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

The Vibe Tax

insufferable.dev

Post reply on HN
Print view View original

101–110 of 135 posts

Re: The Vibe Tax

#101

Post by treykeown »

raincole wrote: post #41
ad_fontes wrote: post #22

I feel like I'm living in a parallel universe when I read these types of posts. My agents have never created code that is straight-up garbage and I have never flushed a week's worth of tokens down the toilet. I just can't identify with all the constant complaints about AI-assisted coding. And my biggest project isn't some hello world app. It's a self-hosted, privacy-focused personal financial management application t…

> personal financial management application > 126k LOC against 240k LOC of regression tests and 30k LOC of CI/CD pipeline I mean... Yeah, that's pretty self-explanatory why you don't identify complains about AI-assisted coding.

Right? This has to be bait. I hope.

Re: The Vibe Tax

#102

Post by mrheosuper »

tptacek wrote: post #99
mrheosuper wrote: post #96

Earlier quoted context omitted.

>the "hello world" of the last 20 years of programming The "hello world" is mostly for making sure your toolchain is working correctly.

Yes, and the todo app is for making sure you have the most basic understanding required to hold it right.

i was reading your comment as "todo app" replaced the "hello world", which is now replaced by "finance tracker app", but in fact the todo app didn't replace hello_world.

Re: The Vibe Tax

#103

Post by tomasphan »

esafak wrote: post #18
tomasphan wrote: post #17

Earlier quoted context omitted.

Dumb models will make more mistakes even with good spec no? They lack capacity to verify (to be introspective) and will pattern match over reasoning.

No, it works great. Just make it smart enough to get the job done, and have the smart model review it at the end.

How do you know what’s smart enough to get the job done? Could actually be an interesting empirical question.

Re: The Vibe Tax

#104

Post by ad_fontes »

the__alchemist wrote: post #91
ad_fontes wrote: post #22

I feel like I'm living in a parallel universe when I read these types of posts. My agents have never created code that is straight-up garbage and I have never flushed a week's worth of tokens down the toilet. I just can't identify with all the constant complaints about AI-assisted coding. And my biggest project isn't some hello world app. It's a self-hosted, privacy-focused personal financial management application t…

> I feel like I'm living in a parallel universe when I read these types of posts. > And my biggest project isn't some hello world app. It's a self-hosted, privacy-focused personal financial management application that I intend to open source. It's about 126k LOC against 240k LOC of regression tests and 30k LOC of CI/CD pipeline. Indeed; non-overlapping Overton windows. edit: I'm going bluntly ask, after pondering thi…

Not satire. But I can understand why my comment seemed contradictory.

I've been designing software for a long time, but I'm nowhere near as good as most career SDEs I know (my career path has been SDE-adjacent). So it's not like I sat down and independently told various LLMs how to build out all these guardrails. I make high level architecture decisions and nudge them in the right direction ("use RabbitMQ", "trunk-based branching, not gitflow", etc).

A lot of this stuff evolved piecemeal and organically. But at no point was a churning out garbage and I never had a runaway agent completely derail the project (or my budget). But, thinking about it more, I guess there are some things I might have done differently than most people:

- I started with documentation: user interview --> user stories --> functional spec --> frozen design contract. These were all done before I wrote any code.

- I specified the tech stack and the architecture in broad strokes, rather than let the LLMs make that decision. I went with boring choices because that's what I know best: Flask/Jinja, Alpine.js, Postgres.

- I've constantly gone back and refactored accumulated tech debt and have added hard CI gates for things like cyclomatic complexity, ensuring that docs don't drift from the underlying code, and an "apparatus ledger" that keeps track of all the rules and constraints that keep getting added.

- I make sure that each session proves that it's tests can fail before shipping a PR, so it's not writing meaningless tests.

Maybe I'm underestimating how impactful all those things add up to shape the behavior of the LLM agents? Because individually, I wouldn't expect them to have saved my from nearly all the AI pitfalls I read about.

Re: The Vibe Tax

#105

Post by marcus_holmes »

ModernMech wrote: post #86
alehlopeh wrote: post #80

Earlier quoted context omitted.

