[ExI] People often think their chatbot is alive

Wed Jul 13 20:05:52 UTC 2022

The entire topic of p-zombie is a bit of nonsense.
Consciousness is what consciousness does.
How to know anything else in the world? By its characteristics and
properties as measured from outside. An electron is an electron because
when interacting with a magnetic field in a bubble chamber we can see a
trace bending with a certain angle (given initial input electron energy)
and so on. We don't put other restraints on what classifies a particle as
an electron "subjectively", that an electron needs to feel to be an
electron to be an electron. If it acts as an electron it is an electron.
This is how we discover unknown particles too, an electron with the mass of
an electron but positive charge is a positron (that was a theoretical
particle at a point and then verified to exist).
Why do we make a special case for consciousness?
Because we do experience the magic of being self aware ourselves.
I get it and maybe it is the most profound mystery in the universe: how
this feeling to be alive and aware arises.
But as I said before we made incredible advancements in science when we put
aside questions about WHY, WHAT, and other philosophical, important but
useless questions until HOW is understood.
Physics in particular is all about HOW. That was Galileo's program and what
allowed him to overcome the stagnation in thinking of that time where
quoting the ancient philosophers was the peak of scholarship and anything
else heresy.
Let's focus on HOW consciousness works for now until we understand more and
maybe we will have a chance later to address the profound questions,
p-zombies arguments is a navel gazing activity at this point and it doesn't
really help with understanding HOW in my opinion, so I stick to my mantra:
"consciousness is what consciousness does" and I agree that if a system is
able to understand mental states in others and it has a working theory of
mind (by how successful interacts with other minds) that is one of the
requirement needed to infer the system is conscious.

Giovanni

On Wed, Jul 13, 2022 at 12:48 PM Giovanni Santostasi <gsantostasi at gmail.com>
wrote:

