@arjan @Purple should have written a bunch of random garbage code that doesn't really work, clearly.

@Purple @halfy LLMs fundamentally do not "understand" things. they cannot access meaning. as such they also can't really fundamentally get better at this. all you can do is little tweaks that cannot resolve the fundamental problems with them cause they are based on how they function.

@JenJen

@juergen_hubert @randahl exactly