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

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

#351

Post by Rochus » Mon, Sep 01, 2025, 5:27 PM UTC

epolanski wrote: post #320

Rochus wrote: post #305

Earlier quoted context omitted.

I'm pretty good at prompting and I successfully use Perplexity (mostly with Claude Sonnet 4) to develop concepts, sometimes with the same session expanded over several days. I think the user interface is much superior over Claude.ai. My hope was that the newer Claude Opus 4.1 would be much better in solving complicated coding tasks, which doesn't seem to be the case. For this I had to subscribe to claude.ai. Actually…

I'll be more detailed in my second reply. 1) Your original post asks a lot if not too much out the LLM, the expectation you have is too big, to the point that to get anywhere near decent results you need a super detailed prompt (if not several spec documents) and your conclusion stands true: it might be faster to just do it manually. That's the state of LLMs as of today. Your post neither hints at such detailed and l…

I don't know where your confidence or assumptions come from. Do you work for Anthropic? My prompts for the code generators included an 1.2kLOC code file plus detailed instructions (as described elsewhere), with more details during the session. So I don't think your points apply.

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

#352

Post by lovestaco » Mon, Sep 01, 2025, 5:31 PM UTC

cschneid wrote: post #170

danielvaughn wrote: post #79

Earlier quoted context omitted.

Yeah I’m still not more productive. Maybe 10% more. But it alleviates a lot of mental energy, which is very nice at the age of 40.

I find AI is most useful at the ancillary extra stuff. Things that I'd never get to myself. Little scripts of course, but more like "it'd be nice to rename this entire feature / db table / tests to better match the words that the business has started to use to discuss it". In the past, that much nitpicky detail just wouldn't have gotten done, my time would have been spent on actual features. But what I just described…

Nice, which reviewer do you use? I was using CodeRabbi now switched to LiveReview.

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

#353

Post by Rochus » Mon, Sep 01, 2025, 5:34 PM UTC

demarq wrote: post #339

jennyholzer wrote: post #251

Earlier quoted context omitted.

as a human being i take it as massive disrespect when another human developer makes me wipe up their AI diarrhea.

What are you replying to

Their inner demons?

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

#354

Post by mgh95 » Mon, Sep 01, 2025, 5:52 PM UTC

imtringued wrote: post #240

mgh95 wrote: post #132

Earlier quoted context omitted.

You should look up intellitest and reshaper test generator. Products exist for this.

Maybe you should have brought that up earlier instead of acting smug and burying the lede? It's also pretty telling that you didn't elaborate this further and kept your comment short. What you should have said is that some parameterized test generators do automated white box testing where they look at your code similar to a fuzzer and try to find the test cases automatically. Your first link is literally just setting…

> Maybe you should have brought that up earlier instead of acting smug and burying the lede? It's also pretty telling that you didn't elaborate this further and kept your comment short.

I thought people were generally competent within the areas they discuss and are aware of the tooling within their preferred ecosystem. I apologize if that is not the case.

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

#355

Post by bluefirebrand » Mon, Sep 01, 2025, 6:30 PM UTC

RianAtheer wrote: post #310

I’m not surprised. AI tools have become such a huge time saver. I use them a lot too, but I still double check everything to keep quality high. I read an article on finance gossips called “The Rise of AI in Banking: Friend or Foe”, and it really put this into perspective. AI’s growth in finance shows how quickly it is reshaping industries, so seeing devs rely on AI for half their code makes total sense. Like in banki…

> as long as we manage trust, ethics, and transparency

Trust, ethics and transparency are at all time lows in every corner of every capitalist industry imo

I don't know how anyone could look at the current state of things and think AI isn't being positioned to gut employment across many industries

Naive, childish and short sighted mentality imo

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

#356

Post by matwood » Mon, Sep 01, 2025, 6:42 PM UTC

cmrdporcupine wrote: post #111

danielvaughn wrote: post #79

Earlier quoted context omitted.

Yeah I’m still not more productive. Maybe 10% more. But it alleviates a lot of mental energy, which is very nice at the age of 40.

