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

Lines of code got a better publicist

curlewis.co.nz

Post reply on HN
Print view View original

41–50 of 309 posts

Re: Lines of code got a better publicist

#41

Post by photochemsyn »

It’s worth looking at sectors where LLM code generation hasn’t been very visible, such as certification-accredited flight-control, braking, train-control, medical, or nuclear-control source code involving real-time embedded operating systems. This sector relies on assurance: deterministic scheduling requirements, detailed commit traceability, tool qualification, configuration management, independent verification, etc.

Since this is an area where failure can lead not to Instagram accounts getting hacked, but planes falling out of the sky and nuclear reactors spewing radioactive elements, it’s worth a close look. Some of the most visible companies in this sector include: QNX, Wind River, SYSGO, Lynx, Green Hills, Siemens Embedded, etc. None of them seem to have much if any adoption of LLMs for source code generation based on public statements.

Research in this area agrees with this view:

“In this paper, I have conducted a comparative analysis of the C++ code generated by popular LLMs including: OpenAI ChatGPT, Google Gemini, DeepSeek, Meta AI, and Microsoft Copilot for compliance with MISRA C++. The study revealed that none of the evaluated LLMs generated MISRA-compliant code despite clear prompts, with DeepSeek showing the fewest violations and Meta AI the most.”

https://arxiv.org/abs/2506.23535

Re: Lines of code got a better publicist

#44

Post by nyrikki »

More that LoC is a simple metric that has always been a problem.

Non-Functional requirements is a vestigial term from ‘function point analysis’ which is from the late 70s, and which also ended up being a proxy for LoC.

The entire industry is so focused on measuring now, and incentives are so skewed to short term that lagging indicators like maintainability are a non starter in many organizations that it will be challenging to fix this time.

Re: Lines of code got a better publicist

#45

Post by weakfish »

Cthulhu_ wrote: post #12
Trasmatta wrote: post #8

> I think every engineer should be using AI daily. Why?

Please read the full paragraph for the answer instead of cherry picking a quote for a knee-jerk reaction: > Be curious, try the new tools, test the latest models. To not do so is silly. > [...] > you could delay adopting “the cloud” for a couple of years and survive. With AI you might get a few months. The way we work has already changed, and it’s not changing back as far as I can tell.

> you could delay adopting “the cloud” for a couple of years and survive. With AI you might get a few months.

I really dislike these claims that act like they know the future of engineering, that they’ve been let in on some enlightenment that we haven’t been. What’s going to happen in a few months? Is Sam Altman going to nuke my house from orbit? Or is it because my CTO is going to fire me for not using AI? If it’s the latter, that’s not a curiosity problem, that’s a “there’s a gun to my head” problem.

Re: Lines of code got a better publicist

#46

Post by esafak »

sunaurus wrote: post #6

I'm constantly thinking about that Microsoft guy who posted something like "we want 1 million LoC per engineer per month", which basically read as satire to most engineers I talked to, except apparently it was not satire at all, and indeed seemed to reflect the position of many CEOs etc when it comes to LLM code generation. I do think that over the past few months, it feels like the hype around producing unmaintainab…

All else being equal, and assuming you are building the right thing, being able to deliver more correct lines of code is a good thing. The question is how to do it reliably, given that a human cannot possibly read all of it. The answer seems to me to involve spot checks with proofs of correctness and statistical quality control, the latter being things that can be automated. One issue I see is that the models are constantly changing and are therefore not well understood statistically.

Re: Lines of code got a better publicist

#47

Post by jovial_cavalier »

The kloc fallacy never actually disappeared. Project and engineering managers got wise to the fact that it was only loosely correlated with shipping features, and stopped emphasizing it. Most everyone else has carried on silently believing it without really thinking about it. And of course engineers themselves have always believed it. How many times have you heard some guy talk about how he wrote 10kloc over the weekend as a brag?

Re: Lines of code got a better publicist

#48

Post by throw4847285 »

ajd555 wrote: post #42
ajd555 wrote: post #20

Confusing skeptic and sceptic will never not be funny to me (edit: I now live in shame)

Damn it - well, I'll never live this one down, I'll learn to shut up next time

Nah, as long as you're good a sport about it, it's all good. In fact, it's refreshing to have someone make a mistake like that so confidently, and then own up to it immediately.

Re: Lines of code got a better publicist

#50

Post by JCTheDenthog »

getnormality wrote: post #5

This weird trend reached an apex in a Feb 2026 OpenAI blog post [1], recently on the front page [2], which describes the process for building... something... written 100% by agents. There is no description of what the thing is, no indication of what value it provides its users. The closest it gets is "the product has been used by hundreds of users internally, including daily internal power users". But the fact that t…

The entire Linux kernel is about 40 million LoC, and only something like 16 million LoC after you remove drivers. I have a hard time imagining whatever OpenAI was talking about there having anywhere close to 6% as much utility as the Linux kernel, despite having 6% as many lines of code. And I have a hard time imagining it's anywhere close to maintainable, regardless of how powerful their LLMs might be.
Post reply on HN