[candiddevmike]

If the faster one creates naive, hard to discover bugs, is it really faster? I don't think we understand the long term consequences (or maintenance) of LLM generated code. So far the anecdotal results haven't been great.

[mintplant]

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.

[jonathanlydall]

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.

[mintplant]

Kitbashed SO code at least had some kind of grounding to it. The AI stuff is fully unmoored.

[andai]

We are having two different conversations. My question was of course based on the invention of AIs that are actually competent.

[CRConrad]

So largely fictional, then.

[cr125rider]

LLMs seem good at replacing off-shore and very Jr. devs. That’s about it so far. We’ll see if they can get over this current stagnation.

[dartos]

Do they?

They just seem to replace stack overflow.

[wpm]

Stack Overflow rarely surfaced a solution to your particular problem, but solutions to tangential or otherwise very similar problems. You still had to reason around the posters problem context and try to see if it really matched your own. You still had to have some understanding.

LLMs present a solution as if it is 100% in the context of your problem. You arrive at a solution without being forced to think at all if the solution applies to your problem.

Without being forced to, many will not. I teach programming and I can tell you it is so so obvious when students are just blasting shit from ChatGPT into their submissions without thought.

[hooverd]

Stack Overflow for better or worse would let you know when you're being an idiot and would shoot your foot off. AI will gladly load the gun for you.