PhilGoetz comments on Friendly, but Dumb: Why formal Friendliness proofs may not be as safe as they appear - Less Wrong

9 Post author: apophenia 19 April 2010 11:38PM

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

Comments (4)

You are viewing a single comment's thread.

Comment author: PhilGoetz 22 April 2010 12:28:21AM 3 points [-]

The argument centers around the fallibility of some (naive) formal proofs of Friendliness which I've seen people discussing the AI box problem willing to accept.

This post might make more sense to me if you presented these proofs.