this post was submitted on 02 Sep 2026
124 points (99.2% liked)
Chapotraphouse
14448 readers
514 users here now
Banned? DM Wmill to appeal.
No anti-nautilism posts. See: Eco-fascism Primer
Slop posts go in c/slop. Don't post low-hanging fruit here.
founded 5 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I dunno that wasn't my experience in the last 6 months or so. 2 years ago yeah it was basically this but nowadays I can get the thing to do some medium complexity work on our codebase and it's pretty much gonna get it right like 95% of the time with maybe some tiny code quality reduction in the form of some duplicated code or such but the thing is pretty much going to work.
Also I built a personal project with it that I wanted to do for a while but never got around to it and it pretty much did it as I wanted it. Granted it was a lot of back and forth and lots of debugging/testing passes but in the end it actually works. Not sure what the overall code quality is but the overall project structure makes sense and the little code I did look seemed solid enough.
Ya, I think it's useful for speeding up personal projects I often don't have the energy for after work, but I want to see the project done at some point still. I've been trying to balance my use of AI on them though, since I think part of the point (at least for me) should be learning new things and keeping my mind sharp, in addition to making the thing. Like, I'll have it find a bug, and then I'll investigate it and try to solve it myself instead of having AI fix it, or things like that.
It's not like work where they don't give a shit about my mind atrophying on over-use of AI and only care about productivity.