Comment by jon-wood | Hacker News Reader

Comment by jon-wood | Hacker News Reader

Parent Full thread

> It seems to work well, mainly hurts when the problems are invisible, so security, backups, breaking migrations, perf, maintenance over time (language / runtime updates, dep updates, server updates etc). All the stuff that hurts if you have never been responsible for the uptime of something before. Not knowing that software is never "done". But junior devs trip on those exact same things.

If we continue from your "water comes from the tap" example this situation feels like someone who has no experience of plumbing deciding they're going to replace their bathroom without bothering to find out how any of it works. They'll possibly end up with a bathroom that superficially works but they're also liable to find problems down the line with leaks, things not draining properly, or water pressure issues.

Some of the people writing software purely via LLMs are even turning this into a business, which I guess would be analogous to deciding you're going to run sewage treatment for a small city without understanding anything about how that works. It'll mainly hurt when the problems are invisible, so food poisoning, or inlets backing up and overflowing into a nearby river.

That analogy breaks down immediately because it's missing the critical novel component: the AI.

In the bathroom remodel analogy, the AI is the plumber that you hire to do the work for you. You tell it what you want, it figures out the details necessary to get it to you. If what you want isn't possible, or requires large changes, a good plumber will raise the issue to you and explain the constraints they are working under, ask for guidance, and offer recommendations.

Sometimes the AI does things in a weird or inefficient way, or neglects details that become important later, or misunderstands something important about the task resulting in an outcome other than what you wanted, but that's also the same as the plumber. This is why people usually want to be at home and keep an eye on the people working on their improvement projects or repairs, because they want to make sure that the guy they hired is replacing the broken faucet, not the functional but odd-looking one.

There is still value in knowing the underlying systems well enough to present a good design vision to the plumber up-front. It's still possible to have a competent executor produce a bad idea, which is how we get stuff like Groverhaus, the Doom Bathroom, and McMansion Hell, which are examples of "slop architecture" in exactly the same way as we are seeing "slop software".

There were terrible software developers before LLMs. Honestly for a lot of people AI generated slop is a massive improvement over what they used to ship.

I agree it's pretty bloody cheeky to run an agency like that though. The only ways out I can see are licensing or real liability.

But let he who has never done dodgy home improvements cast the first stone.

> Honestly for a lot of people AI generated slop is a massive improvement over what they used to ship.

Citation very much needed. Otherwise you're basically arguing that the problems associated with people writing bad code somehow go away when they're suddenly in a position to direct the quality of code generated for them.

I am claiming something slightly different! There are varying effects. I can't really cite, I only have anecdotes.

For "terrible programmers" (I use this loosely, sometimes thats me! - not a value judgement of the person. Might be inexperience, working outside usual area, bad week etc) code shifts from being "fractally wrong how do I even explain to you why it's wrong, you clearly have zero mental model of whats going on here", to "actually ok code but wrong approach and you didn't need to add a 200 line Python script for this". The rework process is explaining the right approach which gets meat proxied to Claude who DOES get it.

I get that a lot of people feel mugged giving feedback and having it proxied, without a _relationship_ where you can see a person is growing and mistakes won't recur. It's like the "author" is just using a robot to steal your time. Sometimes I personally feel relief at work though, because it would steal WAY MORE time to explain detailed and intricate stuff across a really large knowledge gap... in which case I am actually grateful that they have Claude as a cognitive prosthesis. At times I am the one who needs the prosthesis.

Even in the absence of good feedback I frequently see stuff go from "not even wrong" to "thats kinda messed up but it'll get the job done".

Other places, the "good (but not highly conscientious) dev -> slop cannon" effect might be dominating. I feel like AI is raising the floor and ceiling of what people can do (a strong senior / expert can whip the AI until the output is actually good) but having particularly weird effects in the middle. Its enabling people to attempt things outside their usual area (devs doing infra, sres doing more dev, backends & frontends doing each other's jobs) and IMHO that's where good feedback really helps.

Reply on news.ycombinator.com