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

AI usage patterns in software teams

linear.app

Post reply on HN
Print view View original

11–20 of 154 posts

Re: AI usage patterns in software teams

#11

Post by slopinthebag »

danggggg wrote: post #9
dullcrisp wrote: post #7

Earlier quoted context omitted.

It could be. Or it could be 1x, or 0.2x. You don’t have enough information to make that judgment.

[dead]

It’s worthwhile to me under specific conditions, mainly that the codebase has existing patterns and abstractions that the LLM utilizes, and they’re actually good. It’s not a common case but I’m lucky that one of the codebases I’m in is one I built myself mostly by hand, and LLMs are really effective in it at the moment. My main concern is making sure the generated code maintains the high standard, but it’s definitely saving me time.

I’ve kind of changed my mind on prompting, it’s definitely a skill. It’s a skill based on your own skills in the domain. I’m at the point where I can get the LLM to generate the same code (roughly speaking) that I would have written. So it’s basically generating the same thing I would write, just faster. So it’s like reading your own code. Using it as a crutch to do things you aren’t capable of is where people run into trouble. That’s where the massive amounts of code review come into play. For me, I’m only ever reviewing 100-300 loc changes at a time. Often less. Because I know what I’m doing and can break things down into manageable diffs.

Can’t see myself going back, but also can’t see myself doing it without the experience I have without LLMs. Which is a bit of an issue for new developers. Not sure what the solution is for that.

Re: AI usage patterns in software teams

#12

Post by dullcrisp »

danggggg wrote: post #9
dullcrisp wrote: post #7

Earlier quoted context omitted.

It could be. Or it could be 1x, or 0.2x. You don’t have enough information to make that judgment.

[dead]

Well you got me. I’d agree about that workflow, but something more rapid like a few seconds generating code and then a couple minutes reading it can be more engaging to me than writing it out yourself. I think it’s near time we all stop having such strong opinions about the matter either way personally.

Re: AI usage patterns in software teams

#13

Post by danggggg »

dullcrisp wrote: post #12
danggggg wrote: post #9

Earlier quoted context omitted.

[dead]

Well you got me. I’d agree about that workflow, but something more rapid like a few seconds generating code and then a couple minutes reading it can be more engaging to me than writing it out yourself. I think it’s near time we all stop having such strong opinions about the matter either way personally.

[dead]

Re: AI usage patterns in software teams

#14

Post by dullcrisp »

slopinthebag wrote: post #11
danggggg wrote: post #9

Earlier quoted context omitted.

[dead]

It’s worthwhile to me under specific conditions, mainly that the codebase has existing patterns and abstractions that the LLM utilizes, and they’re actually good. It’s not a common case but I’m lucky that one of the codebases I’m in is one I built myself mostly by hand, and LLMs are really effective in it at the moment. My main concern is making sure the generated code maintains the high standard, but it’s definitely…

That plus if you’ve ever stared at your code and then searched StackOverflow to see if you could find a better way of doing it, it’s like having that running continuously.

Re: AI usage patterns in software teams

#15

Post by jdw64 »

danggggg wrote: post #10
tankaiji wrote: post #6

Earlier quoted context omitted.

And then more hours cleaning it up and re-prompting.

[dead]

Writing code directly takes longer to warm up. Usually, I'd keep tens of thousands of lines in my head. In the past, I spent a lot of time designing error propagation and execution contexts. (Talented people might figure it out right away, but unfortunately I don't have that kind of talent.) So I'd have to think about things like Result and how far to propagate errors—and worry about whether my approach would conflict with the existing codebase.

But these days, AI just generates code following the existing patterns of the codebase. In the past, staring at a blank screen meant going through a checklist of things to design—starting from policies and writing everything down step by step. Now, I just ask AI and it gives me a template—which is great. Then if the AI makes a mistake, I fix it manually.

Of course, I still hand-code sometimes—but only in the areas I enjoy. Most of the time, I use AI coding. Both are fun, and they complement each other in interesting ways. Doing both together is actually enjoyable.

Re: AI usage patterns in software teams

#16

Post by dullcrisp »

danggggg wrote: post #13
dullcrisp wrote: post #12

Earlier quoted context omitted.

Well you got me. I’d agree about that workflow, but something more rapid like a few seconds generating code and then a couple minutes reading it can be more engaging to me than writing it out yourself. I think it’s near time we all stop having such strong opinions about the matter either way personally.

[dead]

I’m entitled to my opinion about your opinion just like you’re entitled to your opinion about my opinion about your opinion.

Re: AI usage patterns in software teams

#18

Post by skydhash »

jdw64 wrote: post #15
danggggg wrote: post #10

Earlier quoted context omitted.

[dead]

Writing code directly takes longer to warm up. Usually, I'd keep tens of thousands of lines in my head. In the past, I spent a lot of time designing error propagation and execution contexts. (Talented people might figure it out right away, but unfortunately I don't have that kind of talent.) So I'd have to think about things like Result and how far to propagate errors—and worry about whether my approach would conflic…

For me, coding is either a flow state (when I have huge swaths of code to write) or deeply thinking about just a few lines (mostly to figure if I caught everything). The latter case is when I procrastinate the most, because I usually have an idea of a solution, but don’t want to do the work of actually verifying if it’s correct. Using AI then is skipping the enjoyable part (writing the code) to the unpleasant part (formulating hypothesis and verifying them).
Post reply on HN