is no model coming that will be able to consume an arbitrarily large amount of code goop and integrate with it instantly. That's not a limitation of Artificial Intelligences, that's a limitation of finite intelligences. A model that makes what we humans would call subjectively better code is going to produce a code base that can do more and go farther than a model that just hyper-focuses on the short-term and slops something out that works today. That's a continuum, not a binary, so there will always be room for a better model that makes better code. We will never overwhelm bad code with infinite intelligence because we can't have the latter.
Today, in 2026, providing the guidance for better code is a human role. I'm not promising it will be forever, but it is today. If you're not doing that, you will pay the price of a bad code base. I say that without emotion, just as "tech debt" is not always necessarily bad. It's just a tradeoff you need to decide about, but I guarantee a lot of people are making poor ones today without realizing it, and will be paying for it for years to come no matter how good the future AIs may be. (If the rumors and guesses are true that Windows is nearly in collapse from AI code... how much larger an object lesson do you need? If that is their problem they're probably in even bigger trouble than they realize.)
I also don't guarantee that "good code for humans" and "good code for AIs" will remain as aligned as they are now, though it is my opinion we ought to strive for that to be the case. It hasn't been talked about as much lately, but it's still good for us to be able to figure out why a system did what it did and even if it costs us some percentage of efficiency, having the AIs write human-legible code into the indefinite future is probably still a valuable thing to do so we can examine things if necessary. (Personally I suspect that while there will be some efficiency gain for letting the AIs make their own programming languages that I doubt it'll ever be more than some more-or-less fixed percentage gain rather than some step-change in capability that we're missing out on... and if it is, maybe we should miss out on that step-change. As the moltbots prove that whatever fiction we may have told ourselves about keeping AIs in boxes is total garbage in a world where people will proactively let AIs out of the box for entertainment purposes.)
Perhaps it depends on the nature of the tech-debt. A lot of the software we create has consequences beyond a paticular codebase.
Published APIs cannot be changed without causing friction on the client's end, which may not be under our control. Even if the API is properly versioned, users will be unhappy if they are asked to adopt a completely changed version of the API on a regular basis.
Data that was created according to a previous version of the data model continues to exist in various places and may not be easy to migrate.
User interfaces cannot be radically changed too frequently without confusing the hell out of human users.
> ask claude to come up with an entirely new version that fixes the tech debt/design issues you've identified?
I haven't tried that yet, so not sure.
Once upon a time I was at a company where the PRD specified that the product needs to have a toggle to enable a certain feature temporarily. Engineering implemented it literally, it worked perfectly. But it was vital to be able to disable the feature, which should've been obvious to anyone. Since the PRD didn't mention that, it was not implemented.
In that case, it was done as a protest. But AI is kind of like that, although out of sheer dumbness.
The story is meant to say that with AI it is imperative to be extremely prescriptive about everything, or things will go haywire. So doing a full rewrite will probably work well, only if you manage to have very tight test case coverage for absolutely everything. Which is pretty hard.
Take Claude Code itself. It's got access to an endless amount of tokens and many (hopefully smart) engineers working on it and they can't build a fucking TUI with it.
So, my answer would be no. Tech debt shows up even if every single change made the right decisions and this type of holistic view of projects is something AIs absolutely suck at. They can't keep all that context in their heads so they are forever stuck in the local maxima. That has been my experience at least. Maybe it'll get better... any day now!
