Pavel @spavel.bsky.social · 31/03/2026The main problem with checking AI outputs for errors is that you need to have an idea of what you actually wanted it to do. Most people use AI as a *substitute* for having to figure that out. 922833
Matt needs a UX gig 🐀 @mattz-design.pro · 31/03/2026I would have thought developers would have understood the old CS axiom of "garbage in, garbage out" 100
Jeff @bettysears.bsky.social · 31/03/2026Figuring it out is where all the fun and satisfaction lies. It astounds me that so many people want desperately to avoid it, even when their solutions are more error prone. 010
tweety fish oh wow like a chimera or something spoooky @sifu.tweety.fish · 09/04/2026extremely yes. its usefulness has I would say a supralinear relationship to how well you understand what you're trying to do, much more so than working with even the ineptest other human. 020
Frankie Huang 黄碧赤 @ourobororoboruo.bsky.social · 31/03/2026And it’s kind of degrading to spend time checking the work of a hallucinating machine when you could be getting paid more to just do the work 1230
pave2112.bsky.social @pave2112.bsky.social · 09/04/2026even at highest IT levels, this remains a problem....LLMs are not ML models that "drift"...they're always just guessing, sometime right and sometimes wrong 000
Pavel @spavel.bsky.social · 09/04/2026many are sayingdorian@doriantaylor.comlike sure it'll generate code, and the code will even run! but you won't be able to use it because it doesn't actually do what you need it to do and thus begins the irreducible process of determining what you need the code to do 1210
Mark @aiquest.info · 01/04/2026not sure i agree.. the problem isn't checking outputs.. it's that people aren't using the output as input for their own thinking.. if you treat it like brainstorming with a colleague it works fine even when you're unclear on the end result.. it's a mode of interaction not a final answer 010
猫好きな人 @valoisdubins.bsky.social · 31/03/2026This is one of the key differences with coding compared to most uses of LLMs. 100
