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

241–250 of 321 posts

Re: Why write code in 2026

#241

Post by softwaredoug »

jillesvangurp wrote: post #231
Pavilion2095 wrote: post #217

Earlier quoted context omitted.

> The relevant question is who is going to pay you to write code manually. Hopefully companies in the industries where software quality matters and is regulated, e.g.: medicine, aviation, nuclear, etc. Although this market is relatively small.

You seem to assume that people still have an inherent advantage here. Mostly those sectors compensate for well documented human failures with very rigid and expensive processes and testing. And of course despite that, stuff still goes wrong occasionally. I actually think AI based automation is going to be a key enabler in those kinds of strict environments as well. Recent work on identifying e.g. security bugs seems…

There are ways humans have an advantage. Not in the line by line code, but in the experience of having the whole mental model in your head.

Writing some code with the whole context in your head is the human advantage.

I’m not precious about that code. Maybe it needs to be rewritten by an agent. Or we could build good abstractions so it’s trivial to see the system. We could also use systems that by their design force us + agents away from security, performance, etc

Re: Why write code in 2026

#242

Post by softwaredoug »

SpicyLemonZest wrote: post #188
bluefirebrand wrote: post #143

Earlier quoted context omitted.

> It’s ok to talk to the agent in code. Or create examples for it to follow If you're doing this, then why not just write the effing code?

"Hey Claude, can you please make a full matrix of tests according to the following pattern and parameters? Thanks." That's 15-20 minutes of work that can run in the background while I do something else.

Exactly this. Spending a few hours crafting and debugging a test you trust save hours of pointless agent time.

Re: Why write code in 2026

#243

Post by t43562 »

fragmede wrote: post #176
gnabgib wrote: post #149

Earlier quoted context omitted.

Loops (conditional JMPS - JE/JNE/JZ/JNZ/JB/JNB.. and a dozen others) and functions (CALL, RET) exist in assembly. Goto is there too (all JMPs). C makes assembly sense.

Oh that's an interesting thought. Goto's are considered harmful, because holy hell as a human trying to understand and reason about code, the spaghettifcation if someone else used gotos all over the place and I have to reconstruct their thought process just doesn't sound like fun. But if we're no longer writing code by hand (which, I gotta be honest, I'm using AI to write a lot of code for me these days), then does t…

goto is already useful as an end-of-function cleanup. You pop one at the end of each function (the naming is local to the function) and that's the place where you free ram if the pointer's not null and close the file if the handle is not null and so on.

Then you don't have to litter all of your if/else clauses with hundreds of memory frees and cleanups - you just "goto"

The fact that this is controversial to some people just shows how rules like "Dont use goto" become stupid - if one is trying to make code simpler then there are cases were not using it is the more confusing and error prone choice.

As for "can we now do anything" well if you don't ever need to debug "anything" then yes and if you have any small doubts about your LLM then no.

Re: Why write code in 2026

#244

Post by t43562 »

galaxyLogic wrote: post #204
Salgat wrote: post #183

Earlier quoted context omitted.

LLMs are perfectly capable of translating between programming languages at this point. The main bottleneck for them is logic, not language.

And the amount of logic needed to understand code, including how to fix it or modify it further depends on how complicated the code-structure is. I wonder about this: Does LLM write better code in a better language? Humans often have more difficulty fixing existing code than reqriting it from scratch, and un-structured un-constrained code would be a big reason for that. But maybe it doesn't apply to an LLM if it alwa…

> I wonder about this: Does LLM write better code in a better language?

The whole point is to rewrite everything in a language you don't understand and then ignore whether it's better because you can't tell.

That language, of course, must be Rust.

Re: Why write code in 2026

#245

Post by t43562 »

ares623 wrote: post #152
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?

have you tried thinking for a long time without writing anything down?

writing is a way to get your brain to put thoughts into a form that someone else will be able to reach the same understanding as yourself. The effort to explain oneself often leads to better understanding: Duck Debugging basically.

Re: Why write code in 2026

#246

Post by t43562 »

softwaredoug wrote: post #100
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…

I’m finding it all boils down to cognitive differences. Some people find code easier to read than the English description. It’s more precise and many experienced devs can scan it and know what’s happening Many other people can’t read code. Or they find English easier to read than code. Thats not a knock on anyone. Maybe the latter will rule the world because the former focuses too much on irrelevant details. Or maybe…

The code tells you HOW, the English should be telling you WHY. Both are usually needed IMO. Even a tiny bit of "why" can be extremely helpful to understanding in my experience. I don't want generated AI garbage that merely describes the code - I want the reason the whole thing exists and what was wanted by the person who wrote it.

Re: Why write code in 2026

#247

Post by t43562 »

satvikpendem wrote: post #171
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…

> Just ask Claude to dump out assembly, or a compiled binary, but no, they don't trust the LLM that much No, people do advocate for this. It may simply not be as portable however as something that is high level able to be compiled to assembly for many machines.

It's the logical outcome of believing that human skills aren't important and that you can "think at a higher level". You can't spend all your time thinking at a higher level if you cannot fully trust the output and the assembler argument is just taking the thing to an extreme to make that point.

Re: Why write code in 2026

#248

Post by t43562 »

fuzztester wrote: post #163
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

No need for IRs if LLMs are all powerful. Just tell them to generate x86 and ARM and let them get on with it.

Re: Why write code in 2026

#249

Post by coderatlarge »

ryandvm wrote: post #78
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…

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…

couldn’t the frontier labs simply compile their existing source code training data and have an assembly corpus to train on?

Re: Why write code in 2026

#250

Post by coderatlarge »

jimbokun wrote: post #179
ekidd wrote: post #117

Earlier quoted context omitted.

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;…

Just interesting to see Claude’s hourly rate is around $17. Much cheaper than a human software engineer. But comparable to the wages for some human workers.

claude helped me build a functional visual modem (using the cameras and microphones/speakers) for mac/iPhone in about a day and i've been curious about the feasibility of this concept for quite some time and now i have an actual example to study and measure and hack on, for a fraction of the cost of my pro sub. it wasn’t trivial, i doubt a non-swe could get it done in that time, but i'm a pretty happy customer overall.
Post reply on HN