Robin_Hanson2 comments on Unbounded Scales, Huge Jury Awards, & Futurism - Less Wrong

21 Post author: Eliezer_Yudkowsky 29 November 2007 07:45AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (8)

Sort By: Old

You are viewing a single comment's thread.

Comment author: Robin_Hanson2 29 November 2007 11:35:11AM 7 points [-]

If you are asked to estimate a number that is a product (or sum) of many numbers, and you have good estimates for all those numbers but one, well variance in that last number you can't estimate well will dominate the variance of your answer. It just takes one.