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

Is it all just vapourware?

kirahowe.com

Post reply on HN
Print view View original

181–190 of 206 posts

Re: Is it all just vapourware?

#181

Post by 20k »

mihaelm wrote: post #171
20k wrote: post #130

Earlier quoted context omitted.

They don't though, very few people were anti AI in the early days. Open source projects were largely initially very interested in LLM usage, and generally had a pro AI contribution policy. This changed when it did not help their lives Eg if you check out Godot, initially they were cool with LLM code, and then had to clamp down on it because it was not leading to anything good

Scaling AI use in highly-collaborative environments, which open source projects are, is very challenging. I totally understand the apprehensiveness around it.

How is it challenging for open source projects? You just write a PR, and try to get it to meet the maintainer's quality bar. That's exactly how all code is written in any environment - you do code review and refine a PR until its good enough to be merged

Re: Is it all just vapourware?

#182

Post by mancerayder »

20k wrote: post #39

>If agentic development actually worked the way any of them say it does I think its fascinating just how much of a gap there is between what's being claimed, and the verifiable observable data of the open source world. Major open source projects are by and large starting to ban LLMs now, because the contributions made by LLM users have been universally terrible and unhelpful. There doesn't appear to be a single major…

I'm coming to the conclusion that the right way to use LLMs for code generation is asking it to solve specific problems, giving it existing code and asking it how it would propose changing something or other, or if it has an alternative to an existing logic flow that's problematic and asking it what it thinks the problem is and how it would suggest it be written.

I'm coming from the perspective of infra management so that's my bias, and a very complex code base may make my perspective off mark.

But nowhere does it seem it to be a good idea for the whole thing to be LLM generated. It seems to view a big holistic problem in steps in isolation, causing it to add complexity on top of complexity as it's going through it's later stages. For example it'll create infrastructure designs that add layers of unnecessary and redundant tooling and business logic, when a human would have re evaluated step 1's path when it realized step 3 was doing the same thing again in a more complex way.

Re: Is it all just vapourware?

#183

Post by 20k »

vonnieda wrote: post #152
20k wrote: post #39

>If agentic development actually worked the way any of them say it does I think its fascinating just how much of a gap there is between what's being claimed, and the verifiable observable data of the open source world. Major open source projects are by and large starting to ban LLMs now, because the contributions made by LLM users have been universally terrible and unhelpful. There doesn't appear to be a single major…

> I think its fascinating just how much of a gap there is between what's being claimed, and the verifiable observable data of the open source world. According to this list of top Github repos by stars[1], of the top 10, nine of them are informational and one is OpenClaw, which certainly has plenty of AI generated code. The next 10 include react which has a CLAUDE.md and a .claude, and lots of landed PRs that look lik…

>I think it would be reasonable to ask which major open source projects aren't using AI assistance?

Where are all the vast quantity of LLM commits for these open source projects, if these engineers are truly 10xing their productivity with LLM code generation? Because I regularly browse the source of many of these, and can find almost no evidence that LLM code generation is anywhere near the level of productivity being claimed for:

1. ImGui

2. SFML

3. SDL

4. GLFW

5. OpenSSL

6. Linux

7. GCC

8. Clang/LLVM

9. Libc++/libstdc++/msstl

10. Rust

11. Godot

12. Nlohmann

13. Boost

14. Python

15. GNU tools

Etc etc. There are even more major projects, but these are just the critical ones I can think of off the top of my head. If you go for a browse though eg Godot, you might think that LLMs don't exist. In fact if you go for a browse through any of these, you might think that LLMs are borderline never used for code generation in the open source world. This is a diverse collection of random projects, and yet for some reason none of these have experienced a 10x increase in productivity in any form from any contributors from LLM code generation

>That is not why. Or at least not the majority of it

Its not the quantity, if maintainers were receiving incredibly high quality PRs that could just be merged, they'd be very happy. Godot is an example of a project that was initially pro LLM, and then had to about face because the PRs were just absolutely crap

>Some might be trash, some might be gold

Is there any evidence that any of these PRs have ever been gold?

Re: Is it all just vapourware?

#184

Post by 20k »

satvikpendem wrote: post #161
20k wrote: post #95

Earlier quoted context omitted.

Its always been possible to trade long term productivity for short term gains with technical debt. This is why the bar I'm interested in is long term projects, which have proven to have long term success, instead of a small disposable project where the code quality doesn't matter

Difference is whether it's a false dichotomy now, because models like Fable can write better code than most devs I know.

Then why isn't it showing up in open source at all? The people who file PRs are just regular average devs, but the quality of LLM PRs seems to be universally crap in comparison

Re: Is it all just vapourware?

#185

Post by Lerc »

20k wrote: post #143
Lerc wrote: post #134

Earlier quoted context omitted.

