Kevin, I am not sure that we mean the same thing by "sense of self."
I wonder if you could clarify your definition? Ben > -----Original Message----- > From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]]On > Behalf Of maitri > Sent: Thursday, January 09, 2003 4:19 PM > To: [EMAIL PROTECTED] > Subject: Re: [agi] Friendliness toward humans > > > > > 1) > > Since we humans will be teaching the AGI, and it will be learning by > > interacting with humans and reading human literature, it will absorb > > something of the human sense of self > > I agree that our emodiment, along with our senses, is a primary source of > our sense of self. As I look out my window, I see trees and > houses. When I > look down I see my legs and hand. So There is *me* here, and all > that other > *stuff* out there. So I *must* be a separate self. > > An Intelligent person thinking more deeply realizes that what we call the > self is made totaly of non-self items. So setting aside metaphysical > concepts for the moment, i can even practically see that I am > made of stars, > and oceans and clouds and dirt and animals and air and conversations etc. > etc. etc. So the idea of non-self is not so great a leap..but i digress.. > > For a computer, the idea of self will be more nebulous for sure. But I am > not comforted by the idea that just because they have a more > disparate self, > that they will in any sense be less harmful. In fact, if its ego equates > with its size, it may even be worse than humans!! ;) > > I'm not convinced that conversing with humans will make it more human, or > develop a sense of self. Its all in the code, as I see it. How is the > structure set up? Are there links where the idea of self preservation can > be developed? The machine does not *really* need to have a sense > of self to > be dangerous, just to have an algorithm that encodes self protective like > actions will be enough to spawn potentially dangerous behavior...IMO > > I'm not convinced that a sense of self is required to develop an AGI. Of > course, a computer that understands that its a computer, and that > humans and > the rest of the world are "out there", is more useful than one > that doesn't > understand this most basic of concepts. But this level of understanding > does not constitute a *self* that I would be worried about... > > I think an AGI can exceed humans in many or most ways, yet still have no > sense of self or self preservation... > > In fact, we have computers that do this today, but only in > specific domains. > I am stating that I think the same is possible for a more general > intelligence as well... > > But I think we all can admit that once an AGI grows and grows and > especially > if it can self modify, that something tantamount to *self* or > conscioussness > might emerge... > > Kevin > > > ------- > > 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] > ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/?[EMAIL PROTECTED]
