And that's what happens when you spend a trillion dollars on an autocomplete: amazing at making things look like whatever it's imitating, but with zero understanding of why the original looked that way.

load more comments (8 replies)

[–] captain_aggravated@sh.itjust.works 24 points 3 days ago (2 children)

Well I've got the name for my autobiography now.

load more comments (2 replies)

load more comments (1 replies)

[–] MonkderVierte@lemmy.ml 273 points 4 days ago (14 children)

Code that does not work is just text.

[–] galoisghost@aussie.zone 172 points 4 days ago (5 children)

I’ve never thought of it that way. I’m going to add copy writer to my resume.

[–] Mouselemming@sh.itjust.works 36 points 3 days ago

Maybe fiction writer as well

load more comments (4 replies)

load more comments (13 replies)

[–] beeng@discuss.tchncs.de 17 points 2 days ago (2 children)

Write tests and run them, reiterate until all tests pass.

[–] AnotherPenguin@programming.dev 27 points 2 days ago

Bogosort with extra steps

[–] CanadaPlus@lemmy.sdf.org 15 points 2 days ago* (last edited 2 days ago) (1 children)

That doesn't sound viby to me, though. You expect people to actually code? /s

[–] aeshna_cyanea@lemm.ee 9 points 2 days ago (5 children)

You can vibe code the tests too y'know

load more comments (5 replies)

[–] SoftestSapphic@lemmy.world 55 points 3 days ago* (last edited 3 days ago) (2 children)

Watching the serious people trying to use AI to code gives me the same feeling as the cybertruck people exploring the limits of their car. XD

"It's terrible and I should hate it, but gosh it it isn't just so cool"

I wish i could get so excited over disappointing garbage

[–] person420@lemmynsfw.com 11 points 2 days ago (1 children)

You definitely could use AI to code, the catch is you need to know how to code first.

I use AI to write code for mundane tasks all the time. I also review and integrate the code myself.

[–] prettybunnys@sh.itjust.works 4 points 2 days ago

The AI code my “expert in a related but otherwise not helpful field” coworker writes helps me have a lot of extra work to do!

load more comments (1 replies)

[–] Xerxos@lemmy.ml 87 points 3 days ago (9 children)

All programs can be written with on less line of code. All programs have at least one bug.

By the logical consequences of these axioms every program can be reduced to one line of code - that doesn't work.

One day AI will get there.

[–] Nalivai@lemmy.world 13 points 3 days ago (1 children)

The ideal code is no code at all

[–] racketlauncher831@lemmy.ml 4 points 2 days ago

nocode

[–] Lemminary@lemmy.world 17 points 3 days ago (1 children)

On one line of code you say?

*search & replaces all line breaks with spaces*

[–] Szyler@lemmy.world 1 points 1 hour ago

Fired for not writing the quota number of lines even junior devs manage to hit.

load more comments (7 replies)

[–] ikidd@lemmy.world 8 points 2 days ago* (last edited 2 days ago) (1 children)

On Error Resume Next

[–] ArtVandelay@lemmy.world 6 points 2 days ago

[–] coherent_domain@infosec.pub 147 points 4 days ago* (last edited 4 days ago) (22 children)

The image is taken from Zhihu, a Chinese Quora-like site.

The prompt is talking about give a design of a certain app, and the response seems to talk about some suggested pages. So it doesn't seem to reflect the text.

But this in general aligns with my experience coding with llm. I was trying to upgrade my eslint from 8 to 9, and ask chatgpt to convert my eslint file, and it proceed to spit out complete garbage.

I thought this would be a good task for llm because eslint config is very common and well-documented, and the transformation is very mechanical, but it just cannot do it. So I proceed to read the documents and finished the migration in a couple hour...

[–] 30p87@feddit.org 72 points 4 days ago (11 children)

I asked ChatGPT with help about bare metal 32-bit ARM (For the Pi Zero W) C/ASM, emulated in QEMU for testing, and after the third iteration of "use printf for output" -> "there's no printf with bare metal as target" -> "use solution X" -> "doesn't work" -> "ude printf for output" ... I had enough.

[–] purplemonkeymad@programming.dev 56 points 4 days ago

Sounds like it's perfectly replicated the help forums it was trained on.

load more comments (10 replies)

load more comments (21 replies)

[–] haui_lemmy@lemmy.giftedmc.com 77 points 4 days ago (1 children)

Welp. Its actually very in line with the late stage capitalist system. All polish, no innovation.

load more comments (1 replies)

[–] pennomi@lemmy.world 71 points 4 days ago (19 children)

To be fair, if I wrote 3000 new lines of code in one shot, it probably wouldn’t run either.

LLMs are good for simple bits of logic under around 200 lines of code, or things that are strictly boilerplate. People who are trying to force it to do things beyond that are just being silly.

[–] Boomkop3@reddthat.com 39 points 3 days ago (18 children)

You managed to get an ai to do 200 lines of code and it actually compiled?

load more comments (18 replies)

[–] LanguageIsCool@lemmy.world 47 points 3 days ago (2 children)

I’ve heard that a Claude 4 model generating code for an infinite amount of time will eventually simulate a monkey typing out Shakespeare

load more comments (2 replies)

[–] jubilationtcornpone@sh.itjust.works 72 points 4 days ago (1 children)

Big Beautiful Code

[–] Saleh@feddit.org 49 points 4 days ago (2 children)

My uncle. Very smart very neuronal. He knows the entire Internet, can you imagine? the entire internet. Like the mails of Crooked Hillary Clinton, that crook. You know what stands in that Mails? my uncle knows. He makes the best code. The most beautiful code. No one has ever seen code like it, but for him, he's a genius, like i am, i have inherited all his genius genes. It is very easy. He makes the best code. Sometimes he calls me and asks me: you are even smarter than i am. Can you look at my code?

load more comments (2 replies)

[–] 1984@lemmy.today 35 points 3 days ago* (last edited 3 days ago) (3 children)

Its like having a junior developer with a world of confidence just change shit and spend hours breaking things and trying to fix them, while we pay big tech for the privilege of watching the chaos.

I asked chat gpt to give me a simple squid proxy config today that blocks everything except https. It confidently gave me one but of course it didnt work. It let through http and despite many attempts to get a working config that did that, it just failed.

So yeah in the end i have to learn squid syntax anyway, which i guess is fine, but I spent hours trying to get a working config because we pay for chat gpt to do exactly that....

[–] merc@sh.itjust.works 22 points 3 days ago (6 children)

It confidently gave me one

IMO, that's one of the biggest "sins" of the current LLMs, they're trained to generate words that make them sound confident.

load more comments (6 replies)

load more comments (2 replies)

[–] ZombiFrancis@sh.itjust.works 34 points 3 days ago

Ctrl+A + Del.

So clean.

load more comments