On 13 Apr 2015, at 08:29, Bruce Kellett wrote:
Russell Standish wrote:
Thanks Bruce, that was quite illuminating. I know Bruno will say that
these other notions of personal identity contradict COMP - and I can
see that considering the original copy as dead, and two new persons
being created directly contradicts the "Yes, doctor" postulate. But I
can see it may be pertinent to discuss these alternate notions of
personal identity in a computationalist setting.
I have found Nozick's discussion in 'Philosophical Explanations'
quite helpful. For instance, he points out that the notions of a
'closest continuer' clearly depends on the parameters and metric
used. He floats the idea that different people could differ about
this, so one person's closest continuer may not be the same as
another's. I think this might be interesting in the comp situation.
As I have said elsewhere, I do not think that a complete reading of
my current brain state is possible, since the brain would be
destroyed before the reading could be completed. Thus my ideas of
personal identity might well not apply to the notions of a native AI
being.
If AI is created, not simply as a copy of existing humans but from
scratch, as it were, then their consciousness may not be the same as
ours, and their ideas of closest continuers might well be different.
No problem. I assume comp as working hypothesis.
How can we easily think about this when we cannot actually go out
and ask a functional AI what (s)he thinks?
This is exactly what has been already done. See the part 2 of sane04,
where we interview a universal (Löbian) machine on UDA, and extract
the logic of the observable in the way UDA forces us to do. The hard
work has been done by the logician (Gödel, Löb, Solovay, and others).
Bruno
Bruce
--
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.
http://iridia.ulb.ac.be/~marchal/
--
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.
