[acedTrex]

I have yet to get it to generate code past 10ish lines that I am willing to accept. I read stuff like this and wonder how low yall's standards are, or if you are working on projects that just do not matter in any real world sense.

[dillydogg]

Whenever I read comments from the people singing their praises of the technology, it's hard not to think of the study that found AI tools made developers slower in early 2025.

>When developers are allowed to use AI tools, they take 19% longer to complete issues—a significant slowdown that goes against developer beliefs and expert forecasts. This gap between perception and reality is striking: developers expected AI to speed them up by 24%, and even after experiencing the slowdown, they still believed AI had sped them up by 20%.

https://metr.org/blog/2025-07-10-early-2025-ai-experienced-o...

[logicprog]

Here's an in depth analysis and critique of that study by someone whose job is literally to study programmers psychologically and has experience in sociology studies: https://www.fightforthehuman.com/are-developers-slowed-down-...

Basically, the study has a fuckton of methodological problems that seriously undercut the quality of its findings, and even assuming its findings are correct, if you look closer at the data, it doesn't show what it claims to show regarding developer estimations, and the story of whether it speeds up or slows down developers is actually much more nuanced and precisely mirrors what the developers themselves say in the qualitative quote questionaire, and relatively closely mirrors what the more nuanced people will say here — that it helps with things you're less familiar with, that have scope creep, etc a lot more, but is less or even negatively useful for the opposite scenarios — even in the worst case setting.

Not to mention this is studying a highly specific and rare subset of developers, and they even admit it's a subset that isn't applicable to the whole.

[dillydogg]

This is very helpful, thank you for the resource

[mstkllah]

Ah, the very extensive study with 16 developers. Bulletproof results.

[troupo]

Compared to "it's just a skill issue you're not prompting it correctly" crowd with literally zero actionable data?

[izacus]

Yeah, we should listen to the one "trust me bro" dude instead.

[spicyusername]

4/5 times I can easily get 100s of lines output, that only needs a quick once over.

1/5 times, I spend an extra hour tangled in code it outputs that I eventually just rewrite from scratch.

Definitely a massive net positive, but that 20% is extremely frustrating.

[acedTrex]

That is fascinating to me, i've never seen it generate that much code that is actually something i would consider correct. It's always wrong in some way.

[LinXitoW]

In my experience, if I have to issue more than 2 corrections, I'm better off restarting and beefing up the prompt or just doing it myself

[djeastm]

Standards are going to be as low as the market allows I think. Some industries code quality is paramount, other times its negligible and perhaps speed of development is higher priority and the code is mostly disposable.