Shane Legg wrote:
:-)
No offence taken, I was just curious to know what your position was.
I can certainly understand people with a practical interest not having
time for things like AIXI. Indeed as I've said before, my PhD is in AIXI
and related stuff, and yet my own AGI project is based on other things.
So even I am skeptical about whether it will lead to practical methods.
That said, I can see that AIXI does have some fairly theoretical uses,
perhaps Friendliness will turn out to be one of them?
Well, I could see AIXI type methods being used to provide an
"impossibility proof" for some types of Friendly AI.
I.e., one might possibly be able to show something like "Even with
near-infinite resources, achieving FAI according to definition
Friendliness_17 is not possible."
I am more skeptical about a positive proof of the achievability of
Friendly AI using realistic computational resources, being do-able
using AIXI-type ideas. The problem is that there is nothing,
conceptually, in the whole army of ideas surrounding AIXI,
that tells you about how to deal with the challenges of finite
computational resources. (And my view is that dealing with
these challenges is actually the crux of the AGI problem.)
-- Ben G
-----
This list is sponsored by AGIRI: http://www.agiri.org/email
To unsubscribe or change your options, please go to:
http://v2.listbox.com/member/?list_id=11983
