On 2/16/08, Matt Mahoney <[EMAIL PROTECTED]> wrote:

> I believe his target is the existence of consciousness.  There are many proofs
> showing that the assumption of consciousness leads to absurdities, which I
> have summarized at http://www.mattmahoney.net/singularity.html
> In mathematics, it should not be necessary to prove a theorem more than once.
> But proof and belief are different things, especially when the belief is hard
> coded into the brain.

I would have thought a minimally necessary part of constructing a
proof in this domain would be to give a fairly precise conceptual
analysis or partial analysis (e.g. necessary conditions) of our
concept of consciousness and show why the conditions of its
application do not in fact obtain. The standard practice in philosophy
is to defend such an analysis by arguing it best unifies and explains
our case intuitions about when we apply it. (It may be helpful to
compare this to standard practice in linguistics in relying on our
grammatical intuitions to theorize about grammar.) If there was
anything like this in the link you sent, I'm having a difficult time
identifying and reconstructing it.

I do see, among other things, a series a questions that confuse the
issue of personal identity with that of the existence of
consciousness. We might be quite sure *that* something is conscious
without being sure whose consciousness it is or how it is related to
other consciousnesses we have known and cared about. There's been some
very good work on personal identity issues done by Derek Parfit in
"Reasons and Persons" and Jeff McMahan in "The Ethics of Killing:
Problems at the Margins of Life." Ultimately, they both conclude that
personal identity is in the end just a distraction but something very
close to it, the right kinds of psychological (and, for McMahan,
physical) continuity, is what really matters.

There's no need to bring in uploading or artificial neurons to see
this point either. Imagine that your cerebral hemispheres will be
transplanted into two different bodies and go on to live separate
lives. Since there's not really any grounds to say that one is you and
not the other, and they can't both be you, we should conclude neither
one is you though obviously they bear a very close relation to you.
Furthermore, it is easy to imagine that if their lives are going
fairly well and they are continuing on with your projects, this is
clearly preferable to simply dying. I think we should say that part of
what normally matters in you continuing to exist has been preserved
even though technically, neither one of them is you. Maybe it makes
sense to regret the lack of unity, but I think everything that really
matters can be captured by talking about the right kinds of
psychological and physical relations of connectedness and continuity,
without getting obsessed over incessantly asking, "But is it you?
Which one is you? Where are you? etc."

> The result will not be pretty.  The best definition (not solution) of
> friendliness is probably CEV ( http://www.singinst.org/upload/CEV.html ) which
> can be summarized as "our wish if we knew more, thought faster, were more the
> people we wished we were, had grown up farther together".  What would you wish
> for if your brain was not constrained by the hardwired beliefs and goals that
> you were born with and you knew that your consciousness did not exist?  What
> would you wish for if you could reprogram your own goals?  The logical answer
> is that it doesn't matter.  The pleasure of a thousand permanent orgasms is
> just a matter of changing a few lines of code, and you go into a degenerate
> state where learning ceases.

Your counterfactuals seem very different from Eliezer's and less
relevant to what matters. I think Eliezer's definition was plausible
because it approximated the standards we use to deliberate about our
values. As such, it is getting at deeper values or procedures that we
implicitly presuppose in any serious discussion of values at all. Even
if you were to question whether you should use that standard, your
cognitive architecture would still have to do so by reference to some
internal standard in order to even count as a meaningful type of
questioning and Eliezer's definition would probably be a decent
intuitive characterization of it. Of course, you are free to pose any
type of bizarre counterfactual you want, but I don't see how
evaluating it would be relevant to what matters in the way that
Eliezer's would.

I would prefer to leave behind these counterfactuals altogether and
try to use information theory and control theory to achieve a precise
understanding of what it is for something to be the standard(s) in
terms of which we are able to deliberate. Since our normative concepts
(e.g. should, reason, ought, etc) are fundamentally about guiding our
attitudes through deliberation, I think they can then be analyzed in
terms of what those deliberative standards prescribe.

-------------------------------------------
singularity
Archives: http://www.listbox.com/member/archive/11983/=now
RSS Feed: http://www.listbox.com/member/archive/rss/11983/
Modify Your Subscription: 
http://www.listbox.com/member/?member_id=4007604&id_secret=96140713-a54b2b
Powered by Listbox: http://www.listbox.com

Reply via email to