Live data from Hacker News

Vibe coding kills open source

arxiv.org

191–200 of 304 posts

Re: Vibe coding kills open source

#191

Open source software, by the admission of this article, is a critical input to AI agents useful for code generation. So the way I see it is that there is now an entire industry that is incentivized to financially support open source software for entirely new reasons. To keep the models trained on new languages, libraries, and developments in computer science, they need to make sure that high quality modern code is st…

Seems you are arguing that The Tragedy Of The Commons could never happen because people benefit from the Commons

Re: Vibe coding kills open source

#192
post #177

Small bespoke personalized on the spot apps are the future with LLMs. The future will absolutely not be "How things are today + LLMs" The paradigm now for software is "build a tool shed/garage/barn/warehouse full of as much capability for as many uses possible" but when LLMs can build you a custom(!) hammer or saw in a few minutes, why go to the shed?

Why use a battle tested, secure, library that you know solves your problem when you can burden your project with custom code you need to maintain?

While quality libraries do exist, let's not pretend that most people are validating and testing the libraries they pull in, that abandoned / unmaintained libraries aren't widely used, and that managing the dependency hell caused by libraries is free.

Re: Vibe coding kills open source

#193

Small bespoke personalized on the spot apps are the future with LLMs. The future will absolutely not be "How things are today + LLMs" The paradigm now for software is "build a tool shed/garage/barn/warehouse full of as much capability for as many uses possible" but when LLMs can build you a custom(!) hammer or saw in a few minutes, why go to the shed?

> The paradigm now for software is "build a tool shed/garage/barn/warehouse full of as much capability for as many uses possible" but when LLMs can build you an custom(!) hammer or saw in a few minutes, why go to the shed? 1) Your specific analogy is kinda missing something important: I don't want my tools working differently every time I use them, also it's work to use LLMs. A hammer is kind of a too-simple example,…

I started picturing AI generating tools like it does images of people... I mean, of course every other hammer will have an extra head off to the side, or split into 3 handles.

Seriously though, you can tell AI what libraries and conventions you want to follow... that's been a lot of what I've done with it recently... I've been relatively pleased with the results.

I've said several times that it's not perfect, but it is an overall force multiplier. It's much like working disconnected with an overseas dev team, but you get turn around in minutes instead of the next morning in your email. The better instructions/specs you give, the better the results. On my best day, I got about 3 weeks of what would take me alone done, after about 3 hours of planning/designing and another 2-3 hours of iteration with Claude Code. On my worst day, it was frustrating and it would have been about the same amount of time doing it myself. On average, I'd say I get close to 5 days of work done in 5-6 hours of AI assisted coding. Purely anecdotally.

That said, I usually have a technical mind for how I want the solution structured as well as features and how those features work... often it clashes with the AI approach and sometimes it swims nicely. I'll also say that not all AI coding is the same or even close in terms of usefulness.

Re: Vibe coding kills open source

#194

Earlier quoted context omitted.

I think you're missing the enormous value in apps being standardized and opinionated. Standardized means that in addition to documentation, the whole internet is available to help you. Opinionated means as a user of an app in a new domain, you don't have to make a million decisions about how something should work to just get started. Sure, there will be more personalized apps for those who have a lot of expertise in…

AI's / LLM's have already been trained on best practices for most domains. I've recently faced this decision and I went the LLM custom app path, because the software I needed was a simple internal business type app. There is open source and COTS software packages available for this kind of thing, but they tend to be massive suites trying to solve a bunch of things I don't need and also a minefield of licensing, freem…

What if there is a new domain.

Re: Vibe coding kills open source

#195
Sustaining OSS at its current scale under widespread vibe coding requires major changes in how maintainers are paid

A recent discussion on a related topic, apparently following the same misguided idea of how OSS is motivated:

https://news.ycombinator.com/item?id=46565281

(All my new code will be closed-source from now on: 93 points, 112 comments)

Re: Vibe coding kills open source

#196

Small bespoke personalized on the spot apps are the future with LLMs. The future will absolutely not be "How things are today + LLMs" The paradigm now for software is "build a tool shed/garage/barn/warehouse full of as much capability for as many uses possible" but when LLMs can build you a custom(!) hammer or saw in a few minutes, why go to the shed?

Would you trust your hand next to a saw made by an LLM?

Maybe. Were the designs reviewed by qualified engineers and gone trough rigorous QA cycles before getting placed in front of me?

Re: Vibe coding kills open source

#197

Earlier quoted context omitted.

AI's / LLM's have already been trained on best practices for most domains. I've recently faced this decision and I went the LLM custom app path, because the software I needed was a simple internal business type app. There is open source and COTS software packages available for this kind of thing, but they tend to be massive suites trying to solve a bunch of things I don't need and also a minefield of licensing, freem…

What if there is a new domain.

Then it is new for everyone, no?

Re: Vibe coding kills open source

#198

Related but not sure how much attention it's getting: GPL is a dead man walking since you can have any LLM cleanroom a new implementation in a new language from a public spec with verifiable "never looked at the original source" and it can be more permissively-licensed however you wish (MIT, BSD etc). case in point, check out my current deps on the project I'm currently working on with LLM assist: https://github.com/…

>verifiable "never looked at the original source"

...erm.

To adress the elephant in the room: Who exactly is supposed to be verifiable to never have looked at the original source? You or the LLM?

Re: Vibe coding kills open source

#199
post #170

Earlier quoted context omitted.

I've done a bit of experimentation with that. And the irony is Rust seems to fare best because of the error messages of the compiler. I have had a lot of conversations with Claude about it and it supports that theory.

Warning: Claude may support the theory, because Claude is a sycophant.

I have a well-calibrated ego.

Re: Vibe coding kills open source

#200
post #158

Earlier quoted context omitted.

> Holy hell HN, downvoted to -4 in record time. Y'all don't like what's happening, but it's really happening. > > I'm not lying about this. > > I provided my background so you'd understand the context of my claims. I have a solid background in tech. There are lots of people claiming this. Many of whom have a solid background. Every now and then I check out someone's claim (checking the code they've generated). I've y…

Have you looked at antirez's code? https://github.com/antirez/flux2.c

Generating code from scratch and modifying existing code are two different things, obviously the latter being where AI doesn't do great. Carefully managing and compressing context can somewhat help, but that is far from being a perfect solution.
Post reply on HN