saturn comments on Limits on self-optimisation - Less Wrong

6 Post author: RolfAndreassen 20 January 2012 09:58PM

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

Comments (36)

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

Comment author: saturn 22 January 2012 12:54:22AM 1 point [-]

You can prove that a smaller set of transformations preserve the behavior of subsections of a program, then you can combine arbitrarily many of those transformations and preserve the input to output map of a larger program.