> Correctness is secondary, user satisfaction is primary.
Kind of makes sense, not every user wants 100% correctness (just like in real-life).
And if I want correctness (which I do), I can make the models prioritize that, since my satisfaction is directly linked to the correctness of the responses :)
Kind of makes sense, not every user wants 100% correctness (just like in real-life).
And if I want correctness (which I do), I can make the models prioritize that, since my satisfaction is directly linked to the correctness of the responses :)