News for hackers. Stuff that matters.
Re:Intents: The Endgame for Computing Interfaces? by mintplant on Saturday September 14, 2024 @12:51PM (#41540975)
I've become increasingly frustrated with having to work with other people's AI-"assisted" code. I can tell when I depart from reading sensible human-written code and enter the land of Copilot where all bets are off. Just yesterday I discovered that some environment variables someone had configured on a service weren't actually doing anything, because the service didn't support being configured via environment variables, let alone those particular ones. It's stuff like that which really gets me about all this: you can no longer assume a coherent theory of mind behind what you're reading. You can no longer trust that because something looks specific and intentional (like environment variable names), that it actually came from reality and not a confabulation. It's breaking the social contract that makes collaboration work.
Re:Intents: The Endgame for Computing Interfaces? by jonathanlydall on Saturday September 14, 2024 @02:07PM (#41541612)
I don’t support stupidly applied AI generated code either, but this isn’t a new thing at all, before it was code pasted from Stackoverflow and hammered at until it sort of worked.
Re:Intents: The Endgame for Computing Interfaces? by mintplant on Saturday September 14, 2024 @04:40PM (#41542686)
Kitbashed SO code at least had some kind of grounding to it. The AI stuff is fully unmoored.
Re:Intents: The Endgame for Computing Interfaces? by andai on Sunday September 15, 2024 @02:57AM (#41545756)
We are having two different conversations. My question was of course based on the invention of AIs that are actually competent.
Re:Intents: The Endgame for Computing Interfaces? by CRConrad on Tuesday September 17, 2024 @06:00AM (#41566070)
So largely fictional, then.