Hacker News Reader

I like to say "my code is 200% vibe-coded; the tricky bit is figuring out which 100% to keep".

Decisions matter, both technical and product ones. LLMs don't make as good technical or product decisions as I would, and the way I work with them tries to maximize my strengths and the LLM's strengths. I don't know if I succeed, but it's better than "make me an app like X" as a prompt.

Your quote caused me to consider vibecoding through the analogy of an LLM-human system as a subtractive synthesizer: the LLM is the oscillator, and the human is the filter.

> I think people will start valuing good software a lot more.

How will people determine what is good software and what is not? Even experienced engineers can't tell just by looking at the final product.

Some of the most solid rock-solid applications I see were built years ago and still look primitive (native Windows 7 controls, etc). Many of the worst, bug-infested anti-user software looks slick and modern.

> Claude code can deliver the first 90%, but we all know it is the last 90% that differentiates.

My experience with trying to complete that last 10% of a CC generated project is that it's all very alien looking; very uncanny-valley vibes, and I have serious velocity issues because of the lack of coherence.

> Building all the software you use yourself, whether by hand or by vibe coding, cuts you off from the world.

No one is doing that. In foreseeable future I don't see people making their own OSs, browsers and drivers. Workplaces never ditched Offices and Windows for the open source counterparts and they are certainly not going to do that for vibe coded solutions.

You can rest assured.

Making your own software is a good way to escape enshittification and influence.

I switched from Spotify to buying MP3s and using my own audio client, because I'm fed up of a company telling me which music I should listen to every single time I open the app. It costs more, but I own the music and I escape the constant redesigns, price increases and influential behaviour.

Most apps are very simple and there isn't too much to learn, especially if you're building it to scale to a userbase of yourself. I can't see the need for a ton of CRUD apps which demand subscription fees personally. If you build them yourself, you get to keep your own data, build it out the way you want it, keep it that way, and use computers as a person using a tool as opposed to a customer buying a product.

I did MP3s on my plex server for a while but with endless new music added to my playlists it became a hassle and Apple Music was just convenient and Shazam adding any song I hear and like is just too easy...it also plays perfectly on my Apple Watch over cellular when I go for a run, but everyone has their own use case and where they want to spend their time...

That's understandable. I have quite minimal music taste so my setup worked for me. I only listen to music at home when I'm not doing anything else and it's mostly classical so there doesn't tend to be too much to add at any given time.

A minimal web client audio player with some basic database tables in the back for organising and searching does me fine.

>Claude code can deliver the first 90%, but we all know it is the last 90% that differentiates.

So most software is 180% of 100%? :p

Opensource has been available since before the internet. What is `git clone ... make install` if not "vibe coding"

They're both trust, but one is trusting a person or group of people with some intentionality.

Your entire post is self selection bias and survivorship bias.

SWE field is one of the most cognitive dissonant social groups; cries foul at the slightest whiff their free speech and agency is being put upon; seeks to reduce blockers to their productivity, fewer PMs! Less management!

Now complains about users using their machines without having to block on an SWE.

Insert that quote about how someone will not see the obvious if their paycheck relies on them ignoring the obvious.

Here come LLMs and all they can accomplish with a few arithmetical rules instead of the arbitrary semantics of an SWE; watch as SWEs block social evolution away from disrupting software engineers.

As an example; "protected memory", among many other individual software problems, is an access control problem mired in old semantics relative to OS monoliths.

Didn’t see you all halting as you decimated travel agent jobs, retail jobs, etc etc. Technology advancement must now stand still after centuries of evolution? The self selection bias is as obvious as Trump's.

>Didn’t see you all halting as you decimated travel agent jobs, retail jobs, etc etc.

You have to remember that SWE's are the same group that screams "communism" the first moment you mention the word union and they should have the right to make as much money as possible with no restrictions.

This of course leads to the obvious lack of self reflection in their responses when something threatens their future income.

Labor unions align themselves well with Marxist thought and both are pretty based.

I'm not a SWE because I like money. I'm an SWE because I love programming.

you couldn't have missed GP's point any more if you tried. ignoring the ad-hominems about SWE greed:

these tools have been trained on decades of people "obsessing over every last detail". what GP is arguing is that we're detaching from that: you prompt, you get something that works, it doesn't matter how it got there. we're now entering the world where the majority of code will be vibed. So whatever our foredevelopers came up with, that will be the the final chapter of craftsman-produced, understood, code. whatever the previous generation actually learned about software engineering, that's at an end too, because why bother learning when i can prompt.

there's no stopping this transition, obviously. the next generation of tools will be trained on the current generation of tools' generated code. we're passed the "termination shock" of sofwtare understanding.

Oh I got it just fine. I was knocking their point artisanal software will make a comeback.

Am an EE and have argued against all the developer gibberish and self aggrandizement for years. It's just electromagnetic geometry of the machine to me.

Most software out there is all the gibberish devs need to do their job. Burns a lot of resources clinging to it. Completely useless to using a computer how most users will.

Vectors as a uniform layer of abstraction, rather than arbitrary namespaces a programmer finds cheeky, will obsolete a bunch of gibberish.

It’s all fun and games until it happens to you…

dimator captured the point I was hoping to make, more eloquently than I could hope to. I defer to their comment: https://news.ycombinator.com/item?id=46725512

That said, to address your broader point: me, personally, I am thrilled that the barrier to entry for building software has been all but eliminated. The joy of creation belongs to us all.

"Transportation, like software, is accumulated knowledge. The horse embodied centuries of breeding, training, and hard-won understanding about terrain, endurance, and failure. People learned from the horses they rode. Travel improved through incremental refinement, generation after generation. The automobile didn’t appear in a vacuum.

Building all your transportation yourself—whether by breeding horses or assembling a Model T—cuts you off from that accumulated experience. You lose the benefits of thousands of hours spent by others thinking carefully about the same problems.

I have no objection to Model Ts for personal use, but I wouldn’t be one-tenth the traveler I am without constant exposure to well-bred horses.

Some worry cars make horses obsolete—who needs breeders if anyone can buy an engine? I’m more optimistic. As cars proliferate, people will value good horses more. A Model T gets you the first 90%; it’s the last 90%—judgment, robustness, and adaptability—that differentiates."