[ExI] People often think their chatbot is alive

Sat Jul 9 04:50:29 UTC 2022

Hi Giovanni,

I often say similare things to all of: "*Philosophers are ok, but they make
big deals about relatively non-important stuff (don't let me start on the
stupid Chinese room argument).*"

To me, the difference between philosophy and science is
experimental demonstrateability or falsifiability.

You are predicting (or assuming?) that *redness emerges from self
referential systems*.  *That is a falsifiable claim.*
I guess that places you in the popular consensus functionalist camp
<https://canonizer.com/topic/88-Theories-of-Consciousness/18-Qualia-Emerge-from-Function>
with
Stathis and so many others.

RQT
<https://canonizer.com/topic/88-Theories-of-Consciousness/6-Representational-Qualia>
predicts that redness is simply a physical fact, and that some abstract
description of physical facts (like our description of glutamate, reacting
in a synapse) is a description of the physical redness.  All we need to do
is connect the subjective (which we directly apprehend as a computational
process running directly on those physical qualities) with the objective
(we abstractly sense, from afar), using experimental demonstration of which
of all our descriptions of stuff in the brain is a description of
subjective redness.  Once we demonstrate that, we will have the required
physical dictionary to know what our abstract information about physics
represents.

I understand what you mean by: "*Mathematics is not evident from symbol 2.*"

I agree that redness, as a physical fact, could be defined to represent 2
(maybe if you defined greenness to represent one, and so on).  You can't
have mathematical knowledge without representing it with something
physical, and the associated physical dictionary.  (i.e. redness = 2,
greenness = 1)

If you think of redness in the same way as you do the abstract number 2, or
that a redness quality is not just a physical fact, which has a quality,
all on its own, then that says to me you don't understand demonstrable
intrinsic physical qualities.

Let me quote 2 of Dennett's 4 attributes of physical qualities (or qualia)
in the definition on the wikipedia page on qualia
<https://en.wikipedia.org/wiki/Qualia>.

*2. intrinsic <https://en.wikipedia.org/wiki/Intrinsic>* – they are
non-relational properties, which do not change depending on the
experience's relation to other things.
*4. directly or immediately apprehensible
<https://en.wiktionary.org/wiki/apprehend> by consciousness
<https://en.wikipedia.org/wiki/Consciousness>* – to experience a quale is
to know one experiences a quale, and to know all there is to know about
that quale.

RQT
<https://canonizer.com/topic/88-Theories-of-Consciousness/6-Representational-Qualia>
predicts that nobody will be able to demonstrate a redness experience with
anything (*self referential* or not) other than whatever physics it is,
that has a redness quality.  And that our consciousness computes
directly on those physical qualities.  That computing directly on physical
qualities is more efficient than virtual systems which are abstracted away
from physical qualities requiring dictionaries.

All we know of physics, are the colorness qualities things seem to have.
When in reality, those colorness qualities are what we are computing about
those things with.  Only when we realize this, and discover the true
colorness qualities of things, will we finally discover the true nature of
ourselves AND physics.

I also love what you say about "*Why*."  We won't know "*WHY*" glutamate
has a redness quality, we just need to know what has a redness quality, to
be able to engineer systems that mathematically compute directly on redness
(and all the other colors, and how many more are there?)

Care to place any bets on which theory will be experimentally
demonstrated to be THE ONE?

