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

The hidden cost of AI coding

terriblesoftware.org

Post reply on HN
Print view View original

411–420 of 475 posts

Re: The hidden cost of AI coding

#411

Post by ThrowawayTestr »

skydhash wrote: post #346
ThrowawayTestr wrote: post #331

Earlier quoted context omitted.

I write code to solve problems for my own use or for my hobby electronics projects. Asking chatgpt to write a script is faster than reading the documentation of some python library. Just last week it wrote me a whole application and gui to open a webpage at a specific time. Yeah it breaks after the first trigger but it works for what I need.

And that's OK! I'm not trying to gatekeeping anyone from the title of coder or programmer. But what is fine for quick small scripts and throwaway code can be quite bad even for smallish projects. If you're trying to solve a problem in a systematic way, there's a lot of concerns that pertain to the durability of the solution. There's a lot of literature about these concerns and a lot of methodologies to alleviate them…

>that could have been done with systemd timers

I could have used Windows Task Scheduler but having a nice gui with a custom icon is much more pleasant to use.

Re: The hidden cost of AI coding

#412

Post by ThrowawayTestr »

nairadithya wrote: post #254
ThrowawayTestr wrote: post #192

Earlier quoted context omitted.

I like solving problems but I hate coding. Wasting 20 minutes because you forgot a semicolon or something is not fun. AI let's me focus on the problem and not bother with the tedious coding bit.

This doesn't even make sense, forgetting a semicolon is immediately caught by the compiler. What positive benefits does AI provide here?

By knowing about libraries that I don't have to read and learn and being able to glue them together to quickly accomplish my task.

Re: The hidden cost of AI coding

#413

Post by amiantos »

vendiddy wrote: post #263
ang_cire wrote: post #133

This comment section really shows the stark divide between people who love coding and thus hate AI, and people who hate coding and thus love AI. Honestly, I suspect the people who would prefer to have someone or something else do their coding, are probably the devs who are already outputting the worst code right now.

I love coding but I also love AI. I don't know if I'm a minority but I'd like to think there are a lot of folks like me out there. You can compare it to someone who is writing assembly code and now they've been introduced to C. They were happy writing assembly but now they're thrilled they can write things more quickly. Sure, AI could lead us to write buggier code. Sure, AI could make us dumber because we just have A…

We're the silent majority, I'm pretty sure. If you love coding, you probably love technology, and if you love technology, you probably love AI, which is inarguably the most interesting tech advancement in this decade.

The others, who are not like us? They've got other priorities. If you hate coding but you love AI, you're probably into software engineering because of the money, not love of technology. If you love coding and you hate AI, you're probably more committed to some sort of ideology than you are the love of technology. If you hate coding and you hate AI, well, I hope you throw your cellphone into the river and find a nice cabin in the woods somewhere to hide in.

Re: The hidden cost of AI coding

#414

Post by merb »

knlam wrote: post #322
CopyOnWrite wrote: post #285

Most comments here surprise me: I am using Githubs Copilot / ChatGPT 4.0 at work with a code base which is mostly implements a basic CRUD service... and outside of small/trivial example (where the generated code is mostly okay), prompting is more often than not a total waste of time. Now, I wonder if I am just totally unable to write/refine good prompts for the LLM (as it works for smaller samples, I hope I am not to…

Copilot is just plain bad. The result is day and night compare with cursor + gemini 2.5 (of course with good prompting)

Copilot can also use Gemini 2.5 and sonnet 3.7.

Re: The hidden cost of AI coding

#415

Post by degamad »

godelski wrote: post #403
scarface_74 wrote: post #401

Earlier quoted context omitted.

Every company does this. You don’t invest in your future these days by investing in a pipeline of “talent” knowing that the average tenure of a software developer is 3 years and at any time an employee can leave. You have processes that outlive people. Companies don’t care about society - they care about their bottom line. They aren’t there to make society as a whole better If you want a society of well trained softw…

> You don’t invest in your future ... the average tenure of a software developer is 3 years and at any time an employee can leave. Well this is a 2 stage problem and I think the response is bad for multiple reasons. 1) Tragedy of the Commons: If we all act like this, then no one gets invested in. If we all invest in our employees then when they leave another company gets the rewards. That's still true when "we" are t…

I agree with you, but I think that there's one area of the argument that is worth figuring out how to strengthen.

