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

281–290 of 321 posts

Re: Why write code in 2026

#281

Post by mattmanser »

soco wrote: post #251
mattmanser wrote: post #234

Earlier quoted context omitted.

I think you're pretty wrong here, but I'm no expert so anyone who wants to correct me please do so. As I understand it, there's post-training step that does exactly that, they get real developers to select good and bad code and help the AI figure that out. AFAIK it's the reason why Claude was able to leap-frog OpenAI in coding last year, they did this refinement step a lot better. And now they've taught the older mod…

Claude's coding efficiency is largely due to their control plane governing the actual execution of the model - rules, evaluators and basically looping over results. Not related to the model training or fine tuning.

The models were already much better before Claude Code came out, let's not rewrite history here.

Re: Why write code in 2026

#282

Post by jimbokun »

wartywhoa23 wrote: post #218
jimbokun wrote: post #179

Earlier quoted context omitted.

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.

As soon as human software engineers are Ubered away from the field, the price will ramp up to that of a human software engineer or more, have no doubt. ROI won't make itself up.

Then everyone just starts running open weight models locally.

Re: Why write code in 2026

#283

Post by satvikpendem »

ioseph wrote: post #239
jacomoRodriguez wrote: post #227

Earlier quoted context omitted.

Improvements or just new ways to be occupied and more work? It seems life without agriculture and the like was way simpler and chilled.

Until winter.

Humans have been storing food for winter for hundreds of thousands of years before agriculture and the invention of writing, you think they all died off or something? People whose crops failed instead were more heavily affected in winter than hunter gatherers.

Re: Why write code in 2026

#284

Post by mewpmewp2 »

chromadon wrote: post #237

"Why write code in 2026".. Because AI generated code is STILL complete ass. Even Fable, even whatever custom Pi/opencode leet code harness you have, the output is awful, and, if you cannot distinguish the quality of your code vs the AI's, I've got some bad news for you.

My code is/was worse than AI's, but at least I get paid, so what do I care about the bad news you have.

Re: Why write code in 2026

#285

Post by wartywhoa23 »

jimbokun wrote: post #282
wartywhoa23 wrote: post #218

Earlier quoted context omitted.

As soon as human software engineers are Ubered away from the field, the price will ramp up to that of a human software engineer or more, have no doubt. ROI won't make itself up.

Then everyone just starts running open weight models locally.

Running it on RAM and GPUs which cost like a private jet plane, or have to be smuggled in like cocaine due to import/export tariffs or bans.

Re: Why write code in 2026

#286

Post by DaiPlusPlus »

ipsod wrote: post #276
DaiPlusPlus wrote: post #266

Earlier quoted context omitted.

I'm not anxious about my codebase; I'm anxious about all the fun parts being sucked out of my job as though I'm being promoted from IC to management - and given the inevitability of progress I can see how my new role as an agent shepherd, too, could be obsoleted in the near-future. ...so I've been avoidant of the whole thing ever since 2023, burying my head in the sand to avoid those feelings of anxiety and uncertain…

Ah, well... I can't say that there's any real hope. I dove in in ~2023, and I'm about as deep in it as one can be. The better I get at it, and the better the agents get, the less time I spend even doing what I do - one prompt will often take 3+ hours. I often keep 8+ agents churning for the whole workday (and leave them running when I leave, too, and it's very often that they'll work from 4pm to midnight or later). I…

May I ask what you end-up doing for the rest of the day?

Re: Why write code in 2026

#287

Post by ares623 »

mewpmewp2 wrote: post #255
ares623 wrote: post #215

Earlier quoted context omitted.

Fair. But in all 3 did you very quickly write down the solution as soon as you were able?

My best thinking is when I am going for very long runs, when I write down the thought, my brain stops thinking about it, considers it done and moves on. When writing, thoughts become forced and linear in my view as opposed to floating in a specific way from point to point. Like I lose the natural creativity. Writing is about remembering or communicating, so it is summarizing the thoughts, but it is not thinking itsel…

I see, I'm the same too. Throughout my day my thoughts would be flying and zooming around. Some of them good, most of them not good or otherwise useless.

When I sit down to try and write them down, I blank out. Or the thoughts that I thought were good/useful, I second guess when writing them down. Perhaps it's just lack of practice on writing them down (I'm trying to use a typewriter to do so recently).

Re: Why write code in 2026

#288

Post by inigyou »

imhoguy wrote: post #203
gblargg wrote: post #187

Earlier quoted context omitted.

> My other article on this topic advocates for using code over specs :) Code is executable. Specs are not.

Prompt is executable (interpreted) code with LLM agent harnes now, just the syntax is fuzzy. "Please print 'hello world'"

Oh no.

It's IRP.

https://esolangs.org/wiki/IRP

Re: Why write code in 2026

#289

Post by inigyou »

softwaredoug wrote: post #241
jillesvangurp wrote: post #231

Earlier quoted context omitted.

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…

Sadly, AI can process semantic vectors in latent space much more effectively than any human.

Re: Why write code in 2026

#290

Post by inigyou »

galaxyLogic wrote: post #210
weakfish wrote: post #173

Earlier quoted context omitted.

You’re assuming that progress will continue at the same rate (it’s plateaud a bit as far as I can tell, I can look for sources tomorrow but am on phone now :)) & I think it’s fairly demonstrated that the industry isn’t profitable for training ever increasingly huge models, which get exponentially more expensive each iteration

I wonder, LLMs have progressed at great speed, because they have learned to duplicate what humans did and recorded in the documents and source-code that became the training materials for the LLMs. But now that humans don't write any more code, there is no new learning materials for the LLMs. There are no new things for them to learn. Therefore I expect they will plateau, the progress is no longer so fast. And maybe w…

They are now paying full-time programmers to write new training data.
Post reply on HN