MattG comments on Open thread, Oct. 12 - Oct. 18, 2015 - Less Wrong Discussion
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 (250)
One of the open problems MIRI is working on for FAI is exactly this type of logical uncertainty. It should be able to modify itself if it finds out the logic underlying it's basic programming is incorrect.