Mark, "...and that the (actually explicit) assumption underlying the whole scientific method is that the same causes produces the same results. Comments?"
It seems like a somewhat weaker assumption *could* work; namely, "the same causes produce the same probability distribution on effects". This weakening accepts physical random events. (Although its meaning is arguable-- one interpretation of probability says probability = frequency, so all the assumption is claiming is that a frequency exists. That seems really weak. Another interpretation says that probabilities are real physical properties that are merely *discovered* by counting frequencies of physical events. That's somewhat stronger, but a little strange sounding...) I believe the AIXI answer is that AIXI applies to *either* computable universes *or* universes with computable probability distributions. --Abram On Sat, Oct 25, 2008 at 11:02 PM, Mark Waser <[EMAIL PROTECTED]> wrote: >>> -- truly general AI, even assuming the universe is computable, is >>> impossible for any finite system > Excellent. Unfortunately, I personally missed (or have forgotten) how AIXI > shows or proves this (as opposed to invoking some other form of > incompleteness) unless it is merely because of the assumption that the > universe itself is assumed to be infinite (which I do understand but > which then makes the argument rather pedestrian and less interesting). > >>> The computability of the universe is something that can't really be >>> proved, but I argue that it's an implicit assumption underlying the whole >>> scientific method. > > It seems to me (and I certainly can be wrong about this) that computability > is frequently improperly conflated with consistency (though may be you want > to argue that such a conflation isn't improper) and that the (actually > explicit) assumption underlying the whole scientific method is that the same > causes produces the same results. Comments? > > > ----- Original Message ----- > From: Ben Goertzel > To: agi@v2.listbox.com > Sent: Saturday, October 25, 2008 7:48 PM > Subject: **SPAM** Re: AIXI (was Re: [agi] If your AGI can't learn to play > chess it is no AGI) > > AIXI shows a couple interesting things... > > -- truly general AI, even assuming the universe is computable, is impossible > for any finite system > > -- given any finite level L of general intelligence that one desires, there > are some finite R, M so that you can create a computer with less than R > processing speed and M memory capacity, so that the computer can achieve > level L of general intelligence > > This doesn't tell you *anything* about how to make AGI in practice. It does > tell you that, in principle, creating AGI is a matter of *computational > efficiency* ... assuming the universe is computable. > > The computability of the universe is something that can't really be proved, > but I argue that it's an implicit assumption underlying the whole scientific > method. If the universe can't be usefully modelable as computable then the > whole methodology of gathering finite datasets of finite-precision data is > fundamentally limited in what it can tell us about the universe ... which > would really suck... > > -- Ben G > > -- Ben G > > On Sat, Oct 25, 2008 at 7:21 PM, Matt Mahoney <[EMAIL PROTECTED]> wrote: >> >> --- On Sat, 10/25/08, Mark Waser <[EMAIL PROTECTED]> wrote: >> >> > Ummm. It seems like you were/are saying then that because >> > AIXI makes an >> > assumption limiting it's own applicability/proof (that >> > it requires that the >> > environment be computable) and because AIXI can make some >> > valid conclusions, >> > that that "suggests" that AIXI's limiting >> > assumptions are true of the >> > universe. That simply doesn't work, dude, unless you >> > have a very loose >> > inductive-type definition of "suggests" that is >> > more suited for inference >> > control than anything like a logical proof. >> >> I am arguing by induction, not deduction: >> >> If the universe is computable, then Occam's Razor holds. >> Occam's Razor holds. >> Therefore the universe is computable. >> >> Of course, I have proved no such thing. >> >> -- Matt Mahoney, [EMAIL PROTECTED] >> >> >> >> ------------------------------------------- >> agi >> Archives: https://www.listbox.com/member/archive/303/=now >> RSS Feed: https://www.listbox.com/member/archive/rss/303/ >> Modify Your Subscription: https://www.listbox.com/member/?&; >> Powered by Listbox: http://www.listbox.com > > > > -- > Ben Goertzel, PhD > CEO, Novamente LLC and Biomind LLC > Director of Research, SIAI > [EMAIL PROTECTED] > > "A human being should be able to change a diaper, plan an invasion, butcher > a hog, conn a ship, design a building, write a sonnet, balance accounts, > build a wall, set a bone, comfort the dying, take orders, give orders, > cooperate, act alone, solve equations, analyze a new problem, pitch manure, > program a computer, cook a tasty meal, fight efficiently, die gallantly. > Specialization is for insects." -- Robert Heinlein > > > ________________________________ > agi | Archives | Modify Your Subscription > > ________________________________ > agi | Archives | Modify Your Subscription ------------------------------------------- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=117534816-b15a34 Powered by Listbox: http://www.listbox.com