> If we all invest in our employees then when they leave another company gets the rewards. That's still true when "we" are the "other company". You still benefit regardless. Under the condition that most companies (or rather at least the big companies) collude in this way. They have good reason to as coalitions maximize utility for all parties involved.

You are right that in a world where most companies collude in this manner, we all benefit.

However, in that world, a company that chooses not to contribute (by investing in inexperienced employees) also has access to the same benefits (trained employees).

Furthermore, they can use the money saved by not contributing to inflate the value of the trained employees (offering them higher pay), so they have an incentive to not contribute. This doubly deprives the rest of us of some of that benefit.

How do we adjust the incentives so that bad actors are not motivated to cheat the system?

(In case it seems like a familiar scenario, yes, this is similar to playing Iterated Prisoners' Dilemma with the rest of the world.)

Re: The hidden cost of AI coding

#416

Post by th0ma5 »

simonw wrote: post #130
th0ma5 wrote: post #105

Earlier quoted context omitted.

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.

How did you get there from me agreeing 100% with someone who said that you should be ready to verify everything an LLM does for you and if you're not willing to do that you shouldn't use them at all? Do you ever read my comments, or do you just imagine what I might have said and reply to that?

There's simply no way to verify everything that comes out of these things. Otherwise why use it? You also can't possibly truly know if you know more about a topic since by definition the models know more than you. This is automation bias. Do you not know the problems with even verifying or watching machines? This is a core part of the discussion of self driving vehicles. I guess I assumed you knew stuff about the field of AI!

Re: The hidden cost of AI coding

#417

Post by th0ma5 »

simonw wrote: post #107
th0ma5 wrote: post #104

Earlier quoted context omitted.

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".

Not actual knowledge but adages ! Lol "here is my magic potion that I can't tell you how it differs from the other magic potion!" That is not fixing anything. That's trying to string people along and insert yourself otherwise you'd be able to point so some kind of empirical documented experience as to why one vendor is better than the other or why older models have the problem but newer ones don't, and more importantly assurances that future models or even future unannounced changes to the models you mention will even work the same as they do today. What knowledge are you actually imparting other than "I think this is a road you could try." Thanks.

Re: The hidden cost of AI coding

#418

Post by th0ma5 »

gotimo wrote: post #106
th0ma5 wrote: post #104

Earlier quoted context omitted.

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.

Yeah I'm starting to think they aren't aware of the shell game in their own rhetoric. If nothing can ever be wrong then nothing is right either in that worldview.

Re: The hidden cost of AI coding

#419

Post by thi2 »

CopyOnWrite wrote: post #285

Most comments here surprise me: I am using Githubs Copilot / ChatGPT 4.0 at work with a code base which is mostly implements a basic CRUD service... and outside of small/trivial example (where the generated code is mostly okay), prompting is more often than not a total waste of time. Now, I wonder if I am just totally unable to write/refine good prompts for the LLM (as it works for smaller samples, I hope I am not to…

My employer gives me access to Jetbrains AI, I work on a Vue Frontend with a Kotlin Spring Boot backend.

The codebase is not too old and has grown without too much technical debt, with complex prompts I never had decent success. Its usefull for quick "what does this do" checks but any real functionality seems to be lacking.

Maybe I'm not refining my prompts good enough but doing so would take longer than implementing it myself.

Recently I tried Jetbrains Junie, which acts like Claude if I understand it correctly.

I had a really refined prompt, ran it three times with adjustments and fine tuning but the result was still lacking. So I tossed it and wrote it myself. But watching the machine nearly getting it right was still impressive.

Re: The hidden cost of AI coding

#420

Post by thi2 »

CrimsonRain wrote: post #336
CopyOnWrite wrote: post #285

Most comments here surprise me: I am using Githubs Copilot / ChatGPT 4.0 at work with a code base which is mostly implements a basic CRUD service... and outside of small/trivial example (where the generated code is mostly okay), prompting is more often than not a total waste of time. Now, I wonder if I am just totally unable to write/refine good prompts for the LLM (as it works for smaller samples, I hope I am not to…

You are just bad with prompting or working with very obscure language/framework or bad coding pattern or all of it. I had a talk with a seasoned engineer who has been coding for 50 years and has created many amazing things over lifetime about him having really bad results with AI tools I suggested for him. When I use AI for the same purposes in the same repo he's working on, it works nicely. When he does it, results…

> You are just bad with prompting or working with very obscure language/framework or bad coding pattern or all of it

You just described every existing legacy project^^

Post reply on HN