Eliezer_Yudkowsky comments on Sustained Strong Recursion - Less Wrong

11 Post author: Eliezer_Yudkowsky 05 December 2008 09:03PM

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

Comments (46)

Sort By: Old

You are viewing a single comment's thread.

Comment author: Eliezer_Yudkowsky 05 December 2008 09:48:21PM 3 points [-]

Robin, like I say, most AIs won't hockey-stick, and when you fold a function in on itself this way, it can bottleneck for a billion years if its current output is flat or bounded. That's why self-optimizing compilers don't go FOOM.

"Recursion" is not accelerating growth. It is not a loop of growth factors. "Adding a recursion" describes situations where you might naively be tempted to take an existing function

y = F(t)

and rewrite it as

dy/dt = F(y)

Does that make it any clearer?