Strangely I've found myself more exhausted at the end of the week and I think it's because of the constant supervision necessary to stop Claude from colouring outside the lines when I don't watch it like a hawk. Also I tend to get more done at a time, it makes it easier to get started on "gruntwork" tasks that I would have procrastinated on. Which in turn can lead to burnout quite quickly. I think in the end it's jus…

> Strangely I've found myself more exhausted at the end of the week and I think it's because of the constant supervision necessary to stop Claude from colouring outside the lines when I don't watch it like a hawk.

Welcome to management. Computers and code are easy. People and people wannabes like LLMs are a pain.

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

#357

Post by willhslade » Mon, Sep 01, 2025, 6:42 PM UTC

I know this is late to the party but I think, given that this topic comes up.every day, we should start including statistics in our posts to get a better sense of how AI is working or not for us. I imagine a years of experience / primary language used / tool used / AI positive or negative as a percentile estimate.

Personally for me it's 20 years of experience / Python / Copilot / 85% positive experience.

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

#358

Post by Rochus » Mon, Sep 01, 2025, 7:04 PM UTC

stavros wrote: post #317

Rochus wrote: post #299

Earlier quoted context omitted.

> 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 have both, and Perplexity is much more like a search engine than a chat companion (or at least that's how I use it). I like both, though.

You can select the model. I very much appreciate the Claude Sonnet models which are very good and rational discussion partners, responding to arguments in detail and critically, allowing for the dialectical exploration of complex topics. I have also experimented with other models including ChatGPT, Gemini or Grok, but the resulting discussions were only a fraction as useful (i.e. more optimized towards affirmative feel-good small talk, from my humble point of view).

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

#359

Post by marssaxman » Mon, Sep 01, 2025, 7:05 PM UTC

TheRoque wrote: post #147

marssaxman wrote: post #122

Earlier quoted context omitted.

That's funny. I remember using interactive debuggers all the time back in the '90s, but it's been a long time since I've bothered. Logging, reading, and thinking is just... easier.

Really ? I find myself thinking the opposite. My program always runs in debug mode, and when there's some issue I put a breakpoint, trigger it, and boom I can check what is wrong. I don't need to stop the program, insert a new line to print what i _guess_ is wrong, restart the program from scratch etc. Properly debugging my stack is probably one of the first things I setup because I find it way less tedious. Like, fo…

I imagine that it depends on the kind of software you are working on. I found debuggers helpful back when I was working on interactive GUI programs which had a lot of complex state, built in classic OOP style with lots of objects pointing at each other, but I have not done that sort of thing in a long time. In part, that's because I got seriously into functional programming, which left me with a much more rigorous approach to state transitions; but then I shifted from conventional software into embedded firmware, where you can sometimes stop the microcontroller and use a debugger via JTAG, but it's usually easier to just stream data out over a serial port, or hook an LED up to a spare pin and make it blink. The world doesn't stop even if you want the software to stop, so the utility of a debugger is limited.

After that I went to work for Google, building distributed software running across many machines in a datacenter, and I have no idea how you would hook up a debugger even if you wanted to. It's all logs all the time, there.

By the time that was over, I was thoroughly accustomed to logging, and attaching a debugger had come to seem like a nuisance. Since then I've mostly worked on compilers, or ML pipelines, or both: pure data-processing engines, with no interactivity. If I'm fixing a bug, I'm certainly also writing a regression test about it, which lends itself to a logging-based workflow. I don't mind popping into gdb if that's what would most directly answer my question, but that only happens a couple of times a year.

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

#360

Post by marssaxman » Mon, Sep 01, 2025, 7:23 PM UTC

jennyholzer wrote: post #242

VectorLock wrote: post #84

Earlier quoted context omitted.

Interactive debuggers and printf() are both completely valid and have separate use-cases with some overlap. If you're trying to use, or trying to get people to use, exclusively one, you've got some things to think about.

printf() users in this thread are very proud of their own ignorance

I almost exclusively debug via printf / logging, and I am so stupendously ignorant that I have even written and published a multi-platform interactive debugger, to go with the compiler I also wrote (one of several, but this one was the most successful). Make of that what you will, I suppose.