logoalt Hacker News

throwaway27448yesterday at 10:50 PM1 replyview on HN

It is trivial to contrive a distinct model that behaves the same, no?

Regardless, most uses of a model won't provide direct interaction. This entire line of thought seems starved of use. Unless we're talking about LLM providers themselves... but that is a separate topic entirely


Replies

amazingamazingyesterday at 11:15 PM

no, because you don't know what the "secret prompt" is. there could be hundreds such prompts

show 1 reply