ZoltanBerrigomo comments on What can go wrong with the following protocol for AI containment? - Less Wrong

0 Post author: ZoltanBerrigomo 11 January 2016 11:03PM

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

Comments (29)

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

Comment author: ZoltanBerrigomo 12 January 2016 08:03:15PM *  0 points [-]

These are good points. Perhaps I should not have said "interact" but chosen a different word instead. Still, its ability to play us is limited since (i) we will be examining the records of the world after it is dead (ii) it has no opportunity to learn anything about us.

Edit: we might even make it impossible for it to game us in the following way. All records of the simulated world are automatically deleted upon completion -- except for a specific prime factorization we want to know.

This is a really bad argument for safety.

You are right, of course. But you wrote that in response to what was a parenthetical remark on my part -- the real solution is to use program checking to make sure the laws of physics of the simulated world are never violated.