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

331–340 of 475 posts

Re: The hidden cost of AI coding

#331

Post by ThrowawayTestr »

skydhash wrote: post #224
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.

That comment makes me deeply suspicious about your debugging skills. And the formatting of your code.

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.

Re: The hidden cost of AI coding

#332

Post by elliotbnvl »

bluefirebrand wrote: post #305
_heimdall wrote: post #258

Earlier quoted context omitted.

Where do you draw that line though? If you're talking about a person using an LLM, or some other ML system, to help generate their music then the LLM is really just a tool for that person. I can't run 80 mph but I can drive a car that fast, its my tool to get the job done. Should I not be allowed to do that professionally if I'm not actually the one achieving that speed or carrying capacity? Personally my concerns wi…

> I can't run 80 mph but I can drive a car that fast If you drive a car 80mph you don't get to claim you are a good runner Similarly if you use an LLM to generate 10k lines of code, you don't get to claim you are a good programmer Regardless of the outcome being the "same"

You do get to claim that you’re a good getting-places-er, though, which is the only point of commercial programming.

Re: The hidden cost of AI coding

#334

Post by hooverd »

Workaccount2 wrote: post #273
yapyap wrote: post #246

Earlier quoted context omitted.

> On the other hand, I know people that want to jump straight to the end result. They have some melody or idea in their head, and they just want to generate some song that revolves around that idea. I don't really look down on those people, even though the snobs might argue that they're not "real musicians". I don't understand them, but that's not really something I have to understand either. So if someone generates…

People who can't spin pottery shouldn't be allowed to have bowls, especially mass produced by machine ones. I understand your point, but I think it is ultimately rooted in a romantic view of the world, rather than the practical truth we live in. We all live a life completely inundated with things we have no expertise in, available to us at almost trivial cost. In fact it is so prevalent that just about everyone takes…

Sure, but they also shouldn't claim they're potters because they went to Pottery Barn.

Re: The hidden cost of AI coding

#335

Post by bluefirebrand »

elliotbnvl wrote: post #332
bluefirebrand wrote: post #305

Earlier quoted context omitted.

> I can't run 80 mph but I can drive a car that fast If you drive a car 80mph you don't get to claim you are a good runner Similarly if you use an LLM to generate 10k lines of code, you don't get to claim you are a good programmer Regardless of the outcome being the "same"

You do get to claim that you’re a good getting-places-er, though, which is the only point of commercial programming.

Project Managers will tell you that "getting to a place" is the goal

Then you get to the place and they say "now load all of the things in the garage into the truck"

But oops. You didn't bring a truck, because all they told you was "please be at this address at this time", with no mention of needing a truck

My point is that the purpose of commercial programming is not usually just to get to the goal

Often the purpose of commercial programming is to create a foundation that can be extended to meet other goals later, that you may not even be remotely aware of right now

If your foundation is a vibe coded mess that no one understands, you are going to wind up screwed

And yes, part of being a good programmer includes being aware of this

Re: The hidden cost of AI coding

#336

Post by CrimsonRain »

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 are always not what he wants. It comes down to a combination of him not understanding how to guide the LLMs to correct direction and using a language/framework (he's not familiar with) he can't judge the LLMs output. It is really important to know what you want, be able to describe it in short points (but important points). Points that you know ai will mess up if you don't specify. And also be able to figure out which direction the ai is heading with the solution and correct it EARLY rather than later. Not overloading context/memory with unnecessary things. Focusing on key areas to improve and much more. I'm using AI to get solutions done that I can definitely do myself but it'll take a certain amount of time to hunt down all documentation, API/lib calls etc. With AI, 1/10th time is enough.

I've had massive success with java, js/TS, html css, go, rust, python, bitbucket pipelines/GitHub actions, cdk, docker compose, SQL, flutter/dart, swift etc.

Re: The hidden cost of AI coding

#337

Post by 6747636484 »

pdimitar wrote: post #216
codr7 wrote: post #41

Earlier quoted context omitted.

Exactly, how are you supposed to verify anything when you don't have any skills left beyond prompting.

You don't. That's why you don't use an LLM most of the time. I was talking about cases where either the tasks were too boring or required an expertise that I didn't have at the time. Thought it was obvious.

> or required an expertise that I didn't have at the time

How do you verify code that you don't have the expertise to write on your own?

Re: The hidden cost of AI coding

#338

Post by randcraw »

TrackerFF wrote: post #185

Some people love programming, for the sake of programming itself. They love the CS theory, they love the tooling, they love most everything about it. Other people see all that as an means to an end - and find no joy from the technical aspect of creating something. They're more interested in the end result / product, rather than the process itself. I think that if you're in group A, it can be difficult to understand g…

Some people like to play a musical instrument, others to compose music. Those who play range from classicists, who have limited ability to improvise or interpret, to popular or jazz, or composition, where creativity and subtle expression is the life blood of the work.

Programming is similar to music. (A great many software innovators in the 70s and 80s had musical roots). But AI prunes away all the creativity and stylistic expression from the composition and the performance when designing and building software, reducing the enterprise to mere specification -- as if the libretto of the opera were merely an outline, and even that was based on Cliff Notes.

The case for using AI to code is driven strictly by economics and speed. Stylistically and creatively, AI is a no-brainer.

Re: The hidden cost of AI coding

#339

Post by chw9e »

The things I'm usually tabbing through in cursor are not the things that make me feel a lot of enjoyment in your work. The things that are most enjoyable are usually the system level design aspects, the refactorings to make things work better. These you can brainstorm with AI, but cannot delegate to AI today.

The rest is glorified boilerplate that I find usually saps me of my energy, not gives me energy. I'm a fan of anything that can help me skip over that and get to the more enjoyable work.

Re: The hidden cost of AI coding

#340

Post by dgs_sgd »

Workaccount2 wrote: post #281
clbrmbr wrote: post #204

I have actually had some really great flow evenings lately, the likes of which I have not enjoyed in many years, precisely because of AI-assisted coding. The trick is to break the task down in to components that are of moderate complexity so that the AI can handle them (Gemini 2.5 Pro one-shots), and keep your mind on the high-level design which today's AI cannot coordinate. What helps me is to think of it like I'm a…

I'm a classic engineer, so lots of experience with systems and breaking down problems, but probably Having LLMs like 2.5 now are total game changers. I can basically flow chart a program and have Gemini manifest it. I can break up the program into modules and keep spinning up new instances when context gets too full. The program I am currently working on is up to ~5500 LOC, probably across 10ish 2.5 instances. It's b…

Only 150 hours of programming in 15 years? Are you in more of an Architect / Tech Lead role than an IC (individual contributor) role?
Post reply on HN