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

Survey: a third of senior developers say over half their code is AI-generated

fastly.com

Post reply on HN
Print view View original

321–330 of 388 posts

Re: Survey: a third of senior developers say over half their code is AI-generated

#321

Post by jennyholzer »

chillingeffect wrote: post #281
kelnos wrote: post #271

Earlier quoted context omitted.

I hate to play the "you're holding it wrong" card, but when I started, I had more or less the same experience. Eventually you start to learn how to better talk to it in order to get better results. Something I've found useful with Claude Code is that it works a lot better if I give it many small tasks to perform to eventually get the big thing done, rather than just dumping the big thing in its lap. You can do this i…

Similar here. AI works much better as a consultant than as a developer. I ask it all kinds of things I have suspicions and intuitions about and it provides clarity and examples. It's great for subroutines. Trying to make full programs is just too large of a space. It's difficult to communicate all the implicit requirements.

People who consistently consult LLMs for product direction or software feature design overwhelmingly appear to me as willfully ignorant dullards.

I mean it's even further than willful ignorance. It's delight in one's own ignorance.

Re: Survey: a third of senior developers say over half their code is AI-generated

#323

Post by kaishiro »

adw wrote: post #187
kaishiro wrote: post #135

Jesus, that's a staggering figure to me coming from senior developers. I guess I'm the odd one out here, but ChatGPT is nothing more than an index of Stack Overflow (and friends) for me. It's essentially replaced Googling, but once I get the answer I need I'm still just slinging code like an asshole. Copying the output wholesale from any of these LLMs just seems crazy to me.

If you’re using ChatGPT directly for work then I believe that you are doing it so profoundly wrong, at this point, that you’re going to make really incorrect assumptions. As we have all observed, the models get things wrong, and if you’re wrong 5% of the time, then ten edits in you’re at 60-40. So you need to run them in a loop where they’re constantly sanity checking themselves—-linting, styling, typing and testing.…

Yes, I was using "ChatGPT" colloquially. I’ve tried Claude Code, Copilot - I currently have Gemini running though madox2's vim-ai plug - and a few of the others, but I’ve never personally seen the kind of 10x productivity gains some people here talk about. In my experience, it’s typically been quicker to just write the code myself than to wrangle with the model’s output, iterate, and debug. That’s not to say the tools are useless - like I said I think they're great at exposing docs that are disparate or obtuse (looking at you Google) but for actual problem-solving and building, they’ve unfortunately rarely felt like a net win.

I'm sure you're correct that a lot of this comes down to workflow and domain - in mine, the overhead of prompting, reviewing, and correcting usually outweighs the benefits. Of course, as always, this is just one asshole's opinion!

Re: Survey: a third of senior developers say over half their code is AI-generated

#324

Post by fluidcruft »

Rochus wrote: post #253
oliwary wrote: post #241

Earlier quoted context omitted.

Hey! I would encourage you to try our Claude code instead, which is also part of your subscription. It's a CLI that takes care of many of the issues you encountered, as it works directly on the code files in a directory. No more copy pasting or unscrambling results. Likewise, it can run commands itself to e.g. compile or even test code.

I'm working on old hardware and not-recent Linux and compiler versions, and I have no confidence yet in allowing AI direct (write) access to my repositories. Instead I provided Claude with the source code of a transpiler to C (one file) which is known to work, uses the same IR as the new code generators were supposed to use. This is a controlled experiment with a clear and complete input and clear expectations and sp…

claude-code asks you to allow it to do anything before it does them. Once you start trusting it and get comfortable with its behavior it gets annoying being prompted all the time, so you can whitelist specific commands it wants to run. You can also interactively toggle into (and out of) "accept changes without asking" mode.

(It wasn't clear to me that I would be able to toggle out of accept changes mode, so I resisted for a loooooong time. But turns out it's just a toggle on/off and can be changed in real-time as it's chugging along. There's also a planning state but haven't looked into that yet)

It always asks before running commands unless you whitelist them. I have whitelisted running testsuites and linters, for example so it can iterate on those corners with minimal interaction. I have had to learn to let it go ahead and make small obvious mistakes rather than intervene immediately because the linters and tests will catch them and Claude will diagnose the failure and fix them at that point.

Anyway I took a small toy project and used that to get a feel for claude-code. In my experience using the /init command to create CLAUDE.md (or asking Claude to interview you to create it) is vital for consistent behavior.

I haven't had good "vibe" experiences yet. Mostly I know what I want to do and just basically delegate implementation. Some things that have worked well for me is to ask Claude to propose a few ways to improve or implement a feature. It's come up with a few things I hadn't thought of that way.

