AI coding tools can reduce productivity • Hacker News Board

Re: AI coding tools can reduce productivity

#11

Post by famahar » Fri, Jul 11, 2025, 1:01 AM UTC

justinko wrote: post #3

latenightcoding wrote: post #2

LLMs make me 10-20x more productive in frontend work which I barely do. But when it comes to low-level stuff (C/C++) I personally don't find it too useful. it just replaces my need to search stackoverflow. edit: should have mentioned the low-level stuff I work on is mature code and a lot of times novel.

Same. It’s amazing for frontend.

It's astonishing. A bit scary actually. Can easily see the role of front-end slowly morphing into a single person team managing a set of AI tools. More of an architecture role.

Re: AI coding tools can reduce productivity

#12

Post by cguess » Fri, Jul 11, 2025, 1:05 AM UTC

latenightcoding wrote: post #2

LLMs make me 10-20x more productive in frontend work which I barely do. But when it comes to low-level stuff (C/C++) I personally don't find it too useful. it just replaces my need to search stackoverflow. edit: should have mentioned the low-level stuff I work on is mature code and a lot of times novel.

This is exactly my experience as well. I've had agents write a bit of backend code, always small parts. I'm lucky enough to be experienced enough with code I didn't write to be able to quickly debug it when it fails (and it always fails from the first run). Like using AI to write a report, it's good for outlines, but the details are always seemingly random as far as quality.

For frontend though? The stuff I really don't specialize in (despite some of my first html beginning on FrontPage 1997 back in 1997), it's a lifesaver. Just gotta be careful with prompts since so many front end frameworks are basically backend code at this point.

Re: AI coding tools can reduce productivity

#13

Post by Falimonda » Fri, Jul 11, 2025, 1:14 AM UTC

relaxing wrote: post #9

justinko wrote: post #3

Earlier quoted context omitted.

Same. It’s amazing for frontend.

Is this because they had the entire web to train on, code + output and semantics in every page?

It's moreso that a backend developer can now throw together a frontend and vice-versa without relying on a team member or needing to set aside time to internalize all the necessary concepts to just make that other part of the system work. I imagine even a full-stack developer will find benefits.

Re: AI coding tools can reduce productivity

#14

Post by IX-103 » Fri, Jul 11, 2025, 1:15 AM UTC

moron4hire wrote: post #6

latenightcoding wrote: post #2

LLMs make me 10-20x more productive in frontend work which I barely do. But when it comes to low-level stuff (C/C++) I personally don't find it too useful. it just replaces my need to search stackoverflow. edit: should have mentioned the low-level stuff I work on is mature code and a lot of times novel.

This feels like a parallel to the Gell-Mann amnesia effect. Recently, my company has been investigating AI tools for coding. I know this sounds very late to the game, but we're a DoD consultancy and one not traditional associated with software development. So, for most of the people in the company, they are very impressed with the AI's output. I, on the other hand, am a fairly recent addition to the company. I was sp…

Well, that's what you'd expect from an LLM. They're not designed to give you the best solution. They're designed to give you the most likely solution. Which means that the results would be expected to be average, as "above average" solutions are unlikely by definition.

You can tweak the prompt a bit to skew the probability distribution with careful prompting (LLMs that are told to claim to be math PHDs are better at math problems, for instance), but in the end all of those weights in the model are spent to encode the most probable outputs.

So, it will be interesting to see how this plays out. If the average person using AI is able to produce above average code, then we could end up in a virtuous cycle where AI continuously improves with human help. On the other hand, if this just allows more low quality code to be written then the opposite happens and AI becomes more and more useless.

Re: AI coding tools can reduce productivity

#15

Post by JKCalhoun » Fri, Jul 11, 2025, 1:15 AM UTC

As others probably have experienced, I can only add that I am doing coding now I would have kicked down the road if I did not have LLM assistance.

Example: using LeafletJS — not hard, but I didn't want to have to search all over to figure out how to use it.

Example: other web page development requiring dropping image files, complicated scrolling, split-views, etc.

In short, there are projects I have put off in the past but eagerly begin now that LLMs are there to guide me. It's difficult to compare times and productivity in cases like that.

Re: AI coding tools can reduce productivity

#16

Post by tomcam » Fri, Jul 11, 2025, 1:24 AM UTC

What bothers me more than any of this particular discussion is that we seem to be incapable of determining programmer productivity in a meaningful way since my debut as a programmer 40 years ago.

Re: AI coding tools can reduce productivity

#17

Post by freetime2 » Fri, Jul 11, 2025, 1:29 AM UTC

Tainnor wrote: post #10

freetime2 wrote: post #5

Here is the the methodology of the study: > To directly measure the real-world impact of AI tools on software development, we recruited 16 experienced developers from large open-source repositories (averaging 22k+ stars and 1M+ lines of code) that they’ve contributed to for multiple years. Developers provide lists of real issues (246 total) that would be valuable to the repository—bug fixes, features, and refactors t…

The sample size isn't 16 developers, it's 246 issues.

So agree with that - but on the other hand surely the number of developers matters here? For example, if instead of 16 developers the study consisted of a single developer completing all 246 tasks with or without AI, and comparing the observed times to complete, I think most people would question the reproducibility and relevancy of the study?

Re: AI coding tools can reduce productivity

#18

Post by hluska » Fri, Jul 11, 2025, 1:33 AM UTC

Falimonda wrote: post #13

relaxing wrote: post #9

Earlier quoted context omitted.

Is this because they had the entire web to train on, code + output and semantics in every page?

It's moreso that a backend developer can now throw together a frontend and vice-versa without relying on a team member or needing to set aside time to internalize all the necessary concepts to just make that other part of the system work. I imagine even a full-stack developer will find benefits.

This has nothing to do with what they asked.

Re: AI coding tools can reduce productivity

#19

Post by hluska » Fri, Jul 11, 2025, 1:40 AM UTC

relaxing wrote: post #9

justinko wrote: post #3

Earlier quoted context omitted.

Same. It’s amazing for frontend.

Is this because they had the entire web to train on, code + output and semantics in every page?

I’m not sure how this was extended and refined but there are sure a lot of signs of open source code being used heavily (at least early on). It would make sense to test model fit with the web at large.

Re: AI coding tools can reduce productivity

#20

Post by hluska » Fri, Jul 11, 2025, 1:43 AM UTC

I’ve been around tech for a long time. At this point, I’ve lost count of how many hype cycles I’ve seen hit the “hold on, everything sucks” stage. Generative AI is seemingly at the hold on, everything sucks stage and it’s getting repetitive.