Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AI changes the economics of software rewrites

thetruthasiseeitnow.com

Post reply on HN
Print view View original

31–40 of 113 posts

Re: AI changes the economics of software rewrites

#31

Post by TheOtherHobbes »

jillesvangurp wrote: post #22
bad_username wrote: post #4

It also changes the economics of buy vs build.

That's very true. People put up with the many limitations of off the shelf software because it's cheaper, not because it's better. Developing bespoke software solutions is now a lot cheaper than it used to be. So, there are a lot of cases where that now becomes the better option. Doing in days what used to take months, is a bit of a game changer. Like with past cost reductions, people will underestimate the work and…

They also do it because there's someone to blame, and - more importantly - because they know the people who are selling it from their golf dates.

Re: AI changes the economics of software rewrites

#32

Post by AndrewThrowaway »

fxtentacle wrote: post #27
karlkloss wrote: post #24

Earlier quoted context omitted.

That's also true for humans.

Humans will typically learn after you have forced them to apologise for the same mistake for 20 times in a row. AI won’t.

If you gave some junior dev a large codebase and just told to "refactor it" you would get a terrible result.

If you gave junior dev exact tasks what to do where you will get better results.

Just like with LLM.

Re: AI changes the economics of software rewrites

#35

Post by ed_elliott_asc »

akssri wrote: post #21

Au contraire - LLMs are quite bad at large scale pattern fidelity. They'll even forget key details and constraints unless told over and over again. That's why AI-written code has the quality of a patch-on-patch-on-patch.

The patch-on-patch-on-patch is exactly right, nice way to describe it. It feels like, and I think is, optimized to find the quickest answer not necessarily the right answer.

Re: AI changes the economics of software rewrites

#36

Post by rodrodrod »

apsurd wrote: post #10

again with these linkedin "articles". · every sentence stands on its own because it's the most insightful soundbite of wisdom every constructed. · Aphorisms for the collective upgrade of consciousness. · delivered one tweet at a time. · (this comment adds to the discussion ironically by demonstrating how ridiculous it is to have to derive signal from this format. Please do what you need on Linkedin but take some semb…

I once saw this style be called "broetry"[1], and it's unmistakably LinkedIn-voice. I get that it works because feed algorithms/engagement, but never understood why it seems largely confined to LinkedIn and not other social media sites.

[1] https://fenwick.media/rewild/magazine/dead-broets-society-be...

Re: AI changes the economics of software rewrites

#37

Post by nomel »

matsemann wrote: post #20

What's the point of the rewrite if it doesn't fix the underlying issues, though? A rewrite being a good idea often hinges on the ability to simplify. After a decade or more, it's now apparent what the application should and shouldn't do, so one can build it with those learnings and shed all tech debt from how it grew organically. Aka preserving all behavior is not what I would want from a rewrite. The point would be…

Say I rewrite a large codebase from python to C++, preserving all behavior. That's up to a 50x speed up.

Re: AI changes the economics of software rewrites

#38

Post by al_borland »

AndrewThrowaway wrote: post #32
fxtentacle wrote: post #27

Earlier quoted context omitted.

Humans will typically learn after you have forced them to apologise for the same mistake for 20 times in a row. AI won’t.

If you gave some junior dev a large codebase and just told to "refactor it" you would get a terrible result. If you gave junior dev exact tasks what to do where you will get better results. Just like with LLM.

That’s why junior devs generally aren’t give the responsibility of architecting a large scale refactor. Yet people seem to be trying to had these types of tasks over to LLMs.

Re: AI changes the economics of software rewrites

#39

Post by a96 »

matsemann wrote: post #20

What's the point of the rewrite if it doesn't fix the underlying issues, though? A rewrite being a good idea often hinges on the ability to simplify. After a decade or more, it's now apparent what the application should and shouldn't do, so one can build it with those learnings and shed all tech debt from how it grew organically. Aka preserving all behavior is not what I would want from a rewrite. The point would be…

One obvious target might be rewriting from an unsupported, broken, and/or obsolete target to something that still works. Or moving a project from a platform that no other system in the company uses to the same setup that all the others use.

Of course it won't quite work, but I can definitely see why some people would want that.

Re: AI changes the economics of software rewrites

#40

Post by fhd2 »

Semaphor wrote: post #29
matsemann wrote: post #20

What's the point of the rewrite if it doesn't fix the underlying issues, though? A rewrite being a good idea often hinges on the ability to simplify. After a decade or more, it's now apparent what the application should and shouldn't do, so one can build it with those learnings and shed all tech debt from how it grew organically. Aka preserving all behavior is not what I would want from a rewrite. The point would be…

I work on a codebase from the early 2000s, a lot of it using webforms, a long abandoned .NET technology. A rewrite preserving all behavior and making no observable changes whatsoever would be amazing. But it’s also tested exactly as well as you’d expect from something like that so I’d rather not let AI go wild.

Good example. Transitioning from an outdated framework to a modern (or sometimes "slightly less outdated") one is probably one of the few situations where you do not want to change semantics at all.

And in my experience, these are _dangerous_. People go into "while we're at it..." mode, and it quickly turns into a big 2.0 kind of thing that takes forever.

I would argue that LLMs can speed this kind of thing up, but not by an order of magnitude or anything, just a bit. Unless there's high risk appetite.

Post reply on HN