Brent meeker writes:
>> >and if so what would determine if that negative > emotion is pain,
>> disgust, loathing or something completely different > that no
>> biological organism has ever experienced?
>>
>> I'd assess them according to their function in analogy with biological
>> system
Bruno Marchal writes:
> You seem to be including in your definition of the UM the
> *motivation*, not just the ability, to explore all mathematical
> objects. But you could also program the machine to do anything else
> you wanted, such as self-destruct when it solved a particular theorem.
SP: ' I don't thereby think it is OK for anyone to do any horrible thing
they want. I have my own values, as it happens broadly in agreement with
what you have outlined below.'
MP: I assumed as such :-)
Furthermore I tend to think that we also will agree on a tenet I believe
is attributed
Stathis Papaioannou wrote:
Tom Caylor writes (quoting Bruno Marchal):
[TC]
> > My whole argument is that without it our hope eventually runs out and
> > we are left with despair, unless we lie to ourselves against the
> > absence of hope.
[BM]
> Here Stathis already give a genuine comment
Tom Caylor wrote:
I tried to address everything but ran out of time/energy. If there is
something I deleted from a previous post that I cut out that you wanted
me to address, just bring it back up.
Bruno Marchal wrote:
Le 26-d c.-06, 19:54, Tom Caylor a crit :
>
> On Dec 26, 9:51 am, Bru
Stathis Papaioannou wrote:
Brent Meeker writes:
> Do you not think it is possible to exercise judgement with just a >
hierarchy of motivation?
Yes and no. It is possible given arbitrarily long time and other
resources to work out the consequences, or at least a best estimate of
the con
Stathis Papaioannou wrote:
Jef Allbright writes:
My personal experience is that there's no paradox at all if one is
willing to fully accept that within any framework of description there
is absolutely no difference at all between a person and a zombie, but
even the most philosophically co
Thanks Bruno. Much of your terminology at this point escapes me.
I do see that a small part of our differences below are simply due to the
imprecision of language (and my somewhat sloppy writing.)
I also sense that at the core of much of this discussion is the idea that, although we are
subj
Stathis Papaioannou wrote:
I realised when I was about 12 or 13 years old that there
could not be any ultimate meaning. I was very pleased and
excited with this discovery, and ran around trying to explain
it to people (mostly drawing blank looks, as I remember).
It seemed to me just another i
Stathis Papaioannou wrote:
Jef Allbright writes:
My personal experience is that there's no paradox
at all if one is willing to fully accept that within
any framework of description there is absolutely
no difference at all between a person and a
zombie, but even the most philosophically cogn
Le 29-déc.-06, à 10:57, Tom Caylor a écrit :
I tried to address everything but ran out of time/energy. If there is
something I deleted from a previous post that I cut out that you wanted
me to address, just bring it back up.
No problem, Tom. In fact I will print your post and read it comfo
Bruno -
It appears that you and I have essential agreement on our higher-level
epistemology.
But I don't know much about your "comp" so I'll begin reading.
- Jef
Bruno Marchal wrote:
> With increasing context of self-awareness, subjective values
> increasingly resemble principles of the
Le 29-déc.-06, à 10:39, Stathis Papaioannou a écrit :
You seem to be including in your definition of the UM the
*motivation*, not just the ability, to explore all mathematical
objects. But you could also program the machine to do anything else
you wanted, such as self-destruct when it solved
Le 28-déc.-06, à 21:54, Brent Meeker a écrit : (to Jef)
I think "objective" should just be understood as denoting subjective
agreement from different viewpoints.
Curiosuly enough perhaps I could agree if you were saying "physically
objective" can be understood as denoting subjective agree
Hi Jef,
Please, don't hesitate to skip the remarks you could find a bit too
technical, but which could help others who know perhaps a bit more on G
and G*, which are theories which I use to tackle many questions in this
list. You can come back on those remarks if ever
you got time and motiva
Tom Caylor writes (quoting Bruno Marchal):
[TC]
> > My whole argument is that without it our hope eventually runs out and
> > we are left with despair, unless we lie to ourselves against the
> > absence of hope.
[BM]
> Here Stathis already give a genuine comment. You are just admitting
> yo
I tried to address everything but ran out of time/energy. If there is
something I deleted from a previous post that I cut out that you wanted
me to address, just bring it back up.
Bruno Marchal wrote:
Le 26-d c.-06, 19:54, Tom Caylor a crit :
>
> On Dec 26, 9:51 am, Bruno Marchal <[EMAIL P
Bruno Marchal writes:
Le 28-déc.-06, à 01:32, Stathis Papaioannou a écrit :
>
>
> Bruno Marchal writes:
>
>> > OK, an AI needs at least motivation if it is to do anything, and we
>> > could call motivation a feeling or emotion. Also, some sort of >
>> hierarchy of motivations is needed if i
Jef Allbright writes:
My personal experience is that there's no paradox at all if one is
willing to fully accept that within any framework of description there
is absolutely no difference at all between a person and a zombie, but
even the most philosophically cognizant, being evolved human
Le 27-déc.-06, à 19:39, Brent Meeker a écrit :
I do infer from experience that there is some reality. Sometime ago,
Bruno wrote:
"Hence a Reality, yes. But not necessarily a physical reality. Here is
the logical dependence:
NUMBERS -> "MACHINE DREAMS" -> PHYSICAL -> HUMANS -> PHYSICS ->
NUM
Le 27-déc.-06, à 23:40, Jef Allbright a écrit :
Bruno Marchal wrote:
Le 27-déc.-06, à 19:10, Jef Allbright a écrit :
All meaning is necessarily within context.
OK, but all context could make sense only to
some universal meaning. I mean I don't know,
it is difficult.
But this can be se
Le 28-déc.-06, à 01:32, Stathis Papaioannou a écrit :
Bruno Marchal writes:
> OK, an AI needs at least motivation if it is to do anything, and we
> could call motivation a feeling or emotion. Also, some sort of >
hierarchy of motivations is needed if it is to decide that saving the
> wor
Mark,
Let me make it clear at this late point in the debate that, just because I
don't believe there is any absolute morality, I don't thereby think it is OK
for anyone to do any horrible thing they want. I have my own values, as it
happens broadly in agreement with what you have outlined be
Brent Meeker writes:
> Do you not think it is possible to exercise judgement with just a
> hierarchy of motivation?
Yes and no. It is possible given arbitrarily long time and other resources to
work out the consequences, or at least a best estimate of the consequences, of
actions. Bu
24 matches
Mail list logo