I know. I'm trying to see
what exactly is being
computation being "the same". Is it the
algorithm? Is it
one that has the same steps as described in
not those in LISP?
Is it just one that has the same
these are questions
that have been bypassed in the "yes doctor"
Saying "yes" to the
doctor seems unproblematic when you think of
few neurons with
artificial ones - all you care about is the
But then when you
jump to replacing a whole brain maybe you care
differences. Yet on this list there seems to
assumption that you can
just jump to the Platonic algorithm or even
independent of the algorithm. Bruno pushes
aside by referring to
"at the appropriate level" and by doing all
algorithms. But I'm
more interested in the question of what would I
have to do
to make a
conscious AI. Also, it is the assumption of
allows one to slice it discretely into OMs.
Start by replacing neurons with artificial neurons
a computer program and whose defining
the I/O behaviour of biological neurons. The
program has to
internal workings of a neuron down to a certain
the position and configuration of every molecule
or it may be that shortcuts such as a single
permeability of ion channels in the cell
membrane make no
to the final result. In any case, there are many
even if the same physical model of a neuron is
and the same
basic program can be written in any language and
computer: all that matters is that the artificial
properly. (As an aside, we don't need to worry
artificial neurons are zombies, since that would
conclusions about the nature of consciousness.)
we can progress to replacing the whole brain,
computer program interacting with the outside
and effectors. The program can be implemented in
way - any
language, any hardware - and the consciousness
remain the same as long as the brain behaviour
You're asserting that neuron I/O
replication is the
level" to make "brain behavior" the same; and I tend to
would be sufficient (though perhaps not necessary).
preserving a particular algorithm; one more specific
Platonic computation of its equivalence class. I
machine could perform the same computation, but it
it very differently. And I wonder how the Turing
manage perception. The organs of perception would
responses digitized into bit strings and these would be
the TM on different tapes? I think this illustrates
that, while preservation of consciousness under the
substitution seems plausible, there is still another
substituting an abstract computation for the digital
Also, such an AI brain would not permit slicing the
into arbitrarily short time periods because there is
time involved and neurons run asynchronously.
Yes you can, freeze the computation, dump memory...
memory back, and defreeze. If the time inside the
is an internal feature (a counter inside the program),
associated to the computation cannot notice anything if
other hand the time inside of the computation is an input
parameter from some external then it can notice... but I
always can englobe the whole thing and feed that
from another program or whatever.
That assumes that the AI brain is running synchronously,
i.e. at a
clock rate small compared to c/R where R is the radius of the
brain. But I think the real brain runs asynchronously, so
AI brain must do the simulation at a lower level to take
of transmission times, etc. and run at a much higher clock
than do neurons. But is it then still "the same" computation?
The fact that you can disrupt a computation and restart it
with some different parameters doesn't mean you can't
it with *exactly* the same parameters as when you froze
That's arbitrarily excluding the physical steps in
"starting" a computation, as though you can pick out the
computation as separate from the physical processes. Which
same as assuming that consciousness attaches to the Platonic
"real" computation and those extra physical steps somehow
count as "computations".
>> All those moments will be lost in time, like tears in rain.
You received this message because you are subscribed to the Google
Groups "Everything List" group.
To post to this group, send email to everything-l...@googlegroups.com.
To unsubscribe from this group, send email to
For more options, visit this group at