Re: [agi] AI Morality -- a hopeless quest
Hi Arthur, On Wed, 12 Feb 2003, Arthur T. Murray wrote: . . . Since the George and Barbara Bushes of this world are constantly releasing their little monsters onto the planet, why should we creators of Strong AI have to take any more precautions with our Moravecian Mind Children than human parents do with their human babies? Because of the power of super-intelligence. Cheers, Bill --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AI Morality -- a hopeless quest
I don't think any human alive has the moral and ethical underpinnings to allow them to resist the corruption of absolute power in the long run. We are all kept in check by our lack of power, the competition of our fellow humans, the laws of society, and the instructions of our peers. Remove a human from that support framework and you will have a human that will warp and shift over time. We are designed to exist in a social framework, and our fragile ethical code cannot function properly in a vacuum. This says two things to me. First, we should try to create friendly AI's. Second, we have no hope of doing it. We will forge ahead anyway because progress is always inevitable. We'll do as good a job as we can. At some point humans will be obsolete, but that's no reason to turn back. I'm also a strong proponent of the idea that humans can be made much better with the addition of enhancements, first through external add-ons (gargoyle type apparati which enhance our minds through UI's that are as intuitively useful as a hammer), and later through direct enhancement of our brains. In summary, I think we are getting ahead of ourselves in thinking we even have the capacity to predict what a friendly AI will be, especially if said AI is hyperintelligent and self-modifying. -Brad --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AI Morality -- a hopeless quest
Arthur T. Murray wrote: [snippage] why should we creators of Strong AI have to take any more precautions with our Moravecian Mind Children than human parents do with their human babies? Here are three reasons I can think of, Arthur: 1) Because we know in advance that 'Strong AI', as you put it, will be very much smarter and very much more capable than we are - that is not true in the human scenario. 2) If we don't get AI morality right the first time (or very close to it), its game over for the human race. 3) Attempting to develop 'Strong AI' without spending time getting the morality-bit correct, may cause a governmental agency to squash you like a bug. And I didn't even have to think very hard to come up with those... I'm sure there are other reasons. Could you articulate the reasons why you think the 'quest' is hopeless? Michael Roy Ames --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AI Morality -- a hopeless quest
Brad Wyble wrote: I don't think any human alive has the moral and ethical underpinnings to allow them to resist the corruption of absolute power in the long run. I am exceedingly glad that I do not share your opinion on this. Human altruism *is* possible, and indeed I observe myself possessing a significant measure of it. Anyone doubting thier ability to 'resist corruption' should not IMO be working in AGI, but should be doing some serious introspection/study of thier goals and motivations. (No offence intended, Brad) Michael Roy Ames --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AI Morality -- a hopeless quest
I am exceedingly glad that I do not share your opinion on this. Human altruism *is* possible, and indeed I observe myself possessing a significant measure of it. Anyone doubting thier ability to 'resist corruption' should not IMO be working in AGI, but should be doing some serious introspection/study of thier goals and motivations. (No offence intended, Brad) Michael Roy Ames None taken. I'm altruistic myself, to a fault oftentimes. I have no doubt of my ability to help my fellow man. I bend over backwards to help complete strangers without a care because it makes me feel good. I am a friendly person. But that word fellow is the key. It implies peers, relative equals. I don't think I, or you, or anyone, can expect our personal ethical frameworks to function properly in a situation like that a hyperintelligent AI will face. Tell me this, have you ever killed an insect because it bothered you? -Brad --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AI Morality -- a hopeless quest
On Wed, 12 Feb 2003, Arthur T. Murray wrote: The quest is as hopeless as it is with human children. Although Bill Hibbard singles out the power of super-intelligence as the reason why we ought to try to instill morality and friendliness in our AI offspring, such offspring are made in our own image and likeness: receptive to parental ideas, but ultimately on their own. We better not make them in our own image. We can make them with whatever reinforcement values we like, rather than the ones we humans were born with. Hence my often repeated suggestion that they reinforce behaviors according to human happiness. DISCLAIMERS - In less than one hour I will go on a mountain day-trip and not be on-line to answer even the most personal queries. Have fun, Bill --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AI Morality -- a hopeless quest
