--- BillK <[EMAIL PROTECTED]> wrote: > On 7/2/07, Tom McCabe wrote: > > > > AGIs do not work in a "sensible" manner, because > they > > have no constraints that will force them to stay > > within the bounds of behavior that a human would > > consider "sensible". > > > > > If you really mean the above, then I don't see why > you are bothering > to argue on this list. > (Apart from enjoying all the noise and excitement). > > You believe that an AGI has no constraints on it's > behaviour, so why > argue about what it might or might not do?
You're right - arguing about "what an AGI will do" makes no sense, because AGIs in general can do anything. But you can argue about "what the vast majority of AGIs will do", which is what I usually meant, or what an AGI with some specific design will do, which is what I might have meant in context. > Your case is that AGI might do *anything*. Yes, if you're referring to all possible AGIs. > This list thinks that AGI will arrive whatever we > do. So why not try > and ensure humanity will survive the experience? Er, that's exactly my point- since most AGIs will destroy us, and we know that an AGI can follow any arbitrary behavior, why not build one that follows patterns of behavior we will see as nice, and which will more importantly protect us from other AGIs? > > BillK > > ----- > 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/?& > - Tom ____________________________________________________________________________________ Sick sense of humor? Visit Yahoo! TV's Comedy with an Edge to see what's on, when. http://tv.yahoo.com/collections/222 ----- 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/?member_id=4007604&id_secret=9034744-e4e9e5