Using LLMs at Oxide

"LLMs are amazingly good at writing code" that one was good. I cant stop laughing.

I wrote an entire multiplayer game in XNA that I've tried repeatedly to get LLMs to translate to javascript

it's just utterly hopeless how bad they are at doing it

even if I break it down into parts once you get into the stuff that actually matters i.e. the physics, event handling, and game logic induced by events, it just completely falls apart 100% of the time

I agree with your sentiment, but I do find it amazing that the underlying techniques of inference can emit code that is as apparently coherent as it is. (This does not imply actual coherence.)

I felt this the other day. I wouldn't even consider my example exotic, p2p systems using electron? It just couldn't figure out how to work with YJS correctly.

These things aren't hard if you're familiar with the documentation and have made them before, but what there is is an extreme dearth of information about it compared to web dev tutorials.