Will_Newsome comments on Beginning resources for CEV research - Less Wrong

14 Post author: lukeprog 07 May 2011 05:28AM

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

Comments (31)

You are viewing a single comment's thread. Show more comments above.

Comment author: wedrifid 12 May 2011 09:18:05AM *  0 points [-]

I'm not sure what you mean by the first paragraph. CEV is a plan for friendliness content.

More of a partial plan. I would call it a plan once an approximate mechanism for aggregation is specified. Without the aggregation method the outcome is basically undefined.

or because extrapolated values do not converge cleanly and the value that leads to the supposed failure scenario will not survive a required 'voting' process (or whatever) in the extrapolation process.

The 'people are assholes' failure mode. :)