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

111–120 of 401 posts

Re: Cleaning up after AI rockstar developers

#111

Post by james_marks »

SlinkyOnStairs wrote: post #50
pu_pe wrote: post #38

Earlier quoted context omitted.

Absolutely. I really don't think the future will be humans reading and picking apart an AI-generated codebase, there will be tech debt agents or whatever running overnight.

I think you misunderstand why tech debt lingers around. It's not a capacity or capability problem. Organisations just don't want to deal with the accountability involved with "touching cold code". Whether it's a human or "AI agent" doesn't change the "It worked in prod, you touched it, you broke it, never touch anything again" dynamic.

Exactly this. When I reject a refactor PR (or ideally, _before_ there's a PR), it's not because it's a bad idea, per se.

But there's risk associated with every change, and it takes time to review, QA, monitor the rollout, communicate to stake holders, etc.

The refactor itself may be the smallest part of it.

Re: Cleaning up after AI rockstar developers

#112

Post by karmakurtisaani »

bluGill wrote: post #98
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

The problem is those shoddy foundations can support a lot of weight before they finally fail. A prototype you write in a day - not a big deal to throw away. However if you have been working for a while that is a lot of effort/money. Worse, often you need to spend years before you realize how an initial design decision was a mistake - not only are you proposing to throw away millions of dollars worth of work - you als…

The day you implement the first edge case to your prototype you basically commit to using it forever or spending a lot of money to replace it.

Re: Cleaning up after AI rockstar developers

#113

Post by surfmike »

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…

Did you use AI to rewrite it?

Re: Cleaning up after AI rockstar developers

#114

Post by shrikant »

karmakurtisaani wrote: post #112
bluGill wrote: post #98

Earlier quoted context omitted.

The problem is those shoddy foundations can support a lot of weight before they finally fail. A prototype you write in a day - not a big deal to throw away. However if you have been working for a while that is a lot of effort/money. Worse, often you need to spend years before you realize how an initial design decision was a mistake - not only are you proposing to throw away millions of dollars worth of work - you als…

The day you implement the first edge case to your prototype you basically commit to using it forever or spending a lot of money to replace it.

Well, there's nothing as permanent as a temporary solution...

Re: Cleaning up after AI rockstar developers

#115

Post by roboror »

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…

How much would it have cost to start from scratch?

Re: Cleaning up after AI rockstar developers

#116

Post by Lord_Zero »

eqmvii wrote: post #86
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

And in the before times, you learned a lot and walked away with knowledge on the deps needed, connections, .env secrets, and cleaned it all up and documented it so the next dev would have an easier time doing it.

Re: Cleaning up after AI rockstar developers

#118

Post by mrweasel »

peter_d_sherman wrote: post #75
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…

Interesting! Yes, there's probably a market for vibe-coded software, but if there is, then there's also a market for fixing other companies' vibe-coded mistakes ... Phrased another way, you pay company A to vibe-code some software or extra software features for you, then you subsequently pay company B -- to fix company A's vibe-coded mistakes! (Hey, look on the bright side! It's more money for taxes, GDP, employment…

Some of this is also going to die out, if the prediction of price increases for LLM tools and tokens holds true. In that case a lot of this software essentially becomes abandonware overnight because the actual maintainer was Claude or Codex.

If you're a reasonably talented developers, I think there will be money to be made picking up projects left behind by coding agents. Maybe you'll use AI tools to do this, maybe you charge to migrate to other platforms and maybe you are paid to simply do bugfixes.

Re: Cleaning up after AI rockstar developers

#119

Post by bogwog »

I realized recently that this all has an unsavory element of ego to it. It doesn't help that LLMs have basically been trained to talk like they're performing in a movie, getting creative with techno-babble that sounds both plausible and exciting. I recently had to review some slop where the LLM was using terms like "event storm" to describe how some callbacks work, or "gating-solve" to describe a simple change to an if statement. Combine that with their sycophantic tendencies, and it really can make you feel like you're a star hacker in a Hollywood movie.

It reminds me a little of when Hegseth wrote "we're clean on opsec" in a message thread with confidential military information that he accidentally sent to a journalist. It seems like role playing/fantasy fulfilment for certain personalities. I struggle not to hold some contempt for people like this, who are making life difficult for everyone for their own petty reasons. I can sympathize when it's simple ignorance, but the ego chasing really is inexcusable and needs to be called out more.

Post reply on HN