On 3/27/2015 4:06 AM, Quentin Anciaux wrote:
2015-03-27 11:44 GMT+01:00 LizR <lizj...@gmail.com <mailto:lizj...@gmail.com>>:
On 27 March 2015 at 23:24, Quentin Anciaux <allco...@gmail.com
<mailto:allco...@gmail.com>> wrote:
2015-03-27 10:12 GMT+01:00 LizR <lizj...@gmail.com
<mailto:lizj...@gmail.com>>:
On 27 March 2015 at 19:28, Quentin Anciaux <allco...@gmail.com
<mailto:allco...@gmail.com>> wrote:
The ab asurdo is showing computationalism is incompatible with
physical
supervenience, not that it is true.
Yes sorry, "reject" was a poor choice of words. I meant argue from
the comp
position rather than the materialist one, and know what I'm talking
about.
In the end by being forced to accept consciousness must
supervene on the
movie + broken gate... If you believe it, then you've abandon
computationalism as a theory of the mind as the movie+broken
gates is
not a computation... Or you can keep computationalism and
abandon
physical supervenience.... QED
Yes I realise that. The same applies to Maudlin. All I wanted to
know at the
moment was how the contradiction arises in the MGA.
It seems to me that's what I explained...
I'm sure it does. As I said, I can't quite get my head around it, so it's
unlikely a
quick overview is going to help me do so. (After all I couldn't follow
Bruno's
explanation, which involved smoke and mirrors, or something similar.) Maybe
I'm just
the wrong type of geek to be able to grok this argument, but I keep trying.
it arises because under computationalism, it is assumed consciousness is
supported by a computation.... under computationlism + physical
supervenience,
it assumed the computation is eventually supported by physcial activity
and
eventually this leads to attribute consciousness to the record, which
is not a
computation, contradicting the assumption of computationalism...
Yes, I can see that if you are led to attribute consciousness to a record
then that
will contradict the original assumption. But I haven't yet been able to see
how the
MGA leads to attributing consciousness to a record. I'm sure it does show
that, but
for me it doesn't quite click. Maybe I'm doomed to never get an intuitive
grasp of
the argument.
1- It is assumed you have a machinery/program that is conscious. (a real
conscious AI)
2- You have (for example) a conversation with it.
3- While doing that conversation, you record all inputs fed to the machine.
4- You replay those inputs to the machine.
5- Assuming in 3 the machine was conscious, replaying the same inputs, the machine
should still be conscious.
6- You remove from the machine all the transistor not in use during that particular run
(given the recorded input)
7- You replay those inputs to the ("crippled") machine.
8- Assuming in 3 and 5 the machine was conscious, replaying the same inputs, the machine
should still be conscious as in 5 (because what you removed wasn't in use anyway).
9- You break one transistor, but you make a device (in the MGA it's the projection of
the record on the graph) that permits (even if the transistor is broke) to mimic the
output at the exact moment it should have happen if the transistor wasn't broken (like
the lucky cosmic ray replacing the firing of a neuron).
10- Assuming in 3,5 and 8 the machine was conscious, replaying the same inputs, the
machine should still be conscious as the broken transistor while not working did
nonetheless gave the correct output thanks to the lucky ray/devide/movie projection.
11- You do 9 for all the transistor, so as to leave only the mimic...
12- Assuming in 3,5,8 and 10 the machine was conscious, then the machine is still
conscious while no computation occur anymore.... contradicting computationalism.
From that, either computationalism is false or physical supervenience is false.
A good outline, but it doesn't address the question of counterfactual correctness. After
step 6 the machine can no longer respond correctly to a different input - it and whatever
computation it does, is no longer counterfactually correct. Of course you can expand the
AI to include so much of the world that there are effectively no inputs; which is the same
as saying it computes the outputs for all possible inputs. But then it has become a
Matrix type world unto itself.
Brent
--
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 everything-list+unsubscr...@googlegroups.com.
To post to this group, send email to everything-list@googlegroups.com.
Visit this group at http://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/d/optout.