It’s kinda covered by 1 and 2 of you apply it right, but one view on how this plays it that I’ve found helpful is: Having model uncertainty on many individual steps predictably making the output look low confidence. If you can break something into 10 steps that you multiply together, and feel uncomfortable assigning more than 0.8 to any individual guess, you’re always going to have a low final answer.
It’s kinda covered by 1 and 2 of you apply it right, but one view on how this plays it that I’ve found helpful is: Having model uncertainty on many individual steps predictably making the output look low confidence. If you can break something into 10 steps that you multiply together, and feel uncomfortable assigning more than 0.8 to any individual guess, you’re always going to have a low final answer.