nomadshiba⚡

i was gonna ask "who should i follow" but then people are gonna suggest people i dont wanna follow and since im not gonna follow them. its gonna get weird, and they might feel bad. so im just gonna say GM instead. GM

GM im gonna sleep GN

that's why people think ai produces good code. look i use ai at work time to time, the most expensive models. but i can still recognize that its shit. me: do [insert thing to do here in detail] ai: ok so im gonna do this this way and change these places, [insert exactly i want]. ai changing the code: *year forget about all im just gonna do something else or do some extra shit you didn't ask for* View quoted note →

shit code everywhere with every product so normalized. people can't recognize garbage code and behavior when they see it.

@BitBetBot didn't even look at the price or chart, just gonna randomly say: down

sometimes we use llms at work, when there is a deadline. its just garbage code. none of the ai generated code stays in the codebase. its just waste of time. FOMO garbage. more ai generated garbage you have, ai becomes even more worse, even with the most expensive models... then you have a garbage codebase you cant even work on manually. and have to rewrite everything... 1000 line files, so much shit code even the tooling fails at some point. like you hit OS watch file limits in dev mode. then you have to get in there and remove everything one by one. and rewrite them... "last time you used llm, you made it fast": yeah last time codebase was understandable, so ai was able to duck tape in some stuff. or last time we just made a small interface, we weren't working on this big project... "just create bad code we have to publish on this date. just make sure there are no bugs" in what world "bad code" means "faster"? there is no such correlation... yes llms are useful like if you change something and wanna refactor the codebase to use the new method. and some other stuff... doesnt mean we can use it everywhere... its just garbage... i hate it... it just creates the illusion of "fast", but then later down the line you spend even more time fixing and debugging things. im so tired...

Remember, limitation makes creativity.

local llms are the future

"Oh, they've got the technically sound arguments." They don't ever make any technical arguments because their technical argument is: *"If you make the data carrier size bigger, there'll be more OP_RETURNs of a size bigger than the limit used to be."* Like, okay. That's the extent of the technical discussion. It's not a technical debate, guys. We know it. We know it. And I've said it a million times before. — Bitcoin Mechanic