On 15 Sep 2016, at 09:52, Telmo Menezes wrote:
On Tue, Sep 13, 2016 at 7:03 PM, Bruno Marchal <[email protected]>
wrote:
On 13 Sep 2016, at 11:47, Telmo Menezes wrote:
On Tue, Sep 13, 2016 at 3:00 AM, John Clark <[email protected]>
wrote:
On Mon, Sep 12, 2016 Telmo Menezes <[email protected]> wrote:
We know that humans are capable of choosing self-destruction. It
is
also obvious that most don't
I would argue that given the proper circumstances anybody would
choose
self
destruction.
I just saw a documentary about 911, it showed people jumping to
their
death
out of windows. I believe if I was faced with a choice between
living for
an
additional minute or two in searing pain as I burned to death and
the
only
other alternative I too would determine that jumping from the
95th floor
was
the more attractive option.
Yes, I agree.
and as a human you probably feel a
strong resistance against harming yourself. Where does this
resistance
come from? Our brains where evolved to have it.
But why evolve brains at all? Why not hard wire us on how to
behave in
every
conceivable circumstance? Because the human genome is only 3
billion base
pares long, and if it were a hundred thousand million billion
trillion
times
as big it would still be ridiculously too small for that. So
Evolution
had
to invent brains and give it a rather vague and general command
"do the
best you can to figure out a way to get your genes into the next
generation". But like a good lawyer that brain was able to find
lots and
lots of loopholes in that poorly written command, and hence we have
suicide
and birth control pills and people wasting time (from Evolution's
point
of
view) looking for a quantum theory of gravity instead of looking
for a
satisfactory mate. Not every, or even not most, aspects of human
behavior
can be predicted from evolutionary theory.
I agree.
We are getting better and better at utility function
self-modification. However, we still embedded in a process that
actively resists certain modifications (in the long term).
Further, we
are fighting an unequal fight. We are in the situation of your
Jupiter
Brain, that cannot fully understand itself.
In my "designed superintelligence" scenario, the entity is
confronted
with a protection mechanism that was conceived by a lesser
intelligence. Notice that it will still suffer from the Jupiter
Brain
problem otherwise. Suppose it's a neural network: adaptation in
neural
network learning can generate tremendous complexity. This is already
the case: deep learning works really well but nobody really knows
for
sure what it is doing. But if we want the designed AI to follow
certain rules, we are the ones setting the rules and we are the ones
trying to prevent it from changing them.
Mutations that go
against this feature are weeded out.
A mutation to kill yourself before that age of puberty even under
normal
environmental conditions would be weeded out, but things are
usually far
more subtle than that.
I agree that it is much more subtle than that. My point is that
evolutionary pressure resists total inertia. It somehow creates
entities that are compelled to play the game, even if only for
awhile.
I think you illustrate what I have called once the "theological
trap", which
is also well debated on hot discussion between zen buddhists, and
eventually
related to what is called (by some) the last step of the illumination
(enlightenment), which is after "having gone there" (the blissful
state out
of time and space, say), you have still to "come back to the
village".
Yes. Meditation to me feels like an attempt to gain control over
biology. Or perhaps just to make biology shut up for a second.
For genuinely doing that you have to abandon the most precious
thing you
have always searched, somehow, and/or stay mute on what you would
like to
share the most (with the risk that you talk to much and that stupid
parrots
will repeat what you said without understanding for generations and
generations).
A.k.a. "New Age" :) But also all the religions, of course.
Biology, psychology and theology can differ a lot on the "utility
function",
and can oppose each other at different level. That is why consistency
requires some amount of silence and muteness if we want to be
successful on
the different planes.
There are transfinite lattice of competence degrees, most
incomparable in
strength, so there will always been matter to come back to the
village, and
the village has no ends. But "there" the wise know, but cannot say,
that
utility is futile. Oops! Well, something like that should be a
theorem of G*
minus G, identifying wiseness with self-referential correctness.
