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

Cleaning up after AI rockstar developers

codingwithjesse.com

Post reply on HN
Print view View original

81–90 of 401 posts

Re: Cleaning up after AI rockstar developers

#81

Post by penultimatename »

AndrewKemendo wrote: post #22

It’s literally no different than how to clean up old projects over the last 30 years of software engineering I don’t understand why all this stuff is all of a sudden “new.” It feels like we’ve got an entire generation of people who never had to spend their time factoring or doing hard infrastructure work It’s actually pretty baffling how rare it is to find somebody who has consistent experience in refactoring that is…

In my experience, this is because a modern engineering organization is laser focused on delivering value. Value rarely aligns with refactoring an existing, working implementation. If need the data, you build an integration on the output data. If something isn’t working well enough, you fix that one thing, you don’t refactor half the application.

Getting product to prioritize refactoring a working product is like pulling teeth. Even if maintenance is a moderate drain on resources, work beyond maintenance on working solutions isn’t seen as a net win.

Re: Cleaning up after AI rockstar developers

#82

Post by mannanj »

rfgplk wrote: post #73
anonzzzies wrote: post #19

I like fixing code made by AIs and others (outsourcing code is similar as someone else said already). Last week we found out some client tried to vibe some departmental tool; the result is some massive crap in nextjs that needs 10GB mem to compile, has 1000s of lint errors, dev logs in git (very noisy ones) and so on. Now we have to fix it: its basically free 10k-50k euros over and over again for this type of work. V…

> the result is some massive crap in nextjs that needs 10GB mem to compile, has 1000s of lint errors, dev logs in git (very noisy ones) and so on. The anti-LLM propaganda is getting ridiculous at this point. No project "needs 10GB" to compile, unless you're working with astronomically massive repos, and _no_ LLM will _ever_ generate that. Lint errors (depending on cause) are either meaningless or a result of poor pro…

The OP said that this was coded by a product person though. The product people coding and using these tools, who are spreading the pro-LLM propaganda, are not doing proper prompt engineering nor lint fixing.

> _no_ LLM will _ever_ generate that

Did you even read the post? Seems you are being overly hostile, defensive and dismissive. Honestly, you sound like an astroturfer to me. I'm curious to check your history to see if you match the vibe.

Re: Cleaning up after AI rockstar developers

#83

Post by skydhash »

rzmmm wrote: post #48
JoelMcCracken wrote: post #41

Earlier quoted context omitted.

This is one of the things I keep thinking about. At the very least, these tools make prototyping and idea vetting remarkably cheaper. Then we go back to the old “the prototype works; I’m the boss and I’m telling you to deploy it to production”

Prototyping is widely underappreciated. People think it's waste to throw away stuff but it's more costly to build upon shoddy foundations

You can prototype UX with a tools like balsamiq or taking photos of paper sketches with paper-to-app application. No need for code to share an idea. Especially from business to engineering or vice-versa.

Product Managers coding is like Developers writing marketing pitches.

Re: Cleaning up after AI rockstar developers

#84

Post by gyanchawdhary »

this_user wrote: post #71
gyanchawdhary wrote: post #10

[flagged]

Compilers are deterministic and they actually possess domain knowledge of what they are trying to do. AI models are non-deterministic, have no real domain knowledge due to lack of an underlying world model, and their way of "writing" software is to spew out something that looks like something that they have been trained on, then iterate on it long enough until it has reached the level of being barely runnable.

[flagged]

Re: Cleaning up after AI rockstar developers

#85

Post by hylaride »

rfgplk wrote: post #73
anonzzzies wrote: post #19

I like fixing code made by AIs and others (outsourcing code is similar as someone else said already). Last week we found out some client tried to vibe some departmental tool; the result is some massive crap in nextjs that needs 10GB mem to compile, has 1000s of lint errors, dev logs in git (very noisy ones) and so on. Now we have to fix it: its basically free 10k-50k euros over and over again for this type of work. V…

> the result is some massive crap in nextjs that needs 10GB mem to compile, has 1000s of lint errors, dev logs in git (very noisy ones) and so on. The anti-LLM propaganda is getting ridiculous at this point. No project "needs 10GB" to compile, unless you're working with astronomically massive repos, and _no_ LLM will _ever_ generate that. Lint errors (depending on cause) are either meaningless or a result of poor pro…

Oh sweet summer child...

Do you have any idea, even before modern LLMs, how much code out there was just given more memory instead of optimized? There are even good reasons for it (it can be cheaper than having devs spend time if there's more productive work to be had).

It can be very easy if said code needs to parse through gobs of data.

Re: Cleaning up after AI rockstar developers

#86

Post by eqmvii »

Goofy_Coyote wrote: post #44

These two sentences hit home: > The flow of data was so hard to follow, it seemed like someone was trying to cover up a murder. > Just getting the code to run on your laptop took a week. I always thought I’m the only one having problem understanding the data flow, or setting up a proper dev environment. Impostor syndrome (and sometimes toxic environments that pushed for “velocity”) didn’t help either. Felt good to kn…

> Just getting the code to run on your laptop took a week.

This one surprised me. Claude Code in the CLI has made standing up an app and debugging whatever random dependencies or docker BS a dream compared to the before times, when you'd have to learn the architecture while simultaneously troubleshooting whatever isn't working on your machine

Re: Cleaning up after AI rockstar developers

#87

Post by gyanchawdhary »

DamonHD wrote: post #30
gyanchawdhary wrote: post #10

[flagged]

Hmm, ~30 years ago the compilers that I was using were generating generally fine assembly/machine code. Some of the other tooling was more troublesome: cross platform high performance numerically stable code and C++ static template deduplication paid for a lot of beers around then, and I needed them.

[dead]

Re: Cleaning up after AI rockstar developers

#88

Post by blanched »

thegrimmest wrote: post #69
maerF0x0 wrote: post #35

I've met a handful of people across my life that i'd call truly brilliant. Like, holy heck how in the world is this person this smart? Two things I've noted about really smart people are (usually mutually exclusively) 1) Sometimes they do not realize how smart they are, because it's simple to them, or because they know the subject they assume everyone else, say with a computer science degree, knows and recalls and un…

It's lonely being an outlier, especially in a trait that's so fundamental to how you see the world. Despite best effort, it's hard to relate to most people, and they especially find it hard to relate to you. The delta of lived experience is quite wide, often insurmountable.

I feel like this could be said about most human traits, on both ends of those traits’ axis. I’m not sure if that makes it insightful or obvious :).

Re: Cleaning up after AI rockstar developers

#90

Post by conductr »

darkwater wrote: post #64
rzmmm wrote: post #48

Earlier quoted context omitted.

Prototyping is widely underappreciated. People think it's waste to throw away stuff but it's more costly to build upon shoddy foundations

But... "time to market!", "we won't have cash by the time this gets implemented properly" etc etc are the usual suspects here.

Sounds like valid issues to me. Pristine software isn’t the objective of most businesses. Leaving as a problem for another day, if we’re lucky that day will come, for many businesses, products, and startups it doesn’t and the shoddy prototype usually isn’t to blame.

I feel like SWE’s that make this gripe really need to step back and understand their role and the process for value creation. Because it’s certainly a process, the quality of code/architecture matters little if the low bar of functionality is met. Functionality can be sold to customers or used to test the market. It’s basically the whole MVP thing and the MVP should be a bit jank. If it wasn’t, you spent too much time/effort on it.

All said, there’s definitely some approaches to make it less jank from day one. Unfortunately, jankiness is a subjective metric.

Post reply on HN