Post #1391108
2026-02-10 10:24 UTC
Replies (3)
-
@buherator@infosec.place 2026-02-10 10:37
@troed @chainq One recurring pattern I see with LLM contributions is that code-level abstractions don't make sense. The feature works, all tests pass, but a considerable amount of functionality is at the wrong place. Simplest example is a C project where *technically* it doesn't matter in which file you implement a function, but I've seen the same with Java&classes too. This doesn't matter for machines because they just grep for the function name, but makes human contributions extremely taxing, like living in a mad mans house where the soap is in the fridge and you have to climb a ladder to the attic to find the salt. I think this can be a valid argument against the LLM push.
-
@chainq@mastodon.social 2026-02-10 10:48
@troed If I get to be vibe code cleanup specialist, I want to be financially incentivized too like the people pushing for AI, not doing that in my free time. Just as I don't want to read a book, no one bothered to write, I don't want to fix software, that no one bothered to code. It's that simple. Time is a non-renewable resource. I want to spend it where it is rewarding and makes a difference. Digging into generated junk that will be regenerated tomorrow is neither.
-
@lightbocks@union.place 2026-02-10 10:48
@troed @chainq Uh-oh. How will intermediate users learn if there are no intermediate and beginner tasks and puzzles?