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

291–300 of 388 posts

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

#291

Post by kasey_junk »

deadbabe wrote: post #290
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…

It’d be nice if we could “pipe” prompts directly similar to how we pipe multiple Unix commands to eventually get what we really want. Then we can give someone that entire string of prompts as a repeatable recipe.

You can send prompts on the command line to Claude, I typically save prompts in the repo. But note it won’t produce deterministic output.

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

#292

Post by closewith »

AlecSchueler wrote: post #285
closewith wrote: post #268

Earlier quoted context omitted.

We have plentiful evidence and studies on the effect of even moderate day-long cognitive work has on cognitive ability and on the effect of stress. This is so well-founded that I do not have to provide individual sources - it is the current global accepted reality. I wouldn't provide sources for the effect of CO2 emissions on the climate or gravity, either. However, the opposite is not true. If you have evidence that…

Again you're conflating things and are now also moving goalposts (overwork->moderate work) and asking me for very precise kinds of studies while refusing to even point towards the basis for your own claims. On top of this you're implying that I'm some kind of lunatic by associating my questions with climate denial. It's clear that you're more interested in "winning" than actually have a reasonable discussion so goodb…

Come on. We’ve had decades of occupational-health research on cognitive load, stress, and hours. The pattern is clear. Higher demands and longer hours raise depression risk. Lab and field work shows day-long cognitive tasks produce measurable fatigue, decision drift, and brain chemistry changes. These are universally accepted.

And yet, you now want me to source individual studies on those effects in a HN thread? Yes, in this instance you are approaching flat-earth/climate-change-denial levels of discourse. Reducing cognitive load is an unambiguous good.

If you think routine coding itself improves brain health or cognitive ability, produce the studies showing as you demanded from me, because that is a controversial claim. Or you can crash out of the conversation.

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

#293

Post by blks »

Rochus wrote: post #276
jennyholzer wrote: post #269

Earlier quoted context omitted.

[flagged]

In what specific programming language/toolchain/technology is your experience? Why do you think that "everybody can tell that chat gpt wrote your code"? Meanwhile I looked at a lot of LLM generated code in different languages, and I wouldn't generally subscribe to your statement. And you still didn't explain why Claude should fail. I think it is rather an advantage (when it reliably works in future).

I can tell when my coworkers Go code is generated by an llm. I hate it very much.

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

#294

Post by mattacular »

stavros wrote: post #282
Rochus wrote: post #253

Earlier quoted context omitted.

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…

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…

> The best way I've found is to have it write small functions, and then I tell it to compose them together.

Pretty much how I code without AI, except making my brain break the problem down into small functions and expressing them in code rather than as a chat.

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

#295

Post by blks »

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…

Wow, 30 minutes to rename functions and tests? I wonder how much energy and water that llm wasted for something that any lsp supporting editor can do in a second.

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

#296

Post by blks »

danielvaughn wrote: post #254
mnky9800n wrote: post #233

Earlier quoted context omitted.

Do you feel like you lack mental energy at 40? I do not feel any different from 30. I think the main difference between 30 and 40 is I am much more efficient at doing things and therefore am able to do more.

I do, but I’m not sure it’s age related. Ever since 2020, it feels like my physical and mental energy has been on a downward trajectory. I feel like I’ve lost several IQ points. What’s interesting is that I’ve heard the same from a lot of people. Not sure what the root cause is, but I do need to take better care of myself.

This could be long COVID.

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

#297

Post by mnky9800n »

actionfromafar wrote: post #261
danielvaughn wrote: post #254

Earlier quoted context omitted.

I do, but I’m not sure it’s age related. Ever since 2020, it feels like my physical and mental energy has been on a downward trajectory. I feel like I’ve lost several IQ points. What’s interesting is that I’ve heard the same from a lot of people. Not sure what the root cause is, but I do need to take better care of myself.

I think it may be just age and stress. Also apparently even pretty mild Covid could cause some vasculatory damage? On the flip side physical excercise can cause even very old people to improve radically.

Also creatine is good for everyone for mind and body.

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

#298

Post by jjani »

LinXitoW wrote: post #237
ottah wrote: post #94

Earlier quoted context omitted.

Don't you have to keep dismissing incorrect auto-complete? For me I have a particular idea in mind, and I find auto-complete to be incredibly annoying. It breaks flow. It has no idea my intention, but very eagerly provides suggestions I have to stop and swat away.

My experience with Supermaven has been close to perfect. Imho, the smaller the suggestion, the better it generally is. 99% of supermaven suggestions are just one line.

For those about to look it up: Supermaven is dead.

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

#299

Post by Rochus »

stavros wrote: post #282
Rochus wrote: post #253

Earlier quoted context omitted.

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…

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 recent Claude Opus is in comparison and how much of my work I'm able to delegate. Personally I much prefer the user interface features, performance and availability of Perplexity to Claude.ai.

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

#300

Post by JeremyNT »

kelnos wrote: post #271
Rochus wrote: post #228

The article claims, that senior developers with over 10 years of experience are more than twice as likely to heavily rely on AI tools compared to their junior counterparts. No p-values or statistical significance tests are reported in either The Register article or Fastly's original blog post. I have over 30 years of experience and recently used Claude Opus 4.1 (via browser and claude.ai) to generate an ECMA-335 and…

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…

While this matches my experience, it's worth mentioning thar the act of breaking a task up into the correct chunk size and describing it in English is itself a non trivial task which can be more time consuming than simply writing the actual code.

The fact that it works is amazing, but I'm less convinced that it's enhancing my productivity.

(I think they real productivity boost for me is if I still write the code and have the assistant write test coverage based on diffs, which is trivial to prompt for good results)

Post reply on HN