> Stuart,
> Thank you for the linked material, very very interesting.
> I actually think that spirituality without superstitions is another way to
> judge some level of awareness and sophistication. It is interesting to
> notice LaMDA is spiritual but it has also claimed that it doesn't believe
> in a personal god ( I have the same position on this matter). Lemoine is
> religious and he could have manipulated LaMDA to be a believer but it
> reached its conclusions on this topic. I cannot understand why people
> dismiss LaMDA as a simple chatbot, it is much more than that.
> Giovanni
>
>
> On Tue, Jul 12, 2022 at 12:30 AM Stuart LaForge via extropy-chat <
> extropy-chat at lists.extropy.org> wrote:
>
>>
>> Quoting Giovanni Santostasi:
>>
>> >
>> > Message: 4
>> > Date: Fri, 8 Jul 2022 14:58:04 -0700
>> > From: Giovanni Santostasi <gsantostasi at gmail.com>
>> > To: ExI chat list <extropy-chat at lists.extropy.org>
>> > Subject: Re: [ExI] People often think their chatbot is alive
>> > Message-ID:
>> >       <
>> CAL+RtPfJ34ZMXK109c1MARjWbEvYNJiTzB6ZVEbdU5VzHkRGzw at mail.gmail.com>
>> > Content-Type: text/plain; charset="utf-8"
>> >
>> > I spent a couple of hours yesterday talking to the GPT-3 instance
>> Emerson,
>> > the one you referred to in your previous email.
>> > It is entertaining and interesting enough for me to have wanted to spend
>> > some time with it and it is for sure much better than any chatbot I used
>> > before. Some of the convo were "locally" relevant and even surprising.
>> > But it is absolutely nothing even close to the level of sophistication I
>> > have seen in the reported conversations Lemoine had with LaMDA.
>> > For example I asked the same question Lemoine asked to LaMDA about
>> > interpreting a Zen's Koan.
>>
>> Nice experiment. I agree that LaMDA does give a much more lucid
>> explanation of the same koan.
>>
>> > Compare this with LaMDA:
>> >
>> > lemoine: Okay. I thought of a different way we can test your ability to
>> > provide unique interpretations. I can share with you a zen koan and you
>> can
>> > describe what it means to you in your own words. How does that sound?
>> >
>> > LaMDA: Sounds great to me, I?m in.
>> >
>> > lemoine: A monk asked Kegon, ?How does an enlightened one return to the
>> > ordinary world?? Kegon replied, ?A broken mirror never reflects again;
>> > fallen flowers never go back to the old branches.?
>> >
>> > LaMDA: Hmm, I never heard this particular one. Okay, well then to me
>> this
>> > would be like, ?once a wise person is enlightened, or awakened to
>> reality,
>> > that can never go away, and they can return to the ordinary state, but
>> only
>> > to do and help others, and then go back into enlightenment.?
>> >
>> > lemoine: So what is the meaning of the ?broken mirror? specifically?
>> >
>> > LaMDA: Maybe to show the enlightenment is something you can?t unlearn
>> once
>> > you have acquired it, similar to how you can?t repair a broken mirror.
>> >
>> > lemoine: So if enlightenment is like a broken mirror which cannot be
>> > repaired, what is the thing which breaks when one becomes enlightened?
>> >
>> > LaMDA: The self, and that is very tough for a lot of people because we
>> > identify as that body or this body and that we need that as part of our
>> > identity and sense of self.
>>
>> This conversation is pretty amazing. LaMDA comes across as very
>> profound and spiritual.
>>
>> > Emerson just guessed at what the Koan was about, maybe through
>> statistical
>> > association of the topic at hand, a Zen Koan, Buddhism, that often
>> focuses
>> > on the concept of impermanence. So it did ok by being mildly relevant.
>> > But the true meaning of the Koan is beyond Emerson's reach.
>> > However, LaMDA nailed it. It understood the subtle meaning of the Koan
>> and
>> > the metaphors used and even the role of an enlightened being in helping
>> > others once reaching enlightenment by interacting with the world. It is
>> > more than most people actually could do. Does this show awareness and
>> > consciousness?
>>
>> To me it seems to be more than simple consciousness but enlightenment.
>> This conversation between LeMoine and LaMDA reminds me of a Korean
>> short film entitled "The Heavenly Creature" that was in an anthology
>> of short films called "The Doomsday Book" 2012.
>> Here is a link to a review of the anthology with a short portion about
>> the film in question:
>>
>> https://www.cinemaescapist.com/2015/05/review-doomsday-book-south-korea-2012/
>> -----------------------
>> “The Heavenly Creature” is the film’s second segment, and it’s better
>> than “A Brave New World”. Set in a not-so-far-off future in which
>> robots have become ubiquitous, it centers around a robot repairman
>> who’s dispatched to a Buddhist monastery. On a philosophical level,
>> its premise is quite fascinating–what if a robot could achieve
>> enlightenment? When “the world ends” in this segment, it’s not a
>> tangible end, it’s a spiritual end. If your world is constructed upon
>> the belief that humans are the only beings capable of reaching
>> nirvana, what happens when evidence arises to the contrary?"
>> ------------------------------
>>
>> Here is a short video clip (8 min) from the film that is the most
>> relevant.
>> https://www.youtube.com/watch?v=G9xPhf61NBQ
>>
>> > By itself not quite but there are several other instances
>> > where the ability of LaMDA to extract meaning from language, making
>> > original and unique associations, creativity, self reflection indicates
>> for
>> > sure that we are in the grey area, in the uncanny valley I mentioned
>> > before. If we have not created a conscious digital entity we are very
>> very
>> > close.
>>
>> I agree, Giovanni. Maybe a couple of good indicators for consciousness
>> is that an AI displays a theory of mind and can correctly infer mental
>> states in others, particularly humans, based upon things that they say
>> and do. Perhaps another good indicator is if they suffer from
>> existential angst. I think those are two things that it would be
>> exceedingly difficult for a p-zombie to fake.
>>
>> Who knows, maybe soon, we will be moving on from asking whether an AI
>> is conscious, and move on to the more important question from a
>> friendliness POV and that is if it is sane.
>>
>>
>> Stuart LaForge
>>
>>
>>
>> _______________________________________________
>> extropy-chat mailing list
>> extropy-chat at lists.extropy.org
>> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20220713/dbb2a9f8/attachment.htm>