I can't imagine the military would be interested in AGI, by its very definition. The military would want specialized AI's, constructed around a specific purpose and under their strict control. An AGI goes against everything the military wants from its weapons and agents. They train soldiers for a long time specifically to beat the GI out of them (har har, no pun intended) so that they behave in a predictable manner in a dangerous situation. And while I'm not entirely optimistic about the practicality of building ethics into AI's, I think we should certainly try, and that rules military funding right out. -Brad --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AI Morality -- a hopeless quest
Brad Wyble wrote: Tell me this, have you ever killed an insect because it bothered you? In other words, posthumanity doesn't change the goal posts. Being human should still confer human rights, including the right not to be enslaved, eaten, etc.. But perhaps being posthuman will confer posthuman rights that we understand as little as a dog understands the right to vote. -- James Hughes -- Eliezer S. Yudkowsky http://singinst.org/ Research Fellow, Singularity Institute for Artificial Intelligence --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AI Morality -- a hopeless quest
Hello All.. After reading all this wonderful debate on AI morality and Eliezer's People eating AGI concerns, I'm left wondering this: Am I the *only* one here who thinks that the *most* likely scenario is that such a thing as a universe devouring AGI is utterly impossible? Everyone here seems to talk about this as if it was inevitable and probable. Just because we can dream of something, does not mean it can exist anywhere except our dreams. For instance, time travel has not been entorely refuted as of yet, but that doesn't mean it is practically doable in any way. These discussions seem especially far fetched given that this damn computer doesn't have the slightest idea what I am typing in right now or what it means ;) I think an AGI is *very* plausible and probably imminent. I also think Eliezer is right in that we have to give strong consideration to the ethics of such a machine as they could be dangerous, if even just economically dangerous by crashing financial markets or whole countries economies. They could also potentially use all our own wonderful killing machines against us. But the idea that they will manipulate matter and devour the universe is ludicrous IMO. I am much more inclined to believe that an AGI of tremendous utility will emerge that will be a tool for our use in almost any scientific\engineering\medical\educational etc etc domain. If such a thing as a matter manipulating machine were possible, it should have happened already in this universe. This leads to one of three conclusions as far as I can tell: 1) matter manipulating machines of such a grand scale are not possible 2) mmm's are possible, but never actually do such a thing 3) mmm's are possible and they created this current universe as a simulation ala The Matrix. My bet is on number 1. But none of these three are horrible. Of course, an AGI could be destructive only on the local level, and that is where we have to be wary. I am glad that Ben is working on this and may be closer to succeeding than anyone else. I believe he sincerely has altruistic motives and is open minded enough to consider others thoughts\concerns. That will mean alot as this project progresses towards completion.. Kevin - Original Message - From: Eliezer S. Yudkowsky [EMAIL PROTECTED] To: [EMAIL PROTECTED] Sent: Wednesday, February 12, 2003 1:53 PM Subject: Re: [agi] AI Morality -- a hopeless quest Brad Wyble wrote: Tell me this, have you ever killed an insect because it bothered you? In other words, posthumanity doesn't change the goal posts. Being human should still confer human rights, including the right not to be enslaved, eaten, etc.. But perhaps being posthuman will confer posthuman rights that we understand as little as a dog understands the right to vote. -- James Hughes -- Eliezer S. Yudkowsky http://singinst.org/ Research Fellow, Singularity Institute for Artificial Intelligence --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED] --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AI Morality -- a hopeless quest
- Original Message - From: Philip Sutton To: [EMAIL PROTECTED] Sent: Wednesday, February 12, 2003 2:55 PM Subject: Re: [agi] AI Morality -- a hopeless quest Brad, Maybe what you said below is the key to friendly GAI I don't think any human alive has the moral and ethical underpinnings to allow them to resist the corruption of absolute power in the long run. We are all kept in check by our lack of power, the competition of our fellow humans, the laws of society, and the instructions of our peers. Remove a human from that support framework and you will have a human that will warp and shift over time. We are designed to exist in a social framework, and our fragile ethical code cannot function properly in a vacuum. If we create a *community* of AGIs that have ethics orientated architecture/ethical training then *they* might stand a chance of policing themselves. The situation is analagous to how we try (so far with not enough success, but with improving odds) to protect non-human species. Humans are the biggest threat to non-human species (well demonstrated) but there