Brent Meeker writes:
> >> Pain is limited on both ends: on the input by damage to the physical
> >> circuitry and on the response by the possible range of response.
> >
> > Responses in the brain are limited by several mechanisms, such as
> > exhaustion of neurotransmitter stores at synapses, negative feedback
> > mechanisms such as downregulation of receptors, and, I suppose, the
> > total numbers of neurons that can be stimulated. That would not be a
> > problem in a simulation, if you were not concerned with modelling the
> > behaviour of a real brain. Just as you could build a structure 100km
> > tall as easily as one 100m tall by altering a few parameters in an
> > engineering program, so it should be possible to create unimaginable
> > pain or pleasure in a conscious AI program by changing a few parameters.
>
> I don't think so. It's one thing to identify functional equivalents as 'pain' and 'pleasure'; it's something else to claim they have the same scaling. I can't think of anyway to establish an invariant scaling that would apply equally to biological, evolve creatures and to robots.
Take a robot with pain receptors. The receptors take temperature and convert it
to a voltage or current, which then goes to an analogue to digital converter, which
inputs a binary number into the robot's central computer, which then experiences
pleasant warmth or terrible burning depending on what that number is. Now, any
temperature transducer is going to saturate at some point, limiting the maximal
amount of pain, but what if you bypass the transducer and the AD converter and
input the pain data directly into the computer? Sure, there may be software limits
specifying an upper bound to the pain input (eg, if x>100 then input 100), but what
theoretical impediment would there be to changing this? You would have to show
that pain or pleasure beyond a certain limit is uncomputable.
Stathis Papaioannou
_________________________________________________________________
Be one of the first to try Windows Live Mail.
http://ideas.live.com/programpage.aspx?versionId=5d21c51a-b161-4314-9b0e-4911fb2b2e6d
--~--~---------~--~----~------------~-------~--~----~
You received this message because you are subscribed to the Google Groups "Everything List" group.
To post to this group, send email to everything-list.domain.name.hidden
To unsubscribe from this group, send email to everything-list-unsubscribe.domain.name.hidden
For more options, visit this group at
http://groups.google.com/group/everything-list?hl=en
-~----------~----~----~----~------~----~------~--~---
Received on Mon Jan 01 2007 - 22:51:31 PST