On 2/10/2015 8:47 AM, Jason Resch wrote:
If you define increased intelligence as decreased probability of having a false belief
on any randomly chosen proposition, then superintelligences will be wrong on almost
nothing, and their beliefs will converge as their intelligence rises. Therefore nearly
all superintelligences will operate according to the same belief system. We should stop
worrying about trying to ensure friendly AI, it will either be friendly or it won't
according to what is right.
The problem isn't beliefs, it's values. Humans have certain core values selected by
evolution; and in addition they have many secondary culturally determined values. What
values will super-AI have and where will it get them and will they evolve? That seems to
be the main research topic at the Machine Intelligence Research Institute.
Brent
I think chances are that it will be friendly, since I happen to believe in universal
personhood, and if that belief is correct, then superintelligences will also come to
believe it is correct. And with the belief in universal personhood it would know that
harm to others is harm to the self.
Jason
On Tue, Feb 10, 2015 at 2:19 AM, Alberto G. Corona <[email protected]
<mailto:[email protected]>> wrote:
I can´t even enumerate the number of ways in which that article is wrong.
First of all, any intelligent robot MUST have a religion in order to act in
any way.
A set of core beliefs. A non intelligent robot need them too: It is the set
of
constants. The intelligent robot can rewrite their constants from which he
derive
their calculations for actions and if the robot is self preserving and
reproduce
sexually, it has to adjust his constants i.e. his beliefs according with
some
darwinian algoritm that must take into account himself but specially the
group in
which he lives and collaborates..
If the robot does not reproduce sexually and his fellows do not execute
very similar
programs, it is pointless to teach them any human religion.
These and other higher aspects like acting with other intelligent beings
communicate
perceptions, how a robot elaborate philosophical and theological concepts
and
collaborate with others, see my post about "robotic truth"
But I think that a robot with such level of intelligence will never be
possible.
2015-02-09 21:59 GMT+01:00 meekerdb <[email protected]
<mailto:[email protected]>>:
In two senses of that term! Or something.
http://bigthink.com/ideafeed/robot-religion-2
http://gizmodo.com/when-superintelligent-ai-arrives-will-religions-try-t-1682837922
--
You received this message because you are subscribed to the Google Groups
"Everything List" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To post to this group, send email to [email protected].
Visit this group at http://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/d/optout.
