Jonathan_Graehl comments on An Alternative Approach to AI Cooperation - Less Wrong
You are viewing a comment permalink. View the original post to see all comments and the full post content.
You are viewing a comment permalink. View the original post to see all comments and the full post content.
Comments (25)
Consider any method for committing to run published source code that isn't vulnerable to deception (Freeman's works, I think).
If you are saying that physically supervised joint reincarnation is just (if it works) another type of enforceable mutual source code promise, and otherwise changes nothing, I agree.