←back to thread

Ask HN: Is anyone else sick of AI splattered code

75 points throwaway-ai-qs | 1 comments | 17 Sep 25 17:29 UTC | HN request time: 0s | source

Between code reviews, and AI generated rubbish, I've had it. Whether it's people relying on AI to write pull request descriptions (that are crap by the way), or using it to generate tests.. I'm sick of it.

Over the year, I've been doing a tonne of consulting. The last three months I've watched at least 8 companies embrace AI generated pip for coding, testing, and code reviews. Honestly, the best suggestions I've seen are found by linters in CI, and spell checkers. Is this what we've come to?

My question for my fellow HNers.. is this what the future holds? Is this everywhere? I think I'm finally ready to get off the ride.

Show context
barrell ◴[17 Sep 25 17:54 UTC] No.45279108[source]▶
I'm not convinced it's what the future holds for three main reasons:

1. I was a pretty early adopter of LLMs for coding. It got to the point where most of my code was written by an LLM. Eventually this tapered off week by week to the level it is now... which is literally 0. It's more effort to explain a problem to an LLM than it is to just think it through. I can't imagine I'm that special, just a year ahead of the curve.

2. The maintenance burden of code that has no real author is felt months/years after the code in written. Organizations then react a few months/years after that.

3. The quality is not getting better (see gpt 5) and the cost is not going down (see Claude Code, cursor, etc). Eventually the bills will come due and at the very least that will reduce the amount of code generated by an LLM.

I very easily could be wrong, but I think there is hope and if anyone tells me "it's the future" I just hear "it's the present". No one knows what the future holds.

I'm looking for another technical co-founder (in addition to me) to come work on fun hard problems in a hand written Elixir codebase (frontend is clojurescript because <3 functional programming), if anyone is looking for a non-LLM-coded product! https://phrasing.app

replies(3): >>45279156 #>>45279259 #>>45279390 #
koakuma-chan ◴[17 Sep 25 17:59 UTC] No.45279156[source]▶
I agree on all, but I also have a PTSD of the pre-LLM era where people kept telling me that my code is garbage, because it wasn't SOLID or whatever. I prefer the way it is now.
replies(2): >>45279345 #>>45279376 #
skydhash ◴[17 Sep 25 18:16 UTC] No.45279376[source]▶
SOLID is a nice sets of principles. And like principles, there are valid reasons to break them. To use or not to use is a decision best taken after you’ve become a master, when you know the tradeoffs and costs.

Learn the rules first, then learn when to break them.

replies(2): >>45279746 #>>45280100 #
koakuma-chan ◴[17 Sep 25 18:42 UTC] No.45279746[source]▶
This is idealistic. Do you actually sit down and evaluate whether the code is SOLID or maybe it's more like you're just vibe checking it, and it doesn't actually matter if you call that SOLID or DRY or whatever letters of the alphabet you prefer. Meanwhile your project is just a PostgreSQL proxy.
replies(1): >>45279871 #
1. skydhash ◴[17 Sep 25 18:53 UTC] No.45279871{3}[source]▶
These are principles, not mathematical equations. It’s like drawing an human face. The general rule is that the eyes are spaced by another eye length viewed from the front. Or the intervals between the chin, the base of the nose, the eyebrows and the hairline are equal. It does not fit every face, and artists do break these rules. But a beginner breaks them for the wrong reasons.

So there’s a lot of heuristics in code’s quality. But some time, it’s just plain bad.