AI makes technical debt a bigger problem than ever because it's so easy to pile on new code and the AI resists removing code even when explicitly asked, while many of its biggest boosters have never had to maintain an old, long-running codebase and don't grasp the consequences.
Wes argues that inexperienced 'prompt bros' underestimate real tech debt because AI makes adding code trivial but strongly resists removing it, setting teams up for a reckoning. ✦ AI generated
Wes Bos · Syntax · 2026-07-08 · original ↗
starts at this moment · 10:14
“On my team, a common workflow is an engineer asks an agent to implement a feature or fix a bug, open a PR, address automated review comments if necessary, waits for CI to pass, and merges. In many cases, there is little to no meaningful human review of the actual code.”
I think one thing that the prompt bros don't realize about this stuff is because, you know, most of them have never maintained old systems or long-running systems or these types of things. That tech debt is really real and tech debt is such a major problem with AI now because it's so easy to add code and like AI hates to remove code even when you beg it to remove code.
verbatim transcript · starts at 10:14
10:14it's easy the AI can explain it to you but those like high-level architecture, you know, if you're just adding a whole bunch of crap and duplicating it it's going to be very tricky to sort of unwind a lot of those especially if you don't have like tests and whatnot. >> I think one thing that the prompt bros don't realize about this stuff is because, you know, most of them have
10:36never maintained old systems or long-running systems or these types of things. That tech debt is really real and and tech debt is is such a major problem with AI now because it's so easy to add code and like AI hates to remove code even when you beg it to remove code. So like yeah, I just feel like the amount of code that we be adding sometimes is going to come back to haunt teams.
11:02And sure, you know, Fable is going to come out again and the the clouds will part and you'll say hey make it better and they'll make it better. [laughter] Um and and maybe that's the case but yeah, in the meantime I think we're going to be seeing a lot of software and apps like barely held together cuz that's that's wild to me. Next question here from Sarah Chen. In episode 1009 you
11:26mentioned that nobody knows what a local model is. Can you do an explainer on what local models are? Well, local models are just uh models that you're running on your local machine. I think some people really disconnect that and think, "Ooh, I'm running the software locally, therefore it's local." But it like when reality they're going off and doing API calls. That was the whole thing >> Yeah, all these people are like, "Just
11:52use a local thing." It runs a local use open code and deep seek for local. Like, that's not local. It's going to China. >> Yeah, so it's it's literally running on your machine. And I will point you to the CJ did a really incredible video called your guide to local AI. And so instead of just recreating that here, cuz you know we could I could just recreate CJ's awesome video on the fly
- ·AI makes adding new code trivial and fast
- ·AI strongly resists removing code, even when asked
- ·Result: debt piles up faster than ever before
- ·Many AI boosters never maintained old, long-running codebases
- ·They underestimate how real tech debt consequences are
- ·Sets teams up for a painful future reckoning