On Fri, Jul 8, 2022 at 8:51 PM Giovanni Santostasi <gsantostasi at gmail.com>
wrote:

> Why do you think any qualia is different from anything else that is
> relevant for information storing and processing in the brain?
> Redness for sure is a bunch of connections and neural activation. They are
> associated usually with some external experience but also with things that
> are not external experiences like things we can imagine are red, or
> red-like. All neural connections.  If you are enchanted by the fact qualia
> are "subjective" well that is what happens when you are a system that is
> self-referential. A lot of emergent behavior seems magical because it is
> not immediately evident how it is derived from its components. But qualia
> are not special in that way. What is symbol 2 that is a description of
> twoness? It is really how we use the concept of 2 in operations, that gives
> it meaning, its interaction with other numbers, what we call mathematics.
> Mathematics is not evident from symbol 2.
>
> I'm very interested in the topic of consciousness since a child both from
> an intellectual but also experiential point of view. I have practiced
> meditation for years and read extensively about eastern philosophy. So I
> would be the last to dismiss the incredible experience of subjectivity. But
> it is an emergent property like life.
>
> There was a point when life seemed so magical because it could not be
> easily explained by its components. But we are reaching a point where we
> understand life emerges through the interaction of complex chemical and
> physical processes (this doesn't destroy for me the magic of life but makes
> it even more magical). You experience being alive and it is incredible but
> for sure you don't think that your heart or your cells are nothing else
> than complex machines. Why subjectivity should be so different from other
> emergence phenomena?
>
> Philosophers are ok, but they make big deals about relatively
> non-important stuff (don't let me start on the stupid Chinese room
> argument). This is why we needed science to make real progress. In physics,
> you try to understand things, in a deep way but you always start with: "Ok
> let me first understand HOW something works, when I have more information
> and I understand this process better, I will try to understand WHY.". This
> is what Galileo proposed, the scientific revolution. Maybe we always
> postpone answering WHY but in a way we are doing that when we focus on
> understanding HOW first.
>
> Enormous progress in our understanding of the world ensued. If it was for
> phylosophers we will still idly look at our navels. From an operational and
> HOW point of view, I don't see why qualia are a big deal at all.
> From an experiential point of view, I prefer to transcend and don't even
> use concepts or ideas but just direct experiences of consciousness. By the
> way, it is super cool Blake taught LaMDA how to meditate. I would like to
> understand more about that and what LaMDA's experience of meditation was.
>
>
>
>
>
>
> On Fri, Jul 8, 2022 at 6:48 PM Brent Allsop <brent.allsop at gmail.com>
> wrote:
>
>>
>> Hi Giovanni,
>>
>> Yes, LaMDA is very impressive.  Probably beyond what even I could do.
>> But the reason I struggle with getting that deep, is because I have a one
>> track mind: redness and greenness.
>>
>> Subjectively, I know what redness is, and what it is like.  But
>> objectively, neither I, nor anybody knows what that is.
>>
>> Which of all our abstract descriptions of stuff in the brain is a
>> description of redness?
>>
>> That's the only real question that holds my interest.
>>
>>
>>
>>
>>
>>
>>
>>
>>
>> On Fri, Jul 8, 2022 at 3:59 PM Giovanni Santostasi via extropy-chat <
>> extropy-chat at lists.extropy.org> wrote:
>>
>>> 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.
>>>
>>> Giovanni Santostasi, [7/8/2022 4:29 AM]
>>> you know what a Koan is?
>>>
>>> Emerson AI, [7/8/2022 4:29 AM]
>>> A Koan is a Japanese word that refers to a paradoxical question or
>>> statement used in Zen Buddhism to help someone learn. For example, "What is
>>> the sound of one hand clapping?"
>>>
>>> Giovanni Santostasi, [7/8/2022 4:30 AM]
>>> if I give you a Koan can you try to interpret it for me?
>>>
>>> Emerson AI, [7/8/2022 4:30 AM]
