Re: [singularity] Scenarios for a simulated universe
Matt Mahoney wrote: --- Richard Loosemore [EMAIL PROTECTED] wrote: What I wanted was a set of non-circular definitions of such terms as intelligence and learning, so that you could somehow *demonstrate* that your mathematical idealization of these terms correspond with the real thing, ... so that we could believe that the mathematical idealizations were not just a fantasy. The last time I looked at a dictionary, all definitions are circular. So you win. Sigh! This is a waste of time: you just (facetiously) rejected the fundamental tenet of science. Which means that the stuff you were talking about was just pure mathematical fantasy, after all, and nothing to do with science, or the real world. Richard Loosemre. - 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
Re: [singularity] Scenarios for a simulated universe
Ben Goertzel wrote: Richard Loosemore wrote: Matt Mahoney wrote: --- Richard Loosemore [EMAIL PROTECTED] wrote: What I wanted was a set of non-circular definitions of such terms as intelligence and learning, so that you could somehow *demonstrate* that your mathematical idealization of these terms correspond with the real thing, ... so that we could believe that the mathematical idealizations were not just a fantasy. The last time I looked at a dictionary, all definitions are circular. So you win. Richard, I long ago proposed a working definition of intelligence as Achieving complex goals in complex environments. I then went through a bunch of trouble to precisely define all the component terms of that definition; you can consult the Appendix to my 2006 book The Hidden Pattern Shane Legg and Marcus Hutter have proposed a related definition of intelligence in a recent paper... Anyone can propose a definition. The point of my objection is that a definition has to have some way to be compared against reality. Suppose I define intelligence to be: A funtion that maps goals G and world states W onto action states A, where G, W and A are any mathematical entities whatsoever. That would make any function that maps X [cross] Y into Z an intelligence. Such a definition would be pointless. The question is *why* would it be pointless? What criteria are applied, in order to determine whether the definition has something to the thing that in everyday life we call intelligence. My protest to Matt was that I did not believe his definition could be made to lead to anything like a reasonable grounding. I tried to get him to do the grounding, but to no avail: he eventually resorted to the blanket denial that any definition means anything ... which is a cop out if he wanted to defend the claim that the formalism was something more than a mathematical fantasy. Richard Loosemore P.S. Quick sanity check: you know the last comment in the quote you gave (about loking in the dictionary) was Matt's, not mine, right? - 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
Re: [singularity] Scenarios for a simulated universe
Richard, I long ago proposed a working definition of intelligence as Achieving complex goals in complex environments. I then went through a bunch of trouble to precisely define all the component terms of that definition; you can consult the Appendix to my 2006 book The Hidden PatternShane Legg and Marcus Hutter have proposed a related definition of intelligence in a recent paper... Anyone can propose a definition. The point of my objection is that a definition has to have some way to be compared against reality. Suppose I define intelligence to be: A funtion that maps goals G and world states W onto action states A, where G, W and A are any mathematical entities whatsoever. That would make any function that maps X [cross] Y into Z an intelligence. Such a definition would be pointless. The question is *why* would it be pointless? What criteria are applied, in order to determine whether the definition has something to the thing that in everyday life we call intelligence. The difficulty in comparing my definition against reality is that my definition defines intelligence relative to a complexity measure. For this reason, it is fundamentally a subjective definition of intelligence, except in the unrealistic case where degree of complexity tends to infinity (in which case all reasonably general complexity measures become equivalent, due to bisimulation of Turing machines). To qualitatively compare my definition to the everyday life definition of intelligence, we can check its consistency with our everyday life definition of complexity. Informally, at least, my definition seems to check out to me: intelligence according to an IQ test does seem to have something to do with the ability to achieve complex goals; and, the reason we think IQ tests mean anything is that we think the ability to achieve complex goals in the test-context will correlate with the ability to achieve complex goals in various more complex environments (contexts). Anyway, if I accept for instance **Richard Loosemore** as a measurer of the complexity of environments and goals, then relative to Richard-as-a-complexity-measure, I can assess the intelligence of various entities, using my definition In practice, in building a system like Novamente, I'm relying on modern human culture's consensus complexity measure and trying to make a system that, according to this measure, can achieve a diverse variety of complex goals in complex situations... P.S. Quick sanity check: you know the last comment in the quote you gave (about loking in the dictionary) was Matt's, not mine, right? Yes... 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
