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

Vibe coding kills open source

arxiv.org

Post reply on HN
Print view View original

271–280 of 304 posts

Re: Vibe coding kills open source

#271

Post by thfuran »

spamizbad wrote: post #240
seniorThrowaway wrote: post #188

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…

> AI's / LLM's have already been trained on best practices for most domains. I've been at this long enough to see that today's best practices are tomorrow's anti-patterns. We have not, in fact, perfected the creation of software. And the your practices will evolve not just with the technology you use but the problem domains you're in. I don't mean this as an argument against LLMs or vibe coding. Just that you're alwa…

Also, they've been trained on common practices more than they've been trained on best practices. And best practice is heavily context dependent anyways.

Re: Vibe coding kills open source

#272

Post by aspenmartin »

dimitri-vs wrote: post #241
aspenmartin wrote: post #230

Earlier quoted context omitted.

> Because software developers typically understand how to implement a solution to problem better than the client. If they don't have enough details to implement a solution, they will ask the client for details. If the developer decides to use an LLM to implement a solution, they have the ability to assess the end product. Why do you think agents can’t do that? They can’t do this really well today but if the distance…

Hallucinations are not solved, memory is not solved, prompt injection is not solved, context limits are waaay too low at the same time tokens way too expensive to take advantage of context limits, etc. These problems have existed since the very early days of GPT-4 and there is no clear path to them being solved any time soon. You basically need AGI and we are nowhere close to AGI.

All of the issue you talk about are true, and I don’t personally care about AGI it’s kind of a mishmash of a real thing and a nice package for investors but what I do care about is what has been released and what it can do

All of the issues you talk about: they aren’t solved but we’ve made amazing progress on all of them. Continual learning is a big one and labs are likely close to some POCs.

Token costs per unit performance rapidly goes down. GPT4 level perf costs you 10x less today than two years ago. This will continue to be the case as we just continually push efficiency up.

The AGI question “are we close” tbh to me these questions are just rabbit holes and bait for flame wars because no one can decide on what it means and then even if you do (e.g. super human perf on all economically viable tasks is maybe more of a solid staring point) everyone fights about the ecological validity of evals.

All I’m saying is: taking coding in a complete vacuum, we’re very very close to being at a point where it becomes so obviously beneficial and failure rates for many things fall below the critical thresholds that automating even the things people say make engineers unique (working with people to navigate ambiguous issues that they aren’t able to articulate well, making the right tradeoffs, etc) starts looking like less of a research challenge and more of an exercise in deployment

Re: Vibe coding kills open source

#273

Post by eikenberry »

WarmWash wrote: post #29

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?

Bespoke personalized apps have been around forever in the form of shell scripts. LLMs will expand that capability to a lot more people but won’t change the basic dynamics. Just like shell scripts, LLMs will need lower level building blocks to work with. The main difference will be that the LLM ecosystem will include some libraries as well. Though, I believe, most of those libraries haven’t been written yet.

Re: Vibe coding kills open source

#274

Post by nerdsniper »

dimitri-vs wrote: post #238
Bishonen88 wrote: post #179

Earlier quoted context omitted.

Expertise won't be needed (it already isn't). One can create copies of apps with vague descriptions referencing those big apps: "Create a copy of xyz. It needs to look and behave similarly. I want these features ... And on top of that ...". Millions decisions not needed. A handful of vague descriptions of what one wants is all it takes today. I think claude and co. can even take in screenshots. Documentation won't be…

But millions discussions are needed and will always be needed? "Create a copy of Amazon.com" ok, how did you want to handle 3pl fulfilment and international red tape? "No not that complicated, a minimal copy" How minimal? How many servers should I provision? How vertically integrated should we get? Etc. I really want to see someone build an app of any value with minimal decisions made.

It would be great if LLM's did this (the relevant, and very pointed, follow-up questions). Instead, today they kind of just go "okay sure yeah here it is. here's as much of Amazon.com as I can code within my token budget. Good luck drawing the rest of the owl."

Re: Vibe coding kills open source

#277

Post by MagicMoonlight »

WarmWash wrote: post #29

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?

You could already pay Indians to make you software if you wanted poorly made software. Poorly making it with AI isn’t that big an improvement.

You go to the shed because you know the hammer has undergone extensive testing and won’t immediately be hacked, costing you hundreds of millions.

Re: Vibe coding kills open source

#278

Post by estimator7292 »

WarmWash wrote: post #29

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?

LLMs have been a godsend for throwaway software. I wouldn't want to count the number of hours I've spent hand rolling an application that exists for one purpose for about two weeks and then to the digital graveyard.

Now that LLMs can do it while I make coffee, I can do more useful things with my time like writing business code and posting on HN.

Beyond that, meh.

Re: Vibe coding kills open source

#279

Post by pianopatrick »

II2II wrote: post #128
WarmWash wrote: post #29

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?

> when LLMs can build you an custom(!) hammer or saw in a few minutes, why go to the shed? Because software developers typically understand how to implement a solution to problem better than the client. If they don't have enough details to implement a solution, they will ask the client for details. If the developer decides to use an LLM to implement a solution, they have the ability to assess the end product. The pro…

> If they don't have enough details to implement a solution, they will ask the client for details.

but LLMs are chat bots. Surely eventually someone will set up an LLM based coding system that can ask architecture and design questions before starting to code.

Re: Vibe coding kills open source

#280

Post by ipaddr »

9dev wrote: post #205
ipaddr wrote: post #149

Earlier quoted context omitted.

Photographers use cameras so increasing cameras makes more photographers. CNC saws use to take pencil draws as input and now they can handle files. People always made handmade furniture while CNCs existed. Open source projects around a need will continue. Things like youtube downloader fills a need. But many projects were showing off what you as a developer can write to impress a community. Those are dead. Projects t…

> Open source projects around a need will continue. Things like youtube downloader fills a need. Good! We like things filling a need. > But many projects were showing off what you as a developer can write to impress a community. Those are dead. Good! The world doesn't need more vanity. > Projects that showcased new coding styles or ways to do things are dead. That I doubt. People who want to share ideas for the sake…

Why would companies keep open sourcing for anything new if vanity is off of the table. Many companies open sourced as a signal or to find free help. Those are not important anymore.

99 percent of developers go to the effort of open sourcing for vanity reasons. They want to show off what they made hope others like it.

The world of solutions to core problems is such a small part of open source

The other thing to consider is you will have mountains of AI slope like tailwind landing pages and alike crowding out original thought.

Post reply on HN