[vntok]

True, however as these products have been designed and coded by LLMs from the ground up in 2025+, they are generally using modern (typed even) languages, the latest version of third party libraries, usually have documentation of sorts... sometimes they even have test suites.

As such, they can often be improved as easily as one can prompt, which is much faster and easier than before. Notably in the FOSS world where one had to ask the maintainer, get ghosted for a year and have them go back with a "close: wontfix (too tedious)".

[bagacrap]

I've tried very earnestly to use opus 4.5 to get rid of some backlog tasks that were too tedious to do manually. It turns out that they're still extremely tedious because I have to make every single non trivial decision for the model, unless I don't care one iota about the long term sustainability of the code base. And by long term, I mean more than a week. They're good for saving keystrokes or doing fuzzy searches for me. "Design"? No, that is an anthropomorphism.

[habinero]

I actually had a perfect use case for slopcoding - I needed to scrape a search result and turn it into a csv and a bunch of files.

Totally possible with a hour or so or coding but annoying and not that fun. Completely trivial, tons of stuff like it, piece of cake

Claude got something that looked like it was worked, and didn't. I figured out why, told it what to fix, and it didn't.

Finally after several rounds, it kicked off...and then hung on...something? idk what, it doesn't look like it was rate limited

Also it said the code would check to see it had already downloaded the file and if so, skip it. It definitely did not do that lol

At this point it was 90 minutes--an hour of yelling at the computer and another 30 minutes of my ADHD ass forgetting that I had it running

I like it as fancy autocomplete because it's usually helpful and I can silence it for 20 minutes if it's annoying me, but man.

[nine_k]

Better languages do not necessarily mean better architectural decisions, or even better performance, unless the humans pressure for that and burn tokens on that. With no engineer in the room, more technical issues will be left unnoticed and unaddressed.

Compare it to visual arts. With a guidance form an artist, AI tools can help create wonderful pictures. Without such guidance, or at least expert prompting, a typical one-shot image from Gemini is... well, at best recognizable as such.