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

41–50 of 135 posts

Re: The Vibe Tax

#41

Post by raincole »

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.

Re: The Vibe Tax

#42

Post by Lalabadie »

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?

I don't really think they advertise "Create your app idea in one weekend night" and assume the general public will mentally add "... but hire an experienced developer to supervise the process".

Re: The Vibe Tax

#43

Post by 0x457 »

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?

Literally any coding agent marking material:

- https://cognition.com/

- https://openai.com/index/introducing-the-codex-app/

- https://www.anthropic.com/news/claude-3-7-sonnet

anthropic specifically brags about how good claude code is every annoucement of a new model. I will surrender that none of them claim its "to perfection", but IMO its implied because no one would claim that their model one-shots any issue to dog shit quality.

Re: The Vibe Tax

#44

Post by zahlman »

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 that much out of such a program. I just keep a spreadsheet. (Yes, LibreOffice is also very bloated.)

Re: The Vibe Tax

#46

Post by zahlman »

pgt wrote: post #5

Pre-October 2025, maybe yes. But now? Couldn't disagree more. There is no insight in this post.

The post was published today by someone who is clearly making satirical reference to frontier models ("Pol" alludes to GPT-5.6 Sol).

Re: The Vibe Tax

#47

Post by Lalabadie »

supriyo-biswas wrote: post #2

I feel this, yes. In effect, I’ve always wanted a pair programmer agent, not a zero to one programming agent. Unfortunately models these days are mostly of the latter kind and it has caused a major disruption in the way I work. I’d much rather appreciate a small model making fast and specific edits that I ask if it, rather than ingesting 20 files to make changes, and then starting to write tests, etc.

I would love, love an even better Zeta model for that reason.

Re: The Vibe Tax

#48

Post by blackqueeriroh »

add-sub-mul-div wrote: post #11
hleszek wrote: post #4

Earlier quoted context omitted.

Ask the AI to create a detailed spec according to a few simple requirements. Review the spec yourself and correct what you want changed. Then ask the AI to implement the spec. Each time you request something new, ask the AI to update the spec as well.

This so much more annoying and circuitous than writing code.

Then just write the code, my man! This guy in this post is CHOOSING to use the LLM.

Choose what makes you happy!

Re: The Vibe Tax

#49

Post by hombre_fatal »

0x457 wrote: post #43
uproarchat wrote: post #38

Earlier quoted context omitted.

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

Literally any coding agent marking material: - https://cognition.com/ - https://openai.com/index/introducing-the-codex-app/ - https://www.anthropic.com/news/claude-3-7-sonnet anthropic specifically brags about how good claude code is every annoucement of a new model. I will surrender that none of them claim its "to perfection", but IMO its implied because no one would claim that their model one-shots any issue to dog…

Seems like motte and bailey fallacy. They say their models are good (the motte), therefore their models must one-shot everything to perfection (the bailey).

Besides, other people's claims about something doesn't give you license to abandon all critical thinking. Though it's evident they don't claim what you say they are.

Re: The Vibe Tax

#50

Post by dzhar11 »

This article somewhat reflects my experience with autonomous agentic coding. I've run several experiments with similar results: the agent burns through all my tokens while making very little progress, or produces something unacceptable.

So I'd rather micromanage the process step by step. It takes more of my time, but the result is much, much closer to what I actually wanted.

Post reply on HN