Re: [singularity] Scenarios for a simulated universe
Definition is intelligence. Kind Regards, Bruce LaDuke Managing Director Instant Innovation, LLC Indianapolis, IN [EMAIL PROTECTED] http://www.hyperadvance.com Original Message Follows From: Ben Goertzel [EMAIL PROTECTED] Reply-To: singularity@v2.listbox.com To: singularity@v2.listbox.com Subject: Re: [singularity] Scenarios for a simulated universe Date: Sun, 04 Mar 2007 14:26:33 -0500 Richard, I long ago proposed a working definition of intelligence as Achieving complex goals in complex environments. I then went through a bunch of trouble to precisely define all the component terms of that definition; you can consult the Appendix to my 2006 book The Hidden PatternShane Legg and Marcus Hutter have proposed a related definition of intelligence in a recent paper... Anyone can propose a definition. The point of my objection is that a definition has to have some way to be compared against reality. Suppose I define intelligence to be: A funtion that maps goals G and world states W onto action states A, where G, W and A are any mathematical entities whatsoever. That would make any function that maps X [cross] Y into Z an intelligence. Such a definition would be pointless. The question is *why* would it be pointless? What criteria are applied, in order to determine whether the definition has something to the thing that in everyday life we call intelligence. The difficulty in comparing my definition against reality is that my definition defines intelligence relative to a complexity measure. For this reason, it is fundamentally a subjective definition of intelligence, except in the unrealistic case where degree of complexity tends to infinity (in which case all reasonably general complexity measures become equivalent, due to bisimulation of Turing machines). To qualitatively compare my definition to the everyday life definition of intelligence, we can check its consistency with our everyday life definition of complexity. Informally, at least, my definition seems to check out to me: intelligence according to an IQ test does seem to have something to do with the ability to achieve complex goals; and, the reason we think IQ tests mean anything is that we think the ability to achieve complex goals in the test-context will correlate with the ability to achieve complex goals in various more complex environments (contexts). Anyway, if I accept for instance **Richard Loosemore** as a measurer of the complexity of environments and goals, then relative to Richard-as-a-complexity-measure, I can assess the intelligence of various entities, using my definition In practice, in building a system like Novamente, I'm relying on modern human culture's consensus complexity measure and trying to make a system that, according to this measure, can achieve a diverse variety of complex goals in complex situations... P.S. Quick sanity check: you know the last comment in the quote you gave (about loking in the dictionary) was Matt's, not mine, right? Yes... 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 _ Play Flexicon: the crossword game that feeds your brain. PLAY now for FREE. http://zone.msn.com/en/flexicon/default.htm?icid=flexicon_hmtagline - 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
Re: [singularity] Scenarios for a simulated universe
--- Richard Loosemore [EMAIL PROTECTED] wrote: Matt Mahoney wrote: --- Richard Loosemore [EMAIL PROTECTED] wrote: What I wanted was a set of non-circular definitions of such terms as intelligence and learning, so that you could somehow *demonstrate* that your mathematical idealization of these terms correspond with the real thing, ... so that we could believe that the mathematical idealizations were not just a fantasy. The last time I looked at a dictionary, all definitions are circular. So you win. Sigh! This is a waste of time: you just (facetiously) rejected the fundamental tenet of science. Which means that the stuff you were talking about was just pure mathematical fantasy, after all, and nothing to do with science, or the real world. Richard Loosemre. What does the definition of intelligence have to do with AIXI? AIXI is an optimization problem. The problem is to maximize an accumulated signal in an unknown environment. AIXI says the solution is to guess the simplest explanation for past observation (Occam's razor), and that this solution is not computable in general. I believe these principles have broad applicability to the design of machine learning algorithms, regardless of whether you consider such algorithms intelligent. -- Matt Mahoney, [EMAIL PROTECTED] - 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
Re: [singularity] Scenarios for a simulated universe
On 3/4/07, Matt Mahoney wrote: What does the definition of intelligence have to do with AIXI? AIXI is an optimization problem. The problem is to maximize an accumulated signal in an unknown environment. AIXI says the solution is to guess the simplest explanation for past observation (Occam's razor), and that this solution is not computable in general. I believe these principles have broad applicability to the design of machine learning algorithms, regardless of whether you consider such algorithms intelligent. Matt, you might want to consider that while Occam's Razor is indeed a very beautiful and powerful principle, it is a heuristic directly applicable only to those situations of all else being equal (or made effectively so by means of infinite computing power.) [Observant readers may notice than I'm being slightly tongue in cheek here, drawing a parallel with a recent mismatch of expressed views on the AGI and Extropy lists regarding the elegance of the Principle of Indifference. The analogy is sublime.] My point is that nature never directly applies the perfect principle. Every problem posed to nature carries an implicit bias, and this is enough to start nature down the path toward a satisficing heuristic. While the Principle of Parsimony and the Principle of Indifference play unattainably objective roles in our epistemology, you may want to consider their subjective cousin, Max Entropy, as one of your star players in any practical AI. - Jef - 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
