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

Why write code in 2026

softwaredoug.com

Post reply on HN
Print view View original

161–170 of 321 posts

Re: Why write code in 2026

#161

Post by furyofantares »

ekidd wrote: post #117
ryandvm wrote: post #78

Earlier quoted context omitted.

They don't have Claude write assembly because there is no training corpus on people making CRUD apps in assembly. I'm as hateful of LLMs hollowing out the job market as the next guy, but the reality is the frontier LLMs are really good at writing anything that's been done and documented on the Internet a million times and unfortunately most of what software devs have been doing the last couple decades is shitting out…

Claude is perfectly capable of writing assembly. Here's a working (basic) Prolog interpreter that Claude Fable 5 wrote in WebAssembly in 61 minutes for $16.75 in token costs: https://github.com/emk/fable-wasm-prolog/blob/main/prolog.wa... WebAssembly is slightly easier than real assembly, but here Fable used WASM GC extensions, which are poorly documented and not yet super common. Fable didn't even need to debug it;…

I have a personal game framework that I have LLMs write games in, which is in AssemblyScript. AssemblyScript is certainly closer to TypeScript than it is to WebAssembly, but it's still this thing where the host shares some big chunk of memory with the script and you pick some memory locations to read and write as your means of exposing APIs, and there's not a lot of training data on games written in AssemblyScript and even less in my game framework specifically (none) - and the LLM does an excellent job.

Re: Why write code in 2026

#162

Post by lowsong » 

    Writing code helps me think.
Every time I read some take about keeping up one's skills when using agents people get so tantalisingly close to the obvious answer, and then fall short.

If the tools are making you worse, don't use the tools.

Re: Why write code in 2026

#163

Post by fuzztester »

mrweasel wrote: post #73

Apparently it's not obvious to everyone, but if you can't write code, you can't review it. I do know people, and companies, that says: "So what, we ask Claude to write the code, Codex will then do the review". The thing that then strikes me as odd is that they still ask for the code in Python, Java, or some other high level language.... Why? Just ask Claude to dump out assembly, or a compiled binary, but no, they don…

dump out assembly?

aargh! haalp!

Which rock are you living under these days.

Nowadays everything is IR or MLIR ... or AIR ...

whoops, i may have skipped a few generations. hard to keep up with the dynamic pace these days. got a job to save. sorry suh.

mumble javascript mumble framework of the half-week ...

walks off muttering

Re: Why write code in 2026

#164

Post by h4kunamata »

This does not seem obvious to AI-developers, you cannot fix what you do not understand.

Also, if you use AI to write your code, you are not a developer either.

Let's say AI completely disappears right now, many of the so called "developers" are unable to write code, are unable to fix code, they cannot code.

There are two kind of developers:

1. Non-developers: Use AI for everything, to write code, to test the code, you name it.

2. Real developers: Search engines are broken right now, they use AI as a tool, as replacement for Google to ASSIST you, not to do the task for you.

As AI is falling apart and companies are hiring people back, these non-developers will find themselves out of work.

Re: Why write code in 2026

#165

Post by squibonpig »

h4kunamata wrote: post #164

This does not seem obvious to AI-developers, you cannot fix what you do not understand. Also, if you use AI to write your code, you are not a developer either. Let's say AI completely disappears right now, many of the so called "developers" are unable to write code, are unable to fix code, they cannot code. There are two kind of developers: 1. Non-developers: Use AI for everything, to write code, to test the code, yo…

Ai will fall apart as an industry but it's likely that models on par with e.g. opus 4.8 will be runnable on a home server within the next year and a half and that model hosts will still exist. I figure these tools aren't likely to go away.

Re: Why write code in 2026

#167

Post by fuzztester »

lelanthran wrote: post #142
enraged_camel wrote: post #138

Earlier quoted context omitted.

>> There's more to it than that: writing is thinking. If you stop writing code, you aren't thinking anymore. Humans have been thinking long before writing was invented . Why is code special?

> Humans have been thinking long before writing was invented. And look how poorly they did it until they invented writing. > Why is code special? You don't get better at thinking without doing. With code the "doing" part is writing. In your view, it is reasonable to expect HS students to thoroughly read a book on trigonometry and then ace the exam? We know, from experience , that only by doing problems does the stude…

>>Humans have been thinking long before writing was invented.

>And look how poorly they did it until they invented writing.

Yeah, look how poorly they did it until they invented writing.

[peers into the dim ancient past]

Sorry, my time-machine spectacles are on leave or on strike today.

And congrats on being a multi-millen(ium)arian, and a mind reader, who could both 1) exist so far back in the past, and 2) be able to know the thoughts of people who didn't write them down, because they didn't know writing.

/s

Re: Why write code in 2026

#168

Post by deadbabe »

walt_grata wrote: post #150
deadbabe wrote: post #132

Earlier quoted context omitted.

it's also plausible that with an ability to generate as much code as we want with little effort, we will quickly discover how much code we actually need, and then plateau at that point. Personally, I think we've already reached that point. Even at YC, I have not really seen any startup doing anything interesting where their main value prop is enabled by new proprietary code that does stuff no one else can already do.

We have more code than we need. Proof for me is every "smart" device that worked better before we put a computer in it.

Exactly, this is the true problem with the world today: too much code.

Re: Why write code in 2026

#169

Post by cozzyd »

avaer wrote: post #71
majorbugger wrote: post #65

Why is this even a legit question? I need to keep writing code to stay relevant, not to forget my craft, be able to review code... So many reasons. AI doesn't change a thing.

Before my time ppl mostly did things in asm, I bet the vast majority of people reading this have never touched assembly and will never have any reason to. This is quickly becoming true of most "code". AI has changed that. One way to "stay relevant" would be to admit that.

How can you evaluate what your compiler is doing without looking at the assembly? The many users of godbolt suggest it's pretty common.

Re: Why write code in 2026

#170

Post by satvikpendem »

lelanthran wrote: post #142
enraged_camel wrote: post #138

Earlier quoted context omitted.

>> There's more to it than that: writing is thinking. If you stop writing code, you aren't thinking anymore. Humans have been thinking long before writing was invented . Why is code special?

> Humans have been thinking long before writing was invented. And look how poorly they did it until they invented writing. > Why is code special? You don't get better at thinking without doing. With code the "doing" part is writing. In your view, it is reasonable to expect HS students to thoroughly read a book on trigonometry and then ace the exam? We know, from experience , that only by doing problems does the stude…

> And look how poorly they did it until they invented writing.

How can you know how poorly they did it?

Post reply on HN