every time someone tells me about using llms for codegen, all i can think about is that old adage

"debugging software is twice as hard as writing it, so if you write to the best of your ability, you're not qualified to debug it"

sure enough i know several "don't call me a programmer" friends who find it easier to get starter projects off the ground, and these tools have helped a whole bunch

but they're the first to admit "if it doesn't work i don't know how to begin fixing it"

@tef so, I haven't had to debug this yet, because the integration work is not totally trivial, but I think I had my first success with this recently

I asked it to do a thing which github actions yaml that I knew how to do, but would be a truly mind-numbingly tedious amount of typing; about 100 lines of yaml all told

I asked it to do the thing, and it looked like it basically got it right, and it was a 1-line prompt for 100 lines or so of repetitive, basically branch-free yaml

@tef this is a place where, for example, the IP concerns don't bother me; github actions yaml, pyproject.toml, et. al. are already mostly plagiarized almost by definition

@glyph i get this but this feels like a solution to a problem we created for ourselves, rather than a problem we face

"what do we want" "for loops" "how do we want them" "either recursively templated yaml and/or a fancy markov chain"

@tef hey _I_ didn't make github actions

somebody showed up and said "hey would you like about half a million dollars worth of free computer for open source every year" and the cost was having to generate reams of tedious configuration garbage and honestly it's a pretty good trade, especially if they will give me an extra 100k worth of free computer to compute the tedious configuration garbage too

@glyph oh i'm not faulting you i just feel depressed about it
@tef right there with you buddy, this is a troubling direction for an industry already known for its overwhelming number of troubling directions, I really do want to figure out a way to encourage people to _actually_ solve problems rather than paper over sinkholes with increasingly large piles of papier mâché
@glyph @tef 100% accurate, instead of trying to reduce code we are actively trying to generate more of it, so backwards :<.