Hacker News

points by nsbdhciebsbdhc 22 hours ago | 0 comments

Wanting stuff to work is a valid reason to not use AI for more sophisticated development projects. Having a computer that kernel panics once every three days is useless to me, even if it works for you.

[–] Kwpolska 18 hours ago

A kernel panic is the least of your worries with this hardware. Asahi had to introduce a custom daemon to avoid frying speakers. Apple doesn't need to care about making the hardware interfaces safe if they control the entire stack, so they don't, and expose dangerous capabilities to the OS.

[–] Wowfunhappy 13 hours ago

Does this generalize to basically anything outside of speakers though? I think a pretty easy solution is to not use AI for that specifically.

[–] orangea 11 hours ago

thermal management is the first thing that comes to mind. and battery management

[–] getcrunk 1 hour ago

You would hope both those systems have built in hw failsafes

[–] LoganDark 18 hours ago

There was a fun period of time where Boot Camp still existed, but Windows could fry the speakers because it didn't have any of macOS's thermal protection. I think this was after the 2016 redesigns, as I had a mid-2015 with no such issue.

[–] perching_aix 3 hours ago

Good thing they only ever write correct code which consistently obeys every invariant in that entire stack ever. Excellent design, meet perfect engineering.

[–] gloxkiqcza 22 hours ago

Linux kernel itself is AI development friendly.

[–] tonyedgecombe 21 hours ago

Some of us think that is a mistake.

[–] aeonik 19 hours ago

Hmm very vague. "Some of us".

Do the massive amount of vulnerabilities not make you think twice?

At this point, I trust human code less than llm code. Design and architecture of the code still greatly benefit from a good human touch, but I'm not sure how long that will remain true.

https://www.phoronix.com/news/OpenAI-948-Linux-LPE-Bugs

[–] nsbdhciebsbdhc 16 hours ago

So validate with an llm and humans. People committing code they haven't read - which will inevitability happen - is dangerous and hard to remotely verify.

[–] zdragnar 4 hours ago

People using LLMs put up much larger changes, and much faster. Depending on the LLM used the quality is often much lower.

A lot of projects just stopped accepting any outside contributions rather than deal with the tidal wave of slop they were getting. Choosing to not accept LLM code is IMHO a better compromise.

[–] rowanG077 13 hours ago

In the end there is always a separate reviewer. Even if the producer is adversial and not even looking at the code then this process exists to catch it. This is not at all different from people attempting to get backdoors into Linux.

[–] codedokode 9 hours ago

LLMs will introduce new vulnerabilities. What Linux should have done is stop using non-standard C, or better, stop using C completely in favor of Rust, support code analysers.

[–] palata 8 hours ago

And humans can introduce new vulnerabilities, too. Linux maintainers accept patches from random people over the internet. They already have to just the patch on its technical merit, not on who submitted it. For them I don't think it makes a difference (technically) if the patch was written with the help of an AI.

I believe that there may be valid reasons to refuse anything that was touched by an AI, but that's not about security. It's more about the non-technical problems coming from AI (centralising power, increasing inequalities, carbon footprint, ...).

[–] jasonvorhe 19 hours ago

Some people will always disagree with something. That's what's great about free software. There will probably be some Luddite anti AI Linux fork at some point.

[–] cromka 21 hours ago

That's not what they meant. It's AI friendly, not slop-friendly.

There's a reason no Omarchy patch of any kind has made it to the kernel list yet. I did personally look into some of their code and it is certified, hacked-togeter slop.

[–] ffemac 12 hours ago

Exactly. As an example, read that Gravity Linux guy's responses here. I will never ever trust him. I will stay away from his code as far as possible. Asahi team: I have my trust in you.

[–] ChocolateGod 20 hours ago

How do you define the difference between ai friendly and ai slop?

[–] dj_morocco 20 hours ago

I'm pretty sure Asahi devs experiment with LLM tools, but not to Omarchy's extent. LLM ban is purely a filtration filter, so that they wouldn't be spending time overbearingly exhausting number of patches generated with AI, and not someone who cares about this than a shiny tool.

Everyone understands that LLM is a mean to an end, but it's clear that Omarchy got two confused and it's showing.

[–] saagarjha 1 hour ago

No, they’re pretty against AI in general.

[–] inejge 20 hours ago

My definition, FWIW.

AI-friendly: you can use the LLMs however you wish, but you must thoroughly understand every part of submitted code.

Slop-friendly: understanding anything is optional.

[–] ChocolateGod 9 hours ago

I also agree with that definition. But for example if I get an LLM to generate 95% of a program, but I understand and have read every line of code, is it still slop?

Some would say yes unfortunately.

[–] palata 8 hours ago

Not the OP, but I wanted to share my 2 cents:

As an open source maintainer, when someone opens a PR, I don't know who they are. But I don't really care. I care about the PR: is it a "good" PR (there are multiple dimensions: is it understandable, does it add maintainable code, was it tested, etc) or not?

I think "AI-friendly" says "I don't care if it's written with an AI or not: I want good quality PRs".

I would think that "slop-friendly" is the kind of projects where the maintainers don't read the code. Maybe they try the feature (maybe not even?). I think the Omarchy guy was explaining somewhere that he does not read the code anymore, he just lets his AI write Rust. This is slop-friendly IMO.

If you are not AI-friendly, it means that you refuse to accept a good PR even if you cannot tell that an AI was involved. The mere fact that an AI was involved disqualifies the PR.

[–] shwaj 1 hour ago

Are you one-shotting then reading/understanding? Then probably slop.

Are you iterating to help you understand, prompting to rename/restructure/document until you would have been able to easily understand without AI? Then probably not slop.

[–] flykespice 10 hours ago

Ai friendly patch:

* Author posts patch with a manageable number of lines so maintainer doesn't gets burned out reviewing it.

* Tries to outline on the body what the patch is about and his rationale for the design decisions on the code.

* Promptly answers any maintaners questions about the line changes.

* Discloses which AI model he used to assist on the patch and how was it used.

AI slop patch:

* Submits patch with huge lines of code without explanation.

* The body is written in a self-patronizing tone with superfluous formatting that helps nothing but annoys who is looking for the actual substance of patch

* When questioned by maintainer about some line changes either goes radio silent or reply with the usual AI tone of marketin salesman.

* rarely if ever discloses AI usage.

[–] tkel 20 hours ago

experience

[–] BluSyn 2 hours ago

Human slop is far worse than then AI slop.

[–] orangecat 10 hours ago

It's amusing that people still default to "human-written code is solid and AI code sucks" after the enormous quantity of bugs that AIs are finding in human-written code.

[–] bigstrat2003 7 hours ago

Nobody has ever said human code is perfect. But it is empirically the case that code written by LLMs is on average lower quality than code written by humans.

[–] habitue 3 hours ago

That's not really true, and it's only even potentially true if we talk about the absolute cream of the crop developers. Most human written code is quite bad actually

[–] saagarjha 1 hour ago

> absolute cream of the crop developers

You’re reading their blog

[–] BluSyn 2 hours ago

This has not been true for 6 months. Update your priors.

[–] kcb 6 hours ago

Having a computer where half the features don't work isn't particularly great either...

[–] nickysielicki 9 hours ago

Ok boomer