The hidden cost of AI coding • Hacker News Board

Re: The hidden cost of AI coding

#101

Post by p0w3n3d » Thu, Apr 24, 2025, 5:56 AM UTC

codr7 wrote: post #59

I've tried getting different AIs to say something meaningful about code, never got anything of value back so far. They can't even manage tab-completion well enough to be worth the validation effort for me.

Yeah I wonder how do the code look after such professional AI development. I tried ChatGPT 1o to ask it about simple C function - what errors are there. It answered only after I directly asked about the aspects I was expecting it to tell about. It means that if I didn't know that the LLM wouldn't tell me...

Re: The hidden cost of AI coding

#102

Post by JodieBenitez » Thu, Apr 24, 2025, 6:10 AM UTC

JohnFen wrote: post #91

tptacek wrote: post #4

After all, if we lose the joy in our craft, what exactly are we optimizing for? Solving problems for real people. Isn't the answer here kind of obvious? Our field has a whole ethos of open-source side projects people do for love and enjoyment. In the same way that you might spend your weekends in a basement woodworking shop without furnishing your entire house by hand, I think the craft of programming will be just fi…

> Solving problems for real people. Isn't the answer here kind of obvious? No. There are a thousand other ways of solving problems for real people, so that doesn't explain why some choose software development as their preferred method. Presumably, the reason for choosing software development as the method of solving problems for people is because software development itself brings joy. Different people find joy in di…

> That would pretty much be a life crisis, as I'd have to find and train for something else.

There's inertia in the industry. It's not like what you're describing could happen in the blink of an eye. You may well be at the end of your career when this prophecy is fulfilled, if it ever comes true. I sure will be at the end of mine and I'll probably work for at least another 20 years.

Re: The hidden cost of AI coding

#103

Post by plsbenice34 » Thu, Apr 24, 2025, 6:10 AM UTC

codr7 wrote: post #52

blueboo wrote: post #23

The old joy may be gone. But the new joy is there, if you're receptive to it

And which joy is that? Short sighted profits?

Injecting malware via flaws in the shitty programs, maybe

Re: The hidden cost of AI coding

#104

Post by th0ma5 » Thu, Apr 24, 2025, 6:10 AM UTC

simonw wrote: post #72

only-one1701 wrote: post #61

Earlier quoted context omitted.

What should I have done there? Tell it to make sure that it gives me all 10 objects I give it back? Tell it to not put brackets in the wrong place? This is a real question --- what would you have done?

How long ago was this? I'd be surprised to see Claude 3.7 Sonnet make a mistake of this nature. Either way, when a model starts making dumb mistakes like that these days I start a fresh conversation (to blow away all of the bad tokens in the current one), either with that model or another one. I often switch from Claude 3.7 Sonnet to o3 or o4-mini these days. I paste in the most recent "good" version of the thing we'…

Lol, "it didn't do it... and if it did it didn't mean it... and if it meant it it surely can't mean it now." This is unserious.

Re: The hidden cost of AI coding

#105

Post by th0ma5 » Thu, Apr 24, 2025, 6:12 AM UTC

simonw wrote: post #21

pdimitar wrote: post #17

I don't know man, maybe prompt most of your work, eyeball it and verify it rigorously (which if you cannot do, you should absolutely never touch an LLM!), run a script to commit and push after 3 hours and then... work on whatever code makes you happy without using an LLM? Let's stop pretending or denying it: most of us would delegate our work code to somebody else or something else if we could. Still, prompting LLMs…

> "verify it rigorously (which if you cannot do, you should absolutely never touch an LLM!)" 100% this.

You have an automation bias. "Surely this thing knows more than me it must be right." and there is no reason to believe that, but you will.

Re: The hidden cost of AI coding

#106

Post by gotimo » Thu, Apr 24, 2025, 6:22 AM UTC

th0ma5 wrote: post #104

simonw wrote: post #72

Earlier quoted context omitted.

How long ago was this? I'd be surprised to see Claude 3.7 Sonnet make a mistake of this nature. Either way, when a model starts making dumb mistakes like that these days I start a fresh conversation (to blow away all of the bad tokens in the current one), either with that model or another one. I often switch from Claude 3.7 Sonnet to o3 or o4-mini these days. I paste in the most recent "good" version of the thing we'…

Lol, "it didn't do it... and if it did it didn't mean it... and if it meant it it surely can't mean it now." This is unserious.

this is the rhetoric that you will see replied to effectively any negative experience with LLMs in programming.

Re: The hidden cost of AI coding

#107

Post by simonw » Thu, Apr 24, 2025, 6:30 AM UTC

th0ma5 wrote: post #104

simonw wrote: post #72

Earlier quoted context omitted.

How long ago was this? I'd be surprised to see Claude 3.7 Sonnet make a mistake of this nature. Either way, when a model starts making dumb mistakes like that these days I start a fresh conversation (to blow away all of the bad tokens in the current one), either with that model or another one. I often switch from Claude 3.7 Sonnet to o3 or o4-mini these days. I paste in the most recent "good" version of the thing we'…

Lol, "it didn't do it... and if it did it didn't mean it... and if it meant it it surely can't mean it now." This is unserious.

A full two thirds of the comment you replied to there were me saying "when these things start to make dumb mistakes here are the steps I take to fix the problem".

Re: The hidden cost of AI coding

#108

Post by Kiro » Thu, Apr 24, 2025, 6:38 AM UTC

Can't relate at all. I've never had so much fun programming as I have now. All the boring and tedious parts are gone and I can finally focus on the code I love to write.

Re: The hidden cost of AI coding

#109

Post by NineWillows » Thu, Apr 24, 2025, 6:39 AM UTC

FuckButtons wrote: post #100

pdimitar wrote: post #17

I don't know man, maybe prompt most of your work, eyeball it and verify it rigorously (which if you cannot do, you should absolutely never touch an LLM!), run a script to commit and push after 3 hours and then... work on whatever code makes you happy without using an LLM? Let's stop pretending or denying it: most of us would delegate our work code to somebody else or something else if we could. Still, prompting LLMs…

> Let's stop pretending or denying it: most of us would delegate our work code to somebody else or something else if we could. Hard disagree, I get to hyperfocus on making magical things that surprise and delight me every day.

Nice. I've got a whole lot of magical things that I need built for my day job. Want to connect so I can hand the work over to you? I'll still collect the paychecks, but you can have the joy. :)

Re: The hidden cost of AI coding

#110

Post by jaggederest » Thu, Apr 24, 2025, 6:41 AM UTC

rozap wrote: post #76

tptacek wrote: post #63

Earlier quoted context omitted.

The output of the LLM is probabilistic. The code you actually commit or merge is not.

i'm just vibing though, maybe i merge, maybe i don't, based on the vibes

That sounds like a lot of work, better ask a LLM whether to merge.