Post #1688716
2026-04-01 12:04 UTC
@jonny @maxmortillaro The insane thing is the output of LLM tools I’ve tried actually get worse with further revision instead of better.
Ask it to produce a thing, examine and give feedback, and the revision comes back worse. Every iteration is impressive, but none is usable.
I’m not a coder, but it’s just as bad with prose. It looks like it makes sense, but then doesn’t as you read it. And as you keep working through it, it makes less and less sense, until a credible editor just shitcans it.
Replies (1)
-
@wila@mastodon.social 2026-04-02 08:29
@sfoskett @jonny @maxmortillaro I've tried it for low level API stuff and have come to the conclusion that while some of the code might work, it usually is still wrong in various degrees of wrong. The "it looks correct" type of code is dangerous. Also, it takes more time to verify than to actually write yourself and do it right the first time. No, it's not useless, but I keep it far away from production level code.