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

271–280 of 388 posts

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

#271

Post by kelnos »

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 interactively (prompt, output, prompt, output, prompt, output...) or by writing a big markdown file with the steps to build it laid out.

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

#272

Post by kelnos »

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…

> I have no confidence yet in allowing AI direct (write) access to my repositories.

You don't need to give it write access to your repositories, just to a source tree.

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

#273

Post by kelnos »

jennyholzer wrote: post #267
actionfromafar wrote: post #256

Earlier quoted context omitted.

Wow, shots fired! Would you add something to that?

i spend a lot of time fixing unacceptably poor code that LLM platforms have tricked human coworkers into finding adequate. my coworkers are increasingly ignorant about the software products they work on. LLM-informed software development is organizationally poisonous. Businesses selling LLM coding tools occupy the same place in my mind as drug dealers.

Feels like that's more of a problem with the competence of your coworkers than with the LLM. The LLM is just exposing how bad they are.

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

#274

Post by darkwater »

closewith wrote: post #231
AlecSchueler wrote: post #227

Earlier quoted context omitted.

> The vast majority of developers aren't summitting beautiful mountains I'm not sure you're approaching this metaphor the right away. The point is that coding manually is great cognitive exercise which keeps the mind sharp for doing the beautiful stuff. > The trades destroy human bodies over time and leads to awful health outcomes. Again, you're maybe being too literal and missing the point. No one is destroying thei…

> I'm not sure you're approaching this metaphor the right away. The point is that coding manually is great cognitive exercise which keeps the mind sharp for doing the beautiful stuff. No, I'm challenging the metaphor. Working the trades isn't exercise - it's a grind that wears people out. > Again, you're maybe being too literal and missing the point. No one is destroying their minds by coding. Exercise is good. We ac…

> No, I'm challenging the metaphor. Working the trades isn't exercise - it's a grind that wears people out.

If your job is just grinding out code in a stressful and soul-crushing manner, the issue lies elsewhere. You will be soon either grinding out prompts to create software you don't even understand anymore or you will be replaced by an agent.

And by no way I'm implying you are part of the issue.

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

#276

Post by Rochus »

jennyholzer wrote: post #269
Rochus wrote: post #260

Earlier quoted context omitted.

Do you mean Claude code should fail? Why?

[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).

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

#277

Post by Rochus »

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…

I just tried to use it for something I consider it to provide the most benefit (for my case). Being able to fully delegate a complicated (and boring) part to a machine would give me more time for the things I'm really interested in. I think we are on the right track in this regard, but we still have a long way to go.

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

#278

Post by cpursley »

victorbjorklund wrote: post #184
yodsanklai wrote: post #65

Seems about right for me (older developer at a big tech company). But we need to define what it means that the code is AI-generated. In my case, I typically know how I want the code to look like, and I'm writing a prompt to tell the agent to do it. The AI doesn't solve any problem, it just does the typing and helps with syntax. I'm not even sure I'm ultimately more productive.

100%. My instructions are often pretty exact "i want a genserver that fetches the data every X sec and updates Y if new data"

Yeah, Claude has gotten much better with Elixir. I think too many people expect one-shot miracles, but you have to guide it along like you would a junior, including directing it towards the proper context.

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

#279

Post by danielvaughn »

mshanu wrote: post #235
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 am pleasantly surprised when it is able to figure out the root cause of some bugs which at times require a lot of mental energy

Exactly

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

#280

Post by torben-friis »

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…

On Claude you specifically accept any attempt to use a terminal command (optionally whitelisting) so there’s no risk that it will push force something or whatever. You can also whitelist with granularity, for example to enable it to use git to view git logs but not commit.

You can just let it work, see what’s uncommitted after it’s over, and get rid of the result if you don’t like it.

Post reply on HN