Less Wrong is a community blog devoted to refining the art of human rationality. Please visit our About page for more information.

HoverHell comments on Assessing Kurzweil: the results - Less Wrong

42 Post author: Stuart_Armstrong 16 January 2013 04:51PM

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

Comments (59)

You are viewing a single comment's thread.

Comment author: HoverHell 15 January 2013 04:42:29PM *  1 point [-]

these were not binary yes/no predictions

And how it would be most appropriate to correct for that? Normalizing by random on all alternative predictions (that were made or that can be come up with)?

(with non-binary those graphs, as it seems to me, get relatively useless)

Comment author: CarlShulman 16 January 2013 08:14:22PM 3 points [-]

(with non-binary those graphs, as it seems to me, get relatively useless)

They are at least fairly comparable to the format in Kurzweil's self-assessment, and so useful for putting the high accuracy ratings reported there into perspective.

Comment author: AnthonyC 16 January 2013 01:39:16PM 3 points [-]

Estimate the complexity in bits of each prediction? ;)

Comment author: Stuart_Armstrong 24 January 2013 11:18:29AM 1 point [-]

How complex, in bits is: "it will rain in Oxford at some point this year"? Very. And yet, I would hesitate to call that an impressive prediction...