--- Charles D Hixson <[EMAIL PROTECTED]> wrote: > Tom McCabe wrote: > > -... > > To quote: > > > > "I am not sure you are capable of following an > > argument" > > > > If I'm not capable of even following an argument, > it's > > a pretty clear implication that I don't understand > the > > argument. > > > You have thus far made no attempt that I have been > able to detect to > justify the precise number that you used. And it > was a very precise > number. It wasn't a statement of "in the large > majority of cases", > which might well have been defensible.
Okay. Suppose you are given a universe, which is completely devoid of everything we find hospitable to us- no nice temperate environments, no cozy oxygen atmospheres, no organic pre-made food sources. Given an arbitrary AGI, who did whatever you wanted, following your *intentions* as well as the latter of your request (which is a huge challenge in and of itself), how long would your instructions have to be to specify a universe that could sustain humanity? A page? Two pages? Even a single sentence, with eighty ASCII characters, implies that there are roughly 2,348,542,582,773,833,227,889,480,596,789,337,027,375,682,548,908,319,870,707,290,971,532,209,025,114,608,443,463,698,998,384,768,703,031,934,976 (= 2^360, eighty characters * one byte per character * 4.5 bits of entropy per byte in a random book-length English text) possible AGIs that did something else which did not create a hospitable environment for humanity. Therefore, if you were to build an AGI with goals that were chosen completely at random within this 360-bits-of-complexity bound, the odds are (number of possible sets of instructions which specify a human friendly universe in one sentence)/(ridiculously huge number quoted above) of the human race surviving. Obviously this is give-or-take a few orders of magnitude, but the odds are so ridiculous that it seems like a bet on macroscopic quantum phenomena. QED. > I would have said that you don't appear to *chose* > to follow the > argument. In either case, it renders debating with > you of dubious > utility. If you didn't raise so many interesting > points I would > probably consider you a troll. As it is, my > suspicion is that you have > no grounding in statistics or other math which > includes probability theory. Please back up this assertion. I don't claim any professional training in either subject, but your claim implies that you have spotted some stupid mistakes I have made, and I would very much like those to be pointed out. > > ----- > 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 ____________________________________________________________________________________ It's here! Your new message! Get new email alerts with the free Yahoo! Toolbar. http://tools.search.yahoo.com/toolbar/features/mail/ ----- 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=9729576-33f880
