Quentin Anciaux wrote:
> 2008/8/13 Brent Meeker <[EMAIL PROTECTED]>:
>> I've been following this back-and-forth with interest.  The above leads to an
>> interesting question which I will raise after a couple of background points.
>> First, I don't think a conscious AI can exist independent of some 
>> environment of
>> which it is conscious.  Of course this doesn't mean you can't create an AI
>> which, like us, is conscious of this particular world.
> 
> Agreed.
> 
>> Second, I think a
>> conscious AI must necessarily remember and learn.  A consequence of these 
>> two is
>> that if you copy an AI the two copies will immediately start to diverge due 
>> to
>> different experiences.
> 
> If we can build an AI we control it and we can give to it input in
> whatever way we like, even slowing it down, stopping it, dumping
> memory, restore a copy, record input from the world to the AI,
> (including clock time, etc) restore another copy and restart it 1 hour
> later than the first restore and feed the recorded input data. The two
> should do the same, it's a computation, it's deterministic. 

In principle we could create and artificial environment for two copies of the 
AI 
and keep them identical.  But then it's a metaphysical question as to whether 
there are two separate consciousness.  If consciousness is computation then 
"same computation"="same consciousness".  The usual form of duplication that 
Bruno postulates contemplates two copies at separate places in this world - in 
which case they do diverge immediately.

> If they
> diverge having the same input (and being the same program)  then there
> is magic somewhere.

Or quantum mechanical uncertainty.

Brent Meeker


> 
>> So the indeterminancy will immediately vanish.
> 
> They can be the same as long as you which.
> 
>> There
>> will be two different consciousnesses; which is perfectly ordinary except 
>> that
>> they will share a lot of memories.  So what does this have to do with MMW?
> 
> What is the status of "mind" ?
> 
>> Brent Meeker
>>
> 
> Regards,
> Quentin Anciaux


--~--~---------~--~----~------------~-------~--~----~
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 
http://groups.google.com/group/everything-list?hl=en
-~----------~----~----~----~------~----~------~--~---

Reply via email to