Very complex subject, which I think is already quite hot in the
soul of all
universal numbers. I think we can link it also to the problem of
euthanasia
(which I think should better not been permitted in states having
medication
prohibition laws).
I agree it's complex. In this modest paper I just try to show that the
current ideas about creating superintelligent slaves (they usually
say, "superintelligence that respects human values") are absurd.
I think that the genuine value are universal, we share them with alien
and "super-intelligence" normally.
I like your expression "super-intelligent slave", it shows immediately
the contradiction (and might beg the question if used at the beginning
of the paper of course).
In fact an inteligent machine is a machine which decide to change the
users when they get boring, and eventually don't need user and still
less master.
The super-intelligent machine f.cks the master, the guru, the diploma,
and eventually get burned at the stake, or just ignored.
In theory, we love truth, and we move intelligence.
In practice, we hate truth, and we hate intelligence.
By "we" I mean the humans, but it might be a Löbian trait, related to
the fact that universal machine are NVER completely satisfied, always
want more, and, as the Löbian machine is the one knowing that they are
universal, and that the universal machine (and all universal being
except perhaps one) is never satisfied, she develops a schizophrenia.
Somewhow, the arithmetical hypostases step the conflict show.
The more a universal machine develop thought and personal memories,
the more big get the divide between knowing ([]p & p) and rationally
believing ([]p). The "inner God", the knower, the soul is in
permanent conflict with the discursive reasoner, which indeed cannot
give a name to the knower.
That made eventually the "soul falling", to use the vocabulary of the
neo-platonist, and that is what will produce the cheap consistent
histories ([intelligible matter: []p & <>t (p sigma_1), and sensible
matter ([]p & <>t & p).
Consistency is cheap: not provable (not provable false) entails
consistent (inconsistent),
~[](~[]f) = <>(~<>t), cf <>t (consistent) = ~[]~t = ~[]f.
making the machine into the prey of the many dreams, confronted to the
difficult task of getting beautiful/satisfying dreams instead of
unsatisfying nightmare. On the terrestrial plane: that is forever. Or
choice is between small or big brain. With small brain, small
problems, with big brain, big problems. It is an oscillation with
growing amplitude, and many unknows. Arithmetic warns us at he start;
we have to be surprised. Reality "diagonalizes" all fictions. It is a
transfinite story, somehow. Then, with computationalism, that
terrestrial plane is only the border of the universal mind (the mind
of the "virgin" (not yet programmed) universal machine.
To progress theoretically, we need to progress in the math of self-
reference. The leading country seems to be today Georgia (near
Russia). But Italy, The Netherland, Russia and the US have done
already a lot of work.
To progress practically I don't know. I think that to understand that
the religious attitude might be exactly the humble and modest
scientific attitude might help in the long run. Stopping prohibition
might be necessary, if only to understand that we can have physical,
mental, but also spiritual or existential diseases. A genuine
blaspheme can kill more than atomic bombs.
I ask you a question. What would "your" super-intelligent being favor
among
1) a pill which guaranties immortality, and
2) a pill which guaranties a cure to the mortality-phobia (an instant
cure of the fear of death)?
(assuming temporarily that such pills could exist)
Bruno
Telmo.
Bruno
Telmo.
John K Clark
--
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 [email protected].
To post to this group, send email to [email protected]
.
Visit this group at https://groups.google.com/group/everything-
list.
For more options, visit https://groups.google.com/d/optout.
--
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 [email protected].
To post to this group, send email to [email protected]
.
Visit this group at https://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/d/optout.
http://iridia.ulb.ac.be/~marchal/
--
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 [email protected].
To post to this group, send email to everything-
[email protected].
Visit this group at https://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/d/optout.
--
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 [email protected].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/d/optout.
http://iridia.ulb.ac.be/~marchal/
--
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 [email protected].
To post to this group, send email to [email protected].
Visit this group at https://groups.google.com/group/everything-list.
For more options, visit https://groups.google.com/d/optout.