Don’t get me wrong, I agree. I see Fable and Opus 5 write garbage code and useless tests all the time. And don’t get me started on comments. I’m just trying to understand how vibe coders are to blame for it.

Well because you can instruct it to not do these things if you take more care. The vibing lets it run amok.

This is the way, but it's not the viber's fault.

It's a tool. It does what you tell it to. If it's doing the wrong thing, tell it to do something different.

Re: The Vibe Tax

#106

Post by ad_fontes »

yladiz wrote: post #25
ad_fontes wrote: post #22

I feel like I'm living in a parallel universe when I read these types of posts. My agents have never created code that is straight-up garbage and I have never flushed a week's worth of tokens down the toilet. I just can't identify with all the constant complaints about AI-assisted coding. And my biggest project isn't some hello world app. It's a self-hosted, privacy-focused personal financial management application t…

How in the world do you need 30k LOC for your CI/CD??

Because it's complex and I'm stuffing 30-50 PRs a day through it. 7 GHA workflows across four self-hosted runners.

I'm on my third iteration, after constantly log jamming previous versions. Most steps aren't "run pytest", they're gates that guard against an LLM's bias to continuously add more and more complexity to a system.

I'm aware of the irony of having a complex system to mitigate complexity, but the key difference is these rules bound complexity growth. If you're legitimately interested in the details, let me know. I'm too tired to write up much more but would be willing to drop in a LLM-authored summary of the details.

Re: The Vibe Tax

#107

Post by keeda »

tptacek wrote: post #95
rayiner wrote: post #92

Earlier quoted context omitted.

I replaced my todo list tracker with a vibe coded one, while waiting for things to happen in the middle of a trial. We're living in the future.

It's fucking weird and I think we're not talking about it enough .

Here’s my theory for why this is happening, from the thread the other day on not being excited about technology anymore:

https://news.ycombinator.com/item?id=49350223

Re: The Vibe Tax

#108

Post by 8note »

WD-42 wrote: post #33
ad_fontes wrote: post #22

I feel like I'm living in a parallel universe when I read these types of posts. My agents have never created code that is straight-up garbage and I have never flushed a week's worth of tokens down the toilet. I just can't identify with all the constant complaints about AI-assisted coding. And my biggest project isn't some hello world app. It's a self-hosted, privacy-focused personal financial management application t…

Personal finance tracker - the TODO app of 2026.

its something people want but has been both too difficult to be worth building, and not something you want to use some SASS for where youre giving all your financial data over to a third party and the government

suddenly they're tractable without taking too much time investment

Re: The Vibe Tax

#109

Post by zzrrt »

ad_fontes wrote: post #69
zahlman wrote: post #44

Earlier quoted context omitted.

> Or their predisposition to add, add, and add more stuff when proper engineering practices are more often about subtraction (but I've built mitigation guardrails against a lot of that). > a… personal financial management application… about 126k LOC against 240k LOC of regression tests and 30k LOC of CI/CD pipeline Just how much functionality are you getting out of that? It's hard for me to imagine that people want t…

My wife was a diehard YNAB user before we met but it went by the wayside once we merged finances. She wanted to get back to better managing our money and started using Google Sheets and then got stuck. She asked me for help trying to create a pivot table and like any good engineer, I built her an entirely new application instead. In my defense though, it does way more than a spreadsheet. Stuff like OCRing screenshots…

> do you still owe a minimum payment based on that purchase?

I'm skeptical that the UX is improved much by having the app know the answer. The bank tells you what to pay, a month beforehand. The user has to get that number from the bank anyway, to be sure they don't incur fees. Your app should just pull it from the statements, not independently calculate it.

Re: The Vibe Tax

#110

Post by conartist6 »

ad_fontes wrote: post #22

I feel like I'm living in a parallel universe when I read these types of posts. My agents have never created code that is straight-up garbage and I have never flushed a week's worth of tokens down the toilet. I just can't identify with all the constant complaints about AI-assisted coding. And my biggest project isn't some hello world app. It's a self-hosted, privacy-focused personal financial management application t…

Are you surprised that when you look into the mirror and you see your own face not someone else's?

Remember, models have no identity. They just try to say what they think you want them to say.

Post reply on HN