> >As Moshe pointed out, if one wants to trust to the power of elegant > >generalization, then one can simply trust to the rule I called R_2 in my > >second paper. > > > >This has no emergency patches and no arbitrary set points.. it's > beautiful > >and pretty... > > > >Does this mean it's better than the patched up version? I'm not so sure. > >Elegance is a virtue, but not the only one... > > My point continues to be that the "threat" is from an > evolutionary process larger than ourselves. It's impractical in > principle to try to control it; the best we can do is adapt such > that we can exert the influence of our own values within the > larger system. > -Jef
Jef, I agree strongly with your philosophical point, but I'm not sure what it says regarding the detailed issues I discuss in those essays ... In fact my focus with such futuristic issues tends to be on the "near term" -- on guiding what happens with an AI shortly after it achieves "hard takeoff." I think we can have some control over this, at least. What happens beyond that is even harder to figure given our current state of knowledge. Maybe, as I've suggested before, once an AI reaches IQ of 554444, it is automatically contacted by aliens who rewire its brain ;-) - Ben ------- To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
