PhilGoetz comments on Cryptographic Boxes for Unfriendly AI - Less Wrong

24 Post author: paulfchristiano 18 December 2010 08:28AM

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

Comments (155)

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

Comment author: paulfchristiano 21 December 2010 10:27:32PM 2 points [-]

Perhaps the wikipedia article was a bad link, because it talks about things from the algebraic perspective. Algebraic operations are equivalent to general-purpose programs if you are willing to let things run more slowly; it turns out that computers are built out of ANDs and ORs, which is exactly what homomorphic encryption lets you do. For C programs the slowdown is significant. For logic circuits the slowdown isn't very significant. For LISP programs the slowdown is intermediate.

Comment author: PhilGoetz 06 August 2015 03:25:38AM 0 points [-]

Okay, but the problem is still that you're looking for a way to execute operations without knowing what the operations are.