Comment by littlestymaar
4 days ago
It's good way to assess the model with respect to hallucinations though.
I don't think a model should know the answer, but it must be able to know that it doesn't know if you want to use it reliably.
4 days ago
It's good way to assess the model with respect to hallucinations though.
I don't think a model should know the answer, but it must be able to know that it doesn't know if you want to use it reliably.
No model is good at this yet. I'd expect the flagships to solve the first.