Eliezer_Yudkowsky comments on Sustained Strong Recursion - 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 (46)
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?