are more and more efforts being made by humans to stop that and to provide other species a chance to survive and continue evolving. I think that we need to structure and train AGIs knowing that the same scenario could be played out in relation to us as has happened between us and less poweful life - but we have the advantages that: - we've seen where WE went wrong - we can shape the deep ethical structure of AGIs from the start with this meta issue in mind. Cheers, Philip I would second this, and note for the record the instance of the defense of the treatment of women in traditional societies. In places like Pakistan and Arabia, apologists defend the second-class status of women by saying that they are being "protected" by their male relatives. But without the ability to protect their own safety and status, such "protection" becomes honor killings and FGM. The only guarantee of protection and rights is to give womenthe ability to protect themselves, and that's a tremendous cultural change. Especially when such cultural traditions are claimed to be mandated by God. I guess the relevance here is that Philip has reached the core of this issue. There are no guarantees in this business, especially when trying to predict the behavior of complex adaptive entities with cognitive abilities that we are assuming will be greater than ours. Thus, the only safeguard is the classic one: division of power. C. David NozigliaObject Sciences Corporation6359 Walker Lane, Alexandria, VA(703) 253-1095 "What is true and what is not? Only God knows. And, maybe, America." Dr. Khaled M. Batarfi, Special to Arab News "Just because something is obvious doesn't mean it's true." --- Esmerelda Weatherwax, witch of Lancre
Re: [agi] AI Morality -- a hopeless quest
On Wed, 12 Feb 2003, Brad Wyble wrote: I can't imagine the military would be interested in AGI, by its very definition. The military would want specialized AI's, constructed around a specific purpose and under their strict control. An AGI goes against everything the military wants from its weapons and agents. They train soldiers for a long time specifically to beat the GI out of them (har har, no pun intended) so that they behave in a predictable manner in a dangerous situation. And while I'm not entirely optimistic about the practicality of building ethics into AI's, I think we should certainly try, and that rules military funding right out. As an employee at Cycorp, a DARPA sub-contractor, and as project manager for Cycorp's Terrorism Knowledge Base participation in the DARPA GENOA II program, I believe that the military would be very interested in AGI *because* of its definition. A hierarchical military AGI would bottom out in weapon systems but the General aspect of it facilitates coordination at the battlespace level - involving forces from all services and allies. With the growing military acceptance of Effects Based Operations, national objectives assigned to our military can be accomplished by means other than putting metal on a target. EBO is implemented by Bayesian nets which I imagine will be in the toolbox of any AGI group posting here. In opposition to the military aspect of your second point, I am very comfortable with the building of ethics into an AI and at the moment subscribe the Friendly AI principles which I believe can be straight forwardly expressed in the Cyc symbolic logic vocabulary and whose causal goal structure can be the basis of future Cyc active, self-improving behavior. Furthermore, I believe that our culture entrusts the military with awesome destructive power because of civilian oversight, legal constraints and the ethical structure developed and taught to military personnel of all ranks. For operational ethics, I certainly would accept the teachings of our military academies and staff schools. And I can provide web site links for anyone interested. Civilian oversight is already a reality for my AI work. For example, the GENOA II program is funded by the DARPA Information Awareness Office whose actives will be subject to congressional scrutiny and possible termination if the current funding bill becomes law. I believe that as evidence of AGI (e. g. software that can learn from reading) becomes widely known: (1) the military will provide abundant funding - possibly in excess of what commercial firms could do without a consortium (2) public outcry will assure that military AGI development has civilian and academic oversight. -Steve -- === Stephen L. Reed phone: 512.342.4036 Cycorp, Suite 100 fax: 512.342.4040 3721 Executive Center Drive email: [EMAIL PROTECTED] Austin, TX 78731 web: http://www.cyc.com download OpenCyc at http://www.opencyc.org === --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] AI Morality -- a hopeless quest
As has been pointed out on this list before, the military IS interested in AGI, and primarily for information integration rather than directly weapons-related purposes. See http://www.darpa.mil/body/NewsItems/pdf/iptorelease.pdf for example. -- Ben G I can't imagine the military would be interested in AGI, by its very definition. The military would want specialized AI's, constructed around a specific purpose and under their strict control. An AGI goes against everything the military wants from its weapons and agents. They train soldiers for a long time specifically to beat the GI out of them (har har, no pun intended) so that they behave in a predictable manner in a dangerous situation. And while I'm not entirely optimistic about the practicality of building ethics into AI's, I think we should certainly try, and that rules military funding right out. -Brad --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED] --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
