zlacker

[parent] [thread] 7 comments
1. bluefi+(OP)[view] [source] 2025-07-10 19:10:01
> Take a whole week to do a month's worth of features

Everything else in your post is so reasonable and then you still somehow ended up suggesting that LLMs should be quadrupling our output

replies(1): >>furyof+A6
2. furyof+A6[view] [source] 2025-07-10 19:56:05
>>bluefi+(OP)
I'm specifically talking about greenfield work. I do a lot of game prototypes, it definitely does that at the very beginning.
replies(2): >>bluefi+E8 >>Dzugar+7h
◧◩
3. bluefi+E8[view] [source] [discussion] 2025-07-10 20:08:12
>>furyof+A6
Greenfield is still such a tiny percentage of all software work going on in the world though :/
replies(2): >>furyof+u9 >>Fillig+Of
◧◩◪
4. furyof+u9[view] [source] [discussion] 2025-07-10 20:12:20
>>bluefi+E8
I agree, that's fair. I think a lot of people are playing around with AI on side projects and making some bad extrapolations from their initial experiences.

It'll also apply to isolated-enough features, which is still a small amount of someone's work (not often something you'd work on for a full month straight), but more people will have experience with this.

replies(1): >>lurkin+Je
◧◩◪◨
5. lurkin+Je[view] [source] [discussion] 2025-07-10 20:40:25
>>furyof+u9
greenfield development is also the “easiest” and most fun part of software development. As the famous saying goes, the last 10% of the project takes 90% of the time lol.

I’ve also noticed that, generally, nobody likes maintaining old systems.

so where does this leave us as software engineers? Should I be excited that it’s easy to spin up a bunch of code that I don’t deeply understand at the beginning of my project, while removing the fun parts of the project?

I’m still grappling with what this means for our industry in 5-10 years…

◧◩◪
6. Fillig+Of[view] [source] [discussion] 2025-07-10 20:46:54
>>bluefi+E8
It’s a tiny percentage of software work because the programming is slow, and setting up new projects is even slower.

It’s been a majority of my projects for the past two months. Not because work changed, but because I’ve written a dozen tiny, personalised tools that I wouldn’t have written at all if I didn’t have Claude to do it.

Most of them were completed in less than an hour, to give you an idea of the size. Though it would have easily been a day on my own.

replies(1): >>y0eswd+Xm9
◧◩
7. Dzugar+7h[view] [source] [discussion] 2025-07-10 20:52:36
>>furyof+A6
This is really interesting, because I do gamejams from time to time - and I try every time to make it work, but I'm still quite a lot faster doing stuff myself.

This is visible under extreme time pressure of producing a working game in 72 hours (our team scores consistenly top 100 in Ludum Dare which is a somewhat high standard).

We use a popular Unity game engine all LLMs have wealth of experience (as in game development in general), but the output is 80% so strangely "almost correct but not usable" that I cannot take the luxury of letting it figure it out, and use it as fancy autocomplete. And I also still check docs and Stackoverflow-style forums a lot, because of stuff it plainly mades up.

One of the reasons is maybe our game mechanics often is a bit off the beaten road, though the last game we made was literally a platformer with rope physics (LLM could not produce a good idea how to make stable and simple rope physics under our constraints codeable in 3 hours time).

◧◩◪◨
8. y0eswd+Xm9[view] [source] [discussion] 2025-07-14 14:05:33
>>Fillig+Of
I'm curious what kind of personalized tools you built?
[go to top]