Matt Mahoney wrote:
--- Ben Goertzel <[EMAIL PROTECTED]> wrote:
What AIXI does is to continually search through the space of all
possible programs, to find the one that in hindsight (based on
probabilistic inference with an Occam prior) would have best helped it
achieve its goals -- and then enact that program.
This is not something you can do on a realistic scale.
That is not even something you can do with infinite computing power (a Turing
machine).
OK, I phrased it imprecisely, but the precise phrasing uses math ...
we've both read the paper...
But this does not make AIXI useless. AIXI is useful precisely
because it tell us this.
AIXI may be useful in a theoretical conceptual philosophical sense, but
it provides close to zero
pragmatic guidance for the task of actually creating AGIs in reality...
Ben
-----
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
