|
|
|
|
|
|
by diggan
286 days ago
|
|
|
> 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 :) |
|
|