Why does it seem odd when people who do attempt to contribute back are attacked? AI lowers the bar to making submissions which permits flawed subissions to be thoughtlessly submitted by people who don't really understand what they are doing, technically or culturally. It does, however, enable people who put in the effort to work on something significant. Those people are fewer in number, but exist. They do get to see…

You'd think one 10x engineer or one core developer already part of the project would have completely eclipsed all the other engineers, and worked around the difficulties there Or, failing that, you'd think any of these engineers - given the truly vast amount of programming power now available at their fingertips with their 10x productivity - would have simply replaced these projects. It'd only take a few 10xers who w…

I can't point you at any because I don't want to send a mob their way.

For any instances where people have made things and revealed them to the world have been declared to have been grossly flawed by being held to a standard of scrutiny that no person usually gets.

It seems everyone is Cardinal Richelieu now.

Re: Is it all just vapourware?

#186

Post by Lerc »

acdha wrote: post #142
Lerc wrote: post #134

Earlier quoted context omitted.

Why does it seem odd when people who do attempt to contribute back are attacked? AI lowers the bar to making submissions which permits flawed subissions to be thoughtlessly submitted by people who don't really understand what they are doing, technically or culturally. It does, however, enable people who put in the effort to work on something significant. Those people are fewer in number, but exist. They do get to see…

People are attacked for low quality. There are counter examples but it is definitely striking how infrequently you see a PR which doesn’t stand out for being turgid or flawed, and whose author clearly expects a cookie for their “contribution” of a couple minutes of prompting.

Are you alleging that there are far more things that takes no effort than things that takes quite a lot of effort,

You might have something there.

It probably holds true for a lot of things. Either that or most gutairs sold are defective.

Re: Is it all just vapourware?

#187

Post by Lerc »

sublinear wrote: post #149
Lerc wrote: post #134

Earlier quoted context omitted.

Why does it seem odd when people who do attempt to contribute back are attacked? AI lowers the bar to making submissions which permits flawed subissions to be thoughtlessly submitted by people who don't really understand what they are doing, technically or culturally. It does, however, enable people who put in the effort to work on something significant. Those people are fewer in number, but exist. They do get to see…

Non-falsifiable statements aren't going to work here anymore. What's the point of writing great software if nobody else is going to use it, and how do we even confirm there are these alleged secret geniuses hiding away somewhere? Surely their work would leak out by some nth-order effect.

What statement did I make that was unfalsifiable?

I made a claim that absence of evidence is not evidence of absence.

That is not a claim of existence.

Re: Is it all just vapourware?

#188

Post by preg_match »

IsTom wrote: post #154
jeffreyrogers wrote: post #32

I was fairly skeptical of agentic coding before I used it for a real product. Although I still have to be heavily involved in planning the code that LLMs write for me, they can write code much faster than I can, and they know more about edge cases than I do, so they can handle edge cases/subtle bugs that I would have missed. I have been paid to write code at every level of the stack from assembly to frontend javascri…

Adding too many tests was a real issue before LLMs. You end up in situations where you when you add a feature there's 200 (out of e.g. 10k) tests that fail and you have to figure out which of them should fail and you need to fix them and which are actual bugs.

I disagree, I say the more tests the merrier, if you can afford the time cost. It's fairly rare to see faulty tests in my experience. Yes you can have hundreds failing tests and the code still works 100% - because those tests are testing API usage in a way the actual application never uses. But that's still a bug, it's just a future bug waiting to happen that you caught early. I wouldn't delete those tests.

Re: Is it all just vapourware?

#189

Post by preg_match »

wewewedxfgdf wrote: post #11

"The hard part of software engineering was never writing the code." Again, are we still on this ridiculous concept. I stopped reading at that sentence. Is that going to be the revisionist future that the industry tells itself - ""one day, LLMs came along and suddenly computers could program themselves, and it was an absolute revolution, but it made no difference at all to anything because "The hard part of software e…

I think it's true. Writing code is the most fun part of my job, but it's also the least time consuming. For any given feature, everything around the code takes 10x as much time. Getting the requirements, writing the spec, refining the spec, doing the QA work, delivery. The actual "coding" part in the middle is quick, fun, and creative. Since it's quick I get to sit and think about abstractions and performance, which is great.

But, it could be even quicker if I just give up and willingly write shitty code that works. I don't do that, but I could, and I doubt anyone outside of close developers on my team would ever notice.

Re: Is it all just vapourware?

#190

Post by DrProtic »

ethin wrote: post #63
badlibrarian wrote: post #17

It's August 9, 2026 and if you're a software engineer who hasn't had multiple "holy shit, I can't believe it just did that" moments, it's time to consider a new trade.

Okay. Please generate using an AI model code for a safety-critical system which is able to be incorporated into an aircraft and that passes the coding standards and requirements in that domain and come back and tell us all about it. Surely, if AI was so good across the entire domain of software engineering, this would be trivial to do. Edit: although you might be subject to an NDA... But this is pretty much my test f…

If he’s such a good pediatrician, would you allow him to do brain surgery on you?
Post reply on HN