Live data from Hacker News

Writing code is cheap now

simonwillison.net

461–470 of 522 posts

Re: Writing code is cheap now

#461

Earlier quoted context omitted.

> But do the humans need to actually understand the code? A "yes" means the bottleneck is understanding (code review, code inspection). A "no" means you can go faster, but at some risk. I always thought of things like code reviews as semi pseudo-science in most cases. I've sat through meetings where developers obviously understand the code that they are reviewing, but where they didn't understand anything about the s…

> If anything, I think AI will increase human understanding How?

Have you met the average programmer on a thursday afternoon after a terrible week of little sleep, family issues and unnecessary meetings? When I'm in that state of mind myself I'm fairly confident that any LLM could explain my weeks work better than I could.

Re: Writing code is cheap now

#462
post #349

Earlier quoted context omitted.

So code was apparently cheap, but in fact it was expensive because it was low quality. Now with LLMs, code is cheap and it also has quality, therefore "quality code can be had in the cheap". Do you really believe this is the case? Why don't companies fire all their developers if they can have an algorithm that can output cheap and quality code?

This what I really wonder, what is even the cost of code? Or what is real code quality. I know that things like “clean code” exists but I always felt that actual code quality only shows when you try adding or changing existing code. Not by looking at it. And the ability to judge code quality on a system scale is something I don’t think LLMs can do. But they may support developers in their judgment.

I don't know why people think SWEs are aesthetic snobs when we talk about "clean code"--the point of code is not to be pretty, it's to be understandable and predictable.

Quality doesn't matter if you're writing throwaway code or you need your startup to find a market before you run out of cash.

But once it matters, it matters a lot.

Re: Writing code is cheap now

#463
post #66

Earlier quoted context omitted.

Indeed: The act of actually typing the code into an editor was never the hard or valuable part of software engineering. The value comes from being able to design applications that work well, with reasonable performance and security properties.

It wasn't the hard or valuable part of software engineering, but it was a very time-consuming part. That's what's interesting about this new era - the time-consuming-but-easy bit has suddenly stopped being time-consuming.

It's not time consuming. It seemed slow because of all the other important parts of the job. People vastly overestimate how much time SWEs actually spend writing code lol

Re: Writing code is cheap now

#464

Earlier quoted context omitted.

> Once you can ask your agent to change a feature and be 100% sure they won't break other features then you don't care about how the code looks like. That bar is unreasonably high. Right now, if I ask a senior engineer to change a feature in a mature codebase, I only have perhaps 70% certainty they won't break other features. Tests help, but only so far.

This bar only seems high because the bar in most companies is already unreasonably low. We had decades of research into functional programming, formal methods and specification languages. However, code monkey culture was cheaper and much more readily available. Enterprise software development has always been a race to the bottom, and the excitement for "vibe coding" is just the latest manifestation of its careless, t…

> functional programming, formal methods and specification languages

Haha. Tell me you've never done professional software development without, etc. None of those things are solutions to the problem, which is: does the code do the business value it's supposed to?

Re: Writing code is cheap now

#465
post #457

Earlier quoted context omitted.

> Falcons certainly aren't deterministic. Well falcons are not deterministic and are trained to do something in the art of falconry, yes. Still I fail to see an analogy here as it is the falcon gets trained to execute a few specific tasks triggered by specific commands. Much like a dog. The human more or less needs to remember those few commands. We don't teach dogs and falcons to do everything do we ? Although we do…

I've found that using LLMs has had a very material effect on my productivity as a software developer. I write about them to help other people understand how I'm getting such great results and that this is a learnable skill that they can pick up. I know about the METR paper that says people over-estimate the productivity gains. Taking that into account, I am still 100% certain that the productivity gains I'm seeing ar…

Is this code public?

Re: Writing code is cheap now

#466

I think there's a good parallel with AI images - generating pictures has gotten ridiculously easy and simple, yet producing art that is meaningful or wanted by anyone has gotten only mildly easier. Despire the explosion of AI art, the amount of meaningful art in the world is increased only by a tiny amount.