Re: [agi] AI Morality -- a hopeless quest
Brad Wyble wrote: Under the ethical code you describe, the AGI would swat them like a bug with no more concern than you swatting a mosquito. I did not describe an ethical code, I described two scenarios about a human (myself) then suggested the non-bug-swatting scenario was possible, analogically, for an AGI. All I'm trying to do is shift the focus for a few moments to our own ethical standards as people. If we were put into the shoes of an AGI, would we behave well towards the inferior species? I presume from the phrase If we were put into the shoes of an AGI that human morality and ethics would come along for the ride. If that is what you meant: then it depends on which human you pick as to what happens. I have observed both altruism and cruelty, obsession and indifference in human behaviour toward other species. It bears some thinking about just exactly what one would do in such a situation... I know I have often thought about it. Philip brings up the point that a community AGI's could possibly self-police. I agree. I don't. Policing is only useful/meaningful within a community of almost equal actors that have very little real power. If the actors are not almost equally powerful then you have the 'human and a bug' scenario. If the actors have a very large amount of power, then a single 'transgression' could wipe us all out before any 'policing action' could be initiated. Nor, would one presume, on an AGI's. They might end up with it anyway. I would not presume that so readily. Taking it as a given that we are discussion a Friendly AGI, I would say that there would be significant utility in obtaining a great deal of power. Not to 'Lord it over the petty humans', but to protect them both internal and external threats. Michael Roy Ames --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] AI Morality -- a hopeless quest
Daniel, For a start look at the IPTO web page and links from: http://www.darpa.mil/ipto/research/index.html Darpa has a variety of Offices which sponsor AI related work, but IPTO is now being run by Ron Brachman, the former president of the AAAI. When I listened to the talk he gave a Cycorp in December he spoke of his strong desire to fund AI, if we can tell a compelling story. His budget could be as much as $50 - $100 million per year - if he develops good reseach programs that withstand the competitive pressure for funds from the other DARPA offices. Other government agencies fund work and we submit SBIR proposals when the research objective sufficiently overlaps our core work. -Steve On Wed, 12 Feb 2003, Daniel Colonnese wrote: I believe that as evidence of AGI (e. g. software that can learn from reading) becomes widely known: (1) the military will provide abundant funding - possibly in excess of what commercial firms could do without a consortium (2) public outcry will assure that military AGI development has civilian and academic oversight. Steve, Ben, do you have any gauge as too what kind of grants are hot right now or what kind of narrow AI projects with AGI implications have recently been funded through military agencies? -- === Stephen L. Reed phone: 512.342.4036 Cycorp, Suite 100 fax: 512.342.4040 3721 Executive Center Drive email: [EMAIL PROTECTED] Austin, TX 78731 web: http://www.cyc.com download OpenCyc at http://www.opencyc.org === --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
RE: [agi] AI Morality -- a hopeless quest
Steve, Ben, do you have any gauge as too what kind of grants are hot right now or what kind of narrow AI projects with AGI implications have recently been funded through military agencies? The list would be very long. Just look at the DARPA IPTO website for starters... http://www.darpa.mil/ipto/ And while I'm not entirely optimistic about the practicality of building ethics into AI's, I think we should certainly try, and that rules military funding right out. Yeah, it seems like somewhat of a *moral compromise* to pursue narrow AI research funding with the hopes of creating doing work which may help to one day create AGI. Or as Sartre said: I don't agree that receiving military funding for specific purposes rules out creating an ethical AGI, nor that doing narrow AI work is a moral compromise. For example, suppose one accepts military funding to create an AI application aimed at computer network security. Suppose one creates this application using parts of one's in-development AGI codebase. But, suppose one retains ownership of one's AGI codebase. Where's the ethical dilemma here? In the fact that, theoretically, the military could take one's computer security code and repurpose it for violent intents? There is a bit of an ethical dilemma here, but it is a narrow-AI ethical dilemma, not an AGI ethical dilemma. Because one may still train one's AGI oneself, using one's own ethical principles... -- Ben --- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]