I talked to one fellow about GO playing AI last night and I mentioned these Restricted Boltzmann Machines. If the GO problem can be cast as an image processing problem, RBMs might be worth looking into: http://www.youtube.com/watch?v=AyzOUbkUf3M Here is a more recent Google Tech talk by Hinton on RBMs http://www.youtube.com/watch?v=VdIURAu1-aU
I found those links posted above interesting.
I concede that the human learning process is not at all as explosive as the self-modifying AI processes of the future will be, but I was speaking to a different point:
Eliezer said: "I'd be pretty doubtful of any humans trying to do recursive self-modification in a way that didn't involve logical proof of correctness to start with."
I am arguing that humans do recursive self-modification all the time, without "proofs of correctness to start with" - even to the extent of developing gene thera...
"NS can at best only transfer information from the environment to the genome." Does this statement mean to suggest that the environment is not complex?