Computers don't do what you want, they do what you tell them to do.
Exactly, they're passive aggressive af
I wouldn't call them passive, they do too much work. More like aggressively submissive.
Maliciously compliant perhaps
They do what you tell them, but only exactly what and how you tell them. If you leave any uncertainty chances are it will fuck up the task
Stupid code! Oh, looks like this was my fault again....this time
Must've been chatGPT's fault
My experience is that: If you don't know exactly what code the AI should output, it's just stack overflow with extra steps.
Currently I'm using a 7B model, so that could be why?
Yeah but have you ever coded shaders? That shit’s magic sometimes. Also a pain to debug, you have to look at colors or sometimes millions of numbers trough a frame analyzer to see what you did wrong. Can’t program messages to a log.
Can't you run it on an emulator for debugging, Valgrind-style?
Me looking at my unit tests failing one after another.
Computers don't do what you want, they do what you tell them to do.
Exactly, they're passive aggressive af
I wouldn't call them passive, they do too much work. More like aggressively submissive.
Maliciously compliant perhaps
They do what you tell them, but only exactly what and how you tell them. If you leave any uncertainty chances are it will fuck up the task
Stupid code! Oh, looks like this was my fault again....this time
Must've been chatGPT's fault
My experience is that: If you don't know exactly what code the AI should output, it's just stack overflow with extra steps.
Currently I'm using a 7B model, so that could be why?
Yeah but have you ever coded shaders? That shit’s magic sometimes. Also a pain to debug, you have to look at colors or sometimes millions of numbers trough a frame analyzer to see what you did wrong. Can’t program messages to a log.
Can't you run it on an emulator for debugging, Valgrind-style?
Me looking at my unit tests failing one after another.