>> an LLM is completely opaque
And despite that, although they are not like that in practice as there are too many uncontrolled variables, with temperature at zero, for the same input they produce always the same reply.
> with temperature at zero, for the same input they produce always the same reply.
Nonsense.
https://thinkingmachines.ai/blog/defeating-nondeterminism-in...
Ha, they sure don’t.