Anyway, claude-code was very good at slowly and incrementally earning my trust. I resisted trying it because I expected it would just run hogwild doing bewildering things, but that's not what it does. It tends to be a bit of an asskisser in it's communication style in a way that would annoy me if it were a real person. But I've managed to look past that.

Re: Survey: a third of senior developers say over half their code is AI-generated

#325

Post by lyu07282 »

matt3210 wrote: post #108

Brute forcing a problem by writing more lines with an LLM instead of designing better code is a step the wrong direction

better code == less code? In my mind that would be highly succinct purely functional code in scala or haskell. Those really allow you to "compress" code down to its barest essential domain logic? Perhaps the future is writing highly domain specific DSLs and have the LLM generate the runtime for it.

Re: Survey: a third of senior developers say over half their code is AI-generated

#326

Post by fragmede »

jennyholzer wrote: post #243
quantiq wrote: post #214

Earlier quoted context omitted.

Yeah, I'm not putting stock in this at all. The methodology of this survey seems dubious.

30% of the articles on this forum are covert LLM advertising

Every single last link here is some form of an advertisement, why single out LLM-related ads?

Re: Survey: a third of senior developers say over half their code is AI-generated

#327

Post by gommm »

Rochus wrote: post #299
stavros wrote: post #282

Earlier quoted context omitted.

I use Claude Code with the Max plan, and the experience isn't far off from what you describe. You still need to understand the system and review the implementation, because it makes many mistakes. That's not the part it saves me time in, it saves me time in looking up the documentation. Other than that, it might be slower, because the larger the code change is, the more time I need to spend reviewing, and past a poin…

> it saves me time in looking up the documentation I have a Perplexity subscription which I heavily use for such purpose, just asking how something works or should be used, with a response just on the point and with examples. Very useful indeed. Perplexity gives me access to Claude Sonnet 4 w/o Thinking which I consider great models, and it can also generate decent code. My intention was to find out how good the rece…

I end up using Perplexity a lot too, especially when I'm doing something unfamiliar. It's also a good way to quickly find out what are best practices for a given framework/language I'm not that familiar with (I usually ask it to link to examples in the wild and it find opensource projects illustrating those points)

Re: Survey: a third of senior developers say over half their code is AI-generated

#329

Post by paulcole »

cc62cf4a4f20 wrote: post #307

I've been coding professionally for almost 30 years. I use Claude Code heavily, even for larger features. To get that to work half-decent, you have to take on a PM/Tech-lead role, you're no longer a senior engineer. For large pieces of work, I will iterate with CC to generate a feature spec. It's usually pretty good at getting you most of the way there first shot and then either have it tweak things or manually do so…

> To get that to work half-decent, you have to take on a PM/Tech-lead role, you're no longer a senior engineer.

But you’re saying it can be half-decent?

The problem is that about 75% of HN commenters have their identities tightly wound up in being a (genuflect) senior engineer and putting down PM/tech-lead type roles.

They’ll do anything to avoid losing that identity including writing non-stop about how bad AI code is. There’s an Upton Sinclair quote that fits the situation quite nicely.

Re: Survey: a third of senior developers say over half their code is AI-generated

#330

Post by aleph_minus_one »

LinXitoW wrote: post #236
darkwater wrote: post #223

Earlier quoted context omitted.

IMO it's different. That's why I brought the e-bike similitude: climbing even mild mountains or hills with your own legs will actually make your legs, heart and lungs stronger in the process. So you get both the wonderful views (building the house or delivering the software) but also you get improved health (keeping your mind trained on both high level thinking and low level implementation vs high level only). We mig…

Ironically, e-bikes, at least in the EU, are having the exact opposite effect. More people that don't normally ride bikes are using e-bikes to get about. The motor functions not as a replacement, but as a force multiplier. It also makes "experimenting" easier, because the motor can make up for any mistakes or wrong turns. Caveat: In the EU, an e-bike REQUIRES some physical effort any time for the motor to run. Thrott…

> Ironically, e-bikes, at least in the EU, are having the exact opposite effect. More people that don't normally ride bikes are using e-bikes to get about.

At least in Germany people rather joke that the moment e-bikes became popular, people began to realize that they suddenly became too unathletic to be capable of pedaling a bicycle. I know of no person who uses an e-bike who did not ride an ordinary bicycle before.

> In the EU, an e-bike REQUIRES some physical effort any time for the motor to run.

The motor must shut off when 25 km/h is reached - which is basically the speed that a trained cyclist can easily attain. So because of this red tape stuff, e-bikes are considered to be useless and expensive by cyclists who are not couch potatoes.

Post reply on HN