The conversation

majormajorHNSource author
Lessons learnedExperience excerpt · English

I've worked with outsourced code, and I've worked with similarly-messy/not-forward-thinking …

… I've worked with outsourced code, and I've worked with similarly-messy/not-forward-thinking first-iteration startup-MVP code that found success and now needs to do more and be more reliable while being cheaper to operate. It ain't pretty. Once you start modifying working code that people rely on you quickly start to see that the code itself matters. There aren't enough tests in the world to get around this from a quality POV. And piles of copypasta turn into either inconsistent behaviors (bad from a user satisfaction POV) or a continual drag on velocity (bad from a product goals/competitivness POV). And I've run the tools on those sorts of "found MVP, now need to iterate fast" codebases, both on the messy parts and the better parts. Sure, Claude can chew through the pain points of "let me find the ten copypasta versions of this and try to update them all" and chase down all the weird stupid bugs/janky things that that requires because each of them evolved separately much faster than a human can. …

Original discussionWhy is the HN crowd so anti-AI?765 source comments · at import
2

What was this responding to?

Parent context · original excerpt

_0
_0ffhHN

Thoughtful comment, and I'd like to add another angle: However meaningful it is to say the community is divided, I also think that individuals are "divided" on the question as well. I can speak from myself as an example (although n=1): I am incredibly open to machine learning and the advances it brings. On the other hand I am extremely conscious of the fact that the current LLMs do often write bad code, which becomes especially obvious once projects go much beyond "private toy" size. For me personally the consequence is that I try to make my projects even more modular, and the modules even more clearly delineated. With proper guidance, current LLMs work mostly fine when working on isolated modules. That doesn't mean they don't sometimes fail even there, but they also on rare occasions come up with surprisingly clever solutions when you let them loose on a code base, as long as the proble…

Full original

Community replies 0

No community replies yet. Add your perspective.

Replies from the source 2

Direct replies available in this import. Original-language excerpts.

DA
daymanstepHN

> You hit the point where your agent is churning for hours and running more and more tests and inadvertently breaking more things trying to make the change in all those places I've had this experience with vibe-coded applications written by Claude itself. For some reason, Claude doesn't seem to use any good practices unless I tell it to, and seems to require me to walk it through a decent design up front.

Full original
MV
mvfcHN

The problem is that most people who vibe code or use these claims of “anyone can code now” ignore that software isn’t just a pile of code, but also documentation, tests, design documents, and several other artifacts that the “AI” (LLMs are not intelligent) needs to do anything remotely useful. And most of them will never reach the point where the use of LLMs becomes more problematic than helpful, because by then either they have a product and hired someone to deal with it or it’s abandoned and not used.

Full original
Continue on Hacker News

Respect different perspectives. Share concrete experiences.

Sign in to post, reply, repost, and quote.