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

111–120 of 138 posts

Re: The Vibe Tax

#111

Post by altmanaltman »

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 even have specialized agents doing audits against Regulation Z (US banking law) criteria so the app models the required behavior of banks.

Can you elaborate on this? Clearly you cannot imply this means those audits have any real value since its just roleplay in this context right? Because your app in the current form will not be affected by Regulation Z in any way.

Re: The Vibe Tax

#112

Post by prmoustache »

ad_fontes wrote: post #106
yladiz wrote: post #25

Earlier quoted context omitted.

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 differe…

The complexity of a ci/cd workflow is independent of the number of PR a day.

Re: The Vibe Tax

#113

Post by rayiner »

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 .

I got through a trial using a document manager I vibe coded in two days. No crashes, no runaway memory usage with several gigs of PDFs. All my depo transcripts, expert reports, etc, indexed, with a terminal window integrated so i can ask Grok to “pull up the testimony on the first day when that guy said that thing.” The app has an API so the AI can directly control what documents i’m looking at and jump me to the right places. All I had to do was tell Claude to “expose all the document viewing functionality through applescript,” then tell Grok to “read the applescript dictionary and write yourself a skill.”

It’s like ye olde times when we had overqualified efficient paralegals who could do stuff like that.

Re: The Vibe Tax

#114

Post by onion2k »

uproarchat wrote: post #38
0x457 wrote: post #32

Earlier quoted context omitted.

> i'm not sure why people expect agents to one shot everything to perfection with just a prompt. because that's how agents are marketed.

I've never seen model providers marketing like that. What examples have you seen?

Claude has a /goal function that explicitly says it'll carry on working until it's done what you prompted it to do. That's exactly what a 'AI will zero-shot anything' believer is looking for. Behind the scenes it's really multi-shotting with generated prompts, but the user won't care.

Re: The Vibe Tax

#115

Post by eru »

zahlman wrote: post #44
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…

> 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…

> Just how much functionality are you getting out of that? It's hard for me to imagine that people want that much out of such a program. I just keep a spreadsheet. (Yes, LibreOffice is also very bloated.)

I suspect it depends a lot on which jurisdiction you live under.

My investment portfolio and its management are so trivial, I don't even use a spreadsheet. It's literally just two items: a global index fund and a margin loan. I don't even keep a cash cushion: I use the margin loan or just sell stock, when I need cash.

I can get away with this, partially because we pay no capital gains tax where I live, and there's no capital controls either.

If I had to work around all these tax complications that I read about, like determining which tax lot you should sell or whatever, I would probably appreciate a comprehensive personal financial management application.

Re: The Vibe Tax

#116

Post by localhoster »

Most, if not all, of the code in the company I work in is written by AI. Our tests are useless. We have tests that make sure that mongoose schemas are creating the collections defined in them. We have tests that check that zod shcemas parse objects currently. Every PR, even if 1 line change, will drag 25 file changes because our tests are so ad-hoc, so verbose, and so incompatible with each other. Imagine how the codebase is looking... This is a badge of incompetence for the company I work with, and prob to the entire tech world.

The funny part is? This makes our managers and investors proud, every PR is bigger, we make x3 more PRs (wheres the promised x10).

When they say this is the death of software engineering, this is what they mean.

Re: The Vibe Tax

#117

Post by eru »

ad_fontes wrote: post #106
yladiz wrote: post #25

Earlier quoted context omitted.

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 differe…

Could you drop the LLM-authored summary in a GitHub gist (or so) and link here?

(Suggesting this route, so that we don't spam HN too much.)

Re: The Vibe Tax

#119

Post by larodi »

> ‘A tax on other devs’

Which other devs bro? Those in India which get paid 1/10 your wage or those who get paid corpo salaries to move three lines of code per week…?

And how exactly does your prompted code tax mine? This is incredible nonsense.

If you want to say - generated code killed a lot of handmade one - fine, I get it.

But the fact you struggle to run this new dev process properly does not mean somebody is incurring costs to you on purpose neither that you’re a victim. It is a position you choose to be into.

Re: The Vibe Tax

#120

Post by eloisius »

localhoster wrote: post #116

Most, if not all, of the code in the company I work in is written by AI. Our tests are useless. We have tests that make sure that mongoose schemas are creating the collections defined in them. We have tests that check that zod shcemas parse objects currently. Every PR, even if 1 line change, will drag 25 file changes because our tests are so ad-hoc, so verbose, and so incompatible with each other. Imagine how the cod…

A project I was working on for a couple years until this spring started to turn like this when another contractor started committing AI work. There was a test literally called “test_imports.py” that, you know, tested that you could import every module of the project. I asked if we could just run `python __main__.py` to test that the imports worked, but he said no, we need this for big Claude-powered refactors to make sure nothing breaks.
Post reply on HN