But the amount of pleasing useful art has gone up x1000; If I had a blog, I would now have access to art that would be a perfect fit for my words, whereas 5 years ago, I would have to do with a my own (talent-lacking) doodles. Would some people prefer no art/illustration to AI generated art? Sure. But even more would prefer no art to my doodles.

Not really, it's all samey blandness. It makes good copies of bland samey stock photos

Re: Writing code is cheap now

#467
post #47

Earlier quoted context omitted.

True, however as these products have been designed and coded by LLMs from the ground up in 2025+, they are generally using modern (typed even) languages, the latest version of third party libraries, usually have documentation of sorts... sometimes they even have test suites. As such, they can often be improved as easily as one can prompt, which is much faster and easier than before. Notably in the FOSS world where on…

I've tried very earnestly to use opus 4.5 to get rid of some backlog tasks that were too tedious to do manually. It turns out that they're still extremely tedious because I have to make every single non trivial decision for the model, unless I don't care one iota about the long term sustainability of the code base. And by long term, I mean more than a week. They're good for saving keystrokes or doing fuzzy searches f…

I actually had a perfect use case for slopcoding - I needed to scrape a search result and turn it into a csv and a bunch of files.

Totally possible with a hour or so or coding but annoying and not that fun. Completely trivial, tons of stuff like it, piece of cake

Claude got something that looked like it was worked, and didn't. I figured out why, told it what to fix, and it didn't.

Finally after several rounds, it kicked off...and then hung on...something? idk what, it doesn't look like it was rate limited

Also it said the code would check to see it had already downloaded the file and if so, skip it. It definitely did not do that lol

At this point it was 90 minutes--an hour of yelling at the computer and another 30 minutes of my ADHD ass forgetting that I had it running

I like it as fancy autocomplete because it's usually helpful and I can silence it for 20 minutes if it's annoying me, but man.

Re: Writing code is cheap now

#468
post #465
post #457

Earlier quoted context omitted.

I've found that using LLMs has had a very material effect on my productivity as a software developer. I write about them to help other people understand how I'm getting such great results and that this is a learnable skill that they can pick up. I know about the METR paper that says people over-estimate the productivity gains. Taking that into account, I am still 100% certain that the productivity gains I'm seeing ar…

Is this code public?

The macOS presentation app is at https://github.com/simonw/present

Re: Writing code is cheap now

#469
post #354

Earlier quoted context omitted.

I don't know if you've heard, but there have been a large number of layoffs in the tech sector recently. Whether they're actually related to AI as executives claim, and not section 174 of the US IRS tax code in the BBB, is known only to them, but if your argument hinges on people having not been fired when there have been layoffs, you may need a different one.

As you said, it's impossible to determine how many of the current layoffs are caused by AI, they probably also have a lot to do with the broader economic downturn. But you’re still missing the point, if companies truly have a black box that can produce cheap, high‑quality code as the GP put it, why don't they just fire 95% of their developers and keep only a small core of AI orchestrators?

Who's missing who's point? You're asking why haven't they fired 95% of their people. I'm pointing at tech sector layoffs saying people are being laid off. It's not 95% which is a number you totally made up, but in the broader picture, I wouldn't say it isn't happening.

Re: Writing code is cheap now

#470

Earlier quoted context omitted.

> Have we not learned anything about technical debt and how it bites back hard? I think LLMs are changing the nature of technical debt in weird ways, with trends that are hard to predict. I've found LLMs surprisingly useful in 'research mode', taking an old and badly-documented codebase and answering questions like "where does this variable come from, and what are its ultimate consumers?" Its answers won't be as natu…

> taking an old and badly-documented codebase and answering questions like "where does this variable come from, and what are its ultimate consumers?" Why do you even need an LLM for this? Code is formal notation, it’s not magic. Unless the code is obfuscated, even bad code is pretty clean on what they’re doing and how various symbols are created and used. What is not clear is “why” and the answer is often a business…

Once you are dealing with legacy codebase older than you, with very little comments and confusing documentation, you'd understand that LLM is god send for untangling the mess and troubleshooting issues.
Post reply on HN