On Oct 25, 3:25 am, Bruno Marchal <[EMAIL PROTECTED]> wrote:
> Le 25-oct.-07, à 03:25, Wei Dai a écrit :
> > Rolf Nelson wrote:
> >> An example
> >> that Yudowsky gave: you might spend resources on constructing a unique
> >> arrow pointing at yourself, in order to increase your measure by
> >> making it easier for a search algorithm to find you.
> > While I no longer support UD+ASSA at this point (see my posts titled
> > "against UD+ASSA"), I'm not sure this particular example is especially
> > devastating. UD+ASSA perhaps implies an ethical theory in which all
> > else
> > being equal, you would prefer that there was a unique, easy to find
> > arrow
> > pointing at yourself. But it doesn't say that you should actually spend
> > resources constructing it, since those resources might be better used
> > in
> > other ways, and it's not clear how much one's measure would actually be
> > increased by such an arrow.
> I am not sure who "reads" that arrow, or even what *is* that arrow.
> Bruno

How about SAI (Super Intelligence)?  Or God?  Seriously, of course.
The problem with generic SAI is the one you brought up: how do you
know the SAI is good?  This problem does not exist with a good God.
Also the problem of what is the arrow, how do you make it, does not
exist with the Christian God, since the Christian God (and no other
one) made the arrow himself.


You received this message because you are subscribed to the Google Groups 
"Everything List" group.
To post to this group, send email to [EMAIL PROTECTED]
To unsubscribe from this group, send email to [EMAIL PROTECTED]
For more options, visit this group at 

Reply via email to