You're looking at Less Wrong's discussion board. This includes all posts, including those that haven't been promoted to the front page yet. For more information, see About Less Wrong.

alexflint comments on rationality for turing machines - Less Wrong Discussion

2 Post author: alexflint 23 March 2011 12:38AM

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

Comments (8)

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

Comment author: alexflint 23 March 2011 08:57:29AM 1 point [-]

"Bayes oracle" was really just a term I invented right then, and it was a bad choice. I just meant that there is an optimal output symbol at each step, but that we can't necessarily write down a turing machine that actually generates it. This is not about halting-style uncomputability, rather it's about having to implement an algorithm as a tangible computation, and hence not being able to pause time while we make decisions.

If this sounds confused it's because I am!