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

Generative AI coding tools and agents do not work for me

blog.miguelgrinberg.com

Post reply on HN
Print view View original

21–30 of 464 posts

Re: Generative AI coding tools and agents do not work for me

#21

Post by bdamm »

ken47 wrote: post #18
bdamm wrote: post #11

No offense intended, but this is written by a guy who has the spare time to write the blog. I can only assume his problem space is pretty narrow. I'm not sure what his workflow is like, but personally I am interacting with so many different tools, in so many different environments, with so many unique problem sets, that being able to use AIs for error evaluation, and yes, for writing code, has indeed been a game chan…

> rise of IDEs, or Google search, or AWS. None of these things introduced the risk of directly breaking your codebase without very close oversight. If LLMs can surpass that hurdle, then we’ll all be having a different conversation.

This is not the right way to look at it. You don't have to have the LLMs directly coding your work unsupervised to see the enormous power that is there.

And besides, not all LLMs are the same when it comes to breaking existing functions. I've noticed that Claude 3.7 is far better at not breaking things that already work than whatever it is that comes with Cursor by default, for example.

Re: Generative AI coding tools and agents do not work for me

#22

Post by roxolotl »

> But interns learn and get better over time. The time that you spend reviewing code or providing feedback to an intern is not wasted, it is an investment in the future. The intern absorbs the knowledge you share and uses it for new tasks you assign to them later on.

This is the piece that confuses me about the comparison to a junior or an intern. Humans learn about the business, the code, the history of the system. And then they get better. Of course there’s a world where agents can do that, and some of the readme/doc solutions do that but the limitations are still massive and so much time is spent reexplaining the business context.

Re: Generative AI coding tools and agents do not work for me

#23

Post by ed_mercer »

> It takes me at least the same amount of time to review code not written by me than it would take me to write the code myself, if not more.

Hard disagree. It's still way faster to review code than to manually write it. Also the speed at which agents can find files and the right places to add/edit stuff alone is a game changer.

Re: Generative AI coding tools and agents do not work for me

#25

Post by kibibu »

strangescript wrote: post #9

Everyone is still thinking about this problem the wrong way. If you are still running one agent, on one project at a time, yes, its not going to be all that helpful if you are already a fast, solid coder. Run three, run five. Prompt with voice annotation. Run them when normally you need a cognitive break. Run them while you watch netflix on another screen. Have them do TDD. Use an orchestrator. So many more options.…

I have never seen people work harder to dismantle their own industry than software engineers are right now.

Re: Generative AI coding tools and agents do not work for me

#26

Post by skydhash »

royal__ wrote: post #3

I get confused when I see stances like this, because it gives me the sense that maybe people just aren't using coding tools efficiently. 90% of my usage of Copilot is just fancy autocomplete: I know exactly what I want, and as I'm typing out the line of code it finishes it off for me. Or, I have a rough idea of the syntax I need to use a specific package that I use once every few months, and it helps remind me what t…

That usage is the most disruptive for me. With normal intellisense and a library you're familiar with, you can predict the completion and just type normally with minimal interruption. With no completion, I can just touch type and fix the errors after the short burst. But having whole lines pop up break that flow state.

With unfamiliar syntax, I only needs a few minutes and a cheatsheet to get back in the groove. Then typing go back to that flow state.

Typing code is always semi-unconscious. Just like you don't pay that much attention to every character when you're writing notes on paper.

Editing code is where I focus on it, but I'm also reading docs, running tests,...

Re: Generative AI coding tools and agents do not work for me

#28

Post by adriand »

jumploops wrote: post #2

> It takes me at least the same amount of time to review code not written by me than it would take me to write the code myself, if not more. As someone who uses Claude Code heavily, this is spot on. LLMs are great, but I find the more I cede control to them, the longer it takes to actually ship the code. I’ve found that the main benefit for me so far is the reduction of RSI symptoms, whereas the actual time savings a…

Do you have to review the code? I’ll be honest that, like the OP theorizes, I often just spot review it. But I also get it to write specs (often very good, in terms of the ones I’ve dug into), and I always carefully review and test the results. Because there is also plenty of non-AI code in my projects I didn’t review at all, namely, the myriad open source libraries I’ve installed.

Re: Generative AI coding tools and agents do not work for me

#29

Post by satisfice »

bdamm wrote: post #11

No offense intended, but this is written by a guy who has the spare time to write the blog. I can only assume his problem space is pretty narrow. I'm not sure what his workflow is like, but personally I am interacting with so many different tools, in so many different environments, with so many unique problem sets, that being able to use AIs for error evaluation, and yes, for writing code, has indeed been a game chan…

You think he's not using the tools correctly. I think you aren't doing your job responsibly. You must think he isn't trying very hard. I think you are not trying very hard...

That is the two sides of the argument. It could only be settled, in principle, if both sides were directly observing each other's work in real-time.

But, I've tried that, too. 20 years ago in a debate between dedicated testers and a group of Agilists who believed all testing should be automated. We worked together for a week on a project, and the last day broke down in chaos. Each side interpreted the events and evidence differently. To this day the same debate continues.

Re: Generative AI coding tools and agents do not work for me

#30

Post by jdbernard »

adventured wrote: post #17
handfuloflight wrote: post #6

Will we be having these conversations for the next decade?

The conversations will climb the ladder and narrow. Eventually: well, but, the AI coding agent isn't better than a top 10%/5%/1% software developer. And it'll be that the coding agents can't do narrow X thing better than a top tier specialist at that thing. The skeptics will forever move the goal posts.

If the AI actually outperforms humans in the full context of the work, then no, we won't. It will be so much cheaper and faster that businesses won't have to argue at all. Those that adopt them will massively outcompetes those that don't.

However, assuming we are still having this conversation, that alone is proof to me that the AI is not that capable. We're several years into "replace all devs in six months." We will have to continue wait and see it try and do.

Post reply on HN