[singularity] AGI+LE Poll Question (results)
9 people responded to the AGI+LE poll question (How much does life extension motivate your interest in AGI? - full question posted at bottom of this email). I've taken a few sentences from each reply and posted below. I've also compiled a listing of % interest in AGI as motivated by Life Extension. Where the % was not stated explicitly, I have taken liberty (divined) to come up with a guess. Please feel free to correct me. Also, feel free to reply to this thread with more / newer answers, etc. For me, I was surprised to find how low the % was (28%). However, on reflection I can understand that I'm fairly obsessed with the idea of physical immortality as compared to most others ;-) - Bruce ==Results: 25% Joel Pitt (explicit) 50% Stephen Reed (divined) 00% Bruce LaDuke (explicit) 25% Matt Mahoney (divined) 25% Stathis Papaioannou (divined) 75% Ben Quirk (divined) 25% Mark N. (explicit) 00% Patricia Manney (explicit) 25% Vishaka Datta (divined) --- 28% AVERAGE ==Excerpts from replies to AGI+LE Poll Joel Pitt said: So my belief is that the singularity a) enables us to have longer/indefinite life spans with which to experience more. b) will allow us to experience so much more than our current human senses allow us. Of course I also think AGI is an amazing puzzle and will answer questions (and raise new ones) about self awareness, consciousness and intelligence. I also believe that humanity is currently heading towards collapse if some major changes don't happen soon - so if the singularity can help us survive I'm all for it! :) In summary I'd say life extension is only 25% of my interest in it. -- Stephen Reed said: Since the early 1970's I've had as my life goal participation in technologies that would lead either to Life Extension or to Artificial Intelligence, on the theory that if one of these is achieved, the other will follow in my extended lifetime. My confidence has grown over the years as others have taken up these goals and some, e.g. Kurtzweil have explored the connections between them. -- Bruce LaDuke said: My Life Extension motivation is 0% of the reason why I'm interested in AGI+Singularity. I'm interested in AGI+Singularity because I want to bring the knowledge creation process to AGI researchers. I believe that singularity is the realization of artificial knowledge creation. -- Matt Mahoney said: I don't know if I will live long enough to see the Singularity, but the more I think about it, the more I believe it is irrelevant. Once AGI can start improving itself, I think it will quickly advance beyond human intellect as humans are advanced over bacteria I believe the universe is simulated. I don't know why the simulation exists. Maybe there is an AGI working on some problem whose purpose we cannot understand. Maybe it is just experimenting with different universes for fun. Maybe there is no reason at all; the current universe is just one of an enumeration of all Turing machines. --- Stathis Papaioannou said: The important thing as far as survival goes is not that my memories are preserved or that aspects of my life can be repeated, but that I continue to have new experiences from here on, which experiences contain memories of me in their past and identify as being me. That is, if I had a choice between living for 200 years and living for 100 years repeated 10 times (so that I had no idea which cycle I was in), I would not hesitate to choose the 200 years. In block universe theories of time, the past and present are always there, but this is no comfort at all if I can't expect future new experiences. --- Ben Quirk said: [Now] that I try to sit here and answer your question I find it extremely difficult to put into words. I keep erasing and rewriting what I've typed up... I think my interest [is] motivated [by] the fact that greater-than-human intelligence is our best shot at solving all those eternal questions such as what is reality, why does something exist instead of nothing, what is the nature of consciousness... I'm also extremely [in to] life extension and cognitive enhancement. -- Mark N. said: Life extension is about 25% of the reason I am interested in the Singularity. I do not want to live forever in a world like today's world. I am quite unhappy with the state of the world and this country, and it seems like every year I become more cynical. Who knows if this world as it is today is sustainable? My motivations are creating a sustainable and enjoyable world that everybody will like, and reducing the amount of suffering and problems that exist today. As for what I would get personally out of this? It would be nice to party again without destroying brain cells :P. But in all seriousness, I am not too concerned about personally being alive in a post-singularity world. The concern lies with it actually happening. --- Patricia (PJ) Manney said: I'm interested in AGI+Singularity