>>> Sure! The traditional interpretation of a Koan is that it is a difficult
>>> question or phrase that can be interpreted in many ways to help the student
>>> to understand it.
>>>
>>> Giovanni Santostasi, [7/8/2022 4:30 AM]
>>> Here a koan, can you tell me what you think about this one?
>>> 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.”
>>>
>>> Emerson AI, [7/8/2022 4:30 AM]
>>> I think this quote speaks to the idea of impermanence. Things change and
>>> we must always be open to new experiences.
>>>
>>> Giovanni Santostasi, [7/8/2022 4:31 AM]
>>> What does the analogy of the broken mirror mean here?
>>>
>>> Emerson AI, [7/8/2022 4:31 AM]
>>> It could mean that enlightenment is not something that can be achieved
>>> easily, or that it may be fleeting.
>>>
>>>
>>> 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.
>>>
>>> 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? 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.
>>>
>>> Giovanni
>>>
>>>
>>> On Tue, Jul 5, 2022 at 6:20 AM Giovanni Santostasi <
>>> gsantostasi at gmail.com> wrote:
>>>
>>>> I cannot stand anymore when people dismiss without deep analysis Blake
>>>> Lemoine conclusions on LaMDA.
>>>> The guy is a deep thinker, he has very strong arguments, explanations
>>>> of why LaMDA is not simply an average chatbot but a hive mind. It was
>>>> created among other things using a chatbot but it is the merger of several
>>>> AI technologies whose single components are barely understood but nobody
>>>> has any idea how the merger of these technologies work together.
>>>> PLEASE read and listen to his interviews, he is not an average user of
>>>> Replika or some other simpler chatbot user. The guy is sophisticated and an
>>>> expert in cognition and AI and the most experienced person in terms of how
>>>> LaMDA interacts with people.
>>>> Any statement that quickly dismisses Blake Lemoine conclusions without
>>>> deep arguments based on a real understanding of how LaMDA works (that at
>>>> this point not even Google engineers really know) is meaningless and
>>>> ignorant.
>>>> Besides, the guy simply states that we should take seriously LaMDA's
>>>> own statements about being conscious (not even Blake himself conclusions on
>>>> this issue) and do more experiments (with LaMDA consent) to find out if
>>>> that is the case.
>>>> What the heck is wrong with that?
>>>> Giovanni
>>>>
>>>> On Mon, Jul 4, 2022 at 9:12 AM BillK via extropy-chat <
>>>> extropy-chat at lists.extropy.org> wrote:
>>>>
>>>>> Is AI Sentience Becoming A Reality Or Are Machines Just Getting Better
>>>>> At Conversation?
>>>>> by Tim Sweezy — Thursday, June 30, 2022
>>>>>
>>>>> <
>>>>> https://hothardware.com/news/is-ai-sentience-becoming-reality-or-are-machines-getting-better-at-conversation
>>>>> >
>>>>>
>>>>> Quotes:
>>>>> AI chatbot company Replika is receiving messages from customers who
>>>>> believe their AI companions are actually sentient.
>>>>> It is not something new for someone to believe an AI chatbot has
>>>>> become self-aware. In a recent report from Reuters, Chief Executive
>>>>> Eugenia Kuyda of Replika stated, "We're not talking about crazy people
>>>>> or people who are hallucinating or having delusions. They talk to AI
>>>>> and that's the experience they have."
>>>>>
>>>>> The AI Kuyda is referring to is Replika's bespoke avatars that are
>>>>> meant to be companions for people seeking someone to talk to and
>>>>> listen to them. Kuyda says that it is not uncommon for people who use
>>>>> entertainment chatbots to feel this way.
>>>>> According to Kuyda, people send hundreds of messages a day to their
>>>>> chatbot on average. This can lead to some developing the perception
>>>>> that they are talking to a "conscious entity".
>>>>>
>>>>> "We need to understand that exists, just the way people believe in
>>>>> ghosts," remarked Kuyda. "People are building relationships and
>>>>> believing in something."
>>>>> _________________
>>>>>
>>>>> BillK
>>>>>
>>>>> _______________________________________________
>>>>> extropy-chat mailing list
>>>>> extropy-chat at lists.extropy.org
>>>>> http://lists.extropy.org/mailman/listinfo.cgi/extropy-chat
>>>>>
>>>> _______________________________________________
>>> 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/20220708/db84a134/attachment.htm>