SG:
Fascinating reflexive example here! You using chatGPT as a boundary
(spanning/negotiation) artifact/object convolved with extant SF writings
many (some) of us might be familiar with to help with that
spanning/negotiation!
Your invocation of both concepts in this exchange had me opening a
thread of dialog with chatGPT which helped *me* to elaborate my
understanding of (especially the conventional usage of) both concepts.
I was heartened to see that chatGPT either overlayed (or found in it's
training implicitely?) the more general way I have been using "faceted
ontology" for some time now and expanded my appreciation for boundary
objects (spanning/negotiating/etc).
The net effect seems to be to enhance our (your and mine if nobody
else's) "co-mmunication" (whatever that means).
I am also left with the feeling of what I think professional therapists
call "triangulation" but more in the "good way" if in fact there is such
a thing. Maybe the kind of thing that Glen experiences/encourages among
his pubPhilosophers? Turn-taking as "boundary negotiators"?
:SS
PS. Stranger/Heinlein: I was surprised in my own explorations that
chatGPT came up with Heinlein's "grokking" in relationship to
faceted ontologies and "water sharing", "church of all worlds", and
"the Martian Language" as Boundary Objects. I"m guessing that a
lot of literary criticism has been written in these terms?
PPS. DiamondAge/Stephenson: Maybe more obviously, the Primer, the
Drummers, and the Confucian Justice System were identified as
boundary objects and " 'ractors" and "phyles" were identified as
implementing faceted ontologies.
Steve, here's what I would query you wrt this thread on
communication. I hit the polite poly first:
Summarize two science fiction works that explore the theme of faceted
ontologies that create boundary spanning objects that allow
communication between wildly different life forms
1.
"Embassytown" by China Miéville: This science fiction novel delves
into the nature of language, communication, and the relationship
between different life forms. The story takes place in
Embassytown, a city on the edge of the known universe inhabited by
both humans and the enigmatic, insect-like Ariekei. The Ariekei
language is unique in that it requires two voices to be spoken
simultaneously, and they are only able to comprehend language that
has an authentic, conscious intent behind it. To facilitate
communication between humans and the Ariekei, genetically
engineered humans called Ambassadors are created, who can speak
the Ariekei language. The novel explores the complex ontological
and linguistic challenges of communication between these vastly
different life forms and how their interactions shape their
understanding of each other's worlds.
2.
"Solaris" by Stanisław Lem: In this classic science fiction novel,
a team of human scientists studies an alien planet called Solaris,
which is covered by a vast, sentient ocean. This ocean is capable
of creating physical manifestations, called "visitors," based on
the thoughts and memories of the human researchers. The
researchers grapple with the challenge of understanding and
communicating with this fundamentally different life form, which
operates on a completely different ontological level. The novel
delves into the limitations of human understanding and the nature
of communication between species with vastly different cognitive
frameworks.
Both of these science fiction works explore the concept of faceted
ontologies in the sense that they address the challenges of
communication between life forms that operate on entirely different
cognitive and ontological levels. The novels offer unique perspectives
on the notion of creating bridging mechanisms or spanning objects that
facilitate communication and understanding between these disparate
life forms.
And a follow up exploring the duality of the two systems of cognition:
1.
"Story of Your Life" by Ted Chiang: This science fiction novella,
which was the basis for the movie "Arrival," explores the theme of
communication between humans and an alien species known as the
Heptapods. The story follows linguist Dr. Louise Banks, who is
tasked with understanding and communicating with the Heptapods.
The boundary spanning object in this case is the Heptapod
language, specifically their written language called Heptapod B,
which is expressed in intricate, circular symbols. Heptapod B
represents a fundamentally different system of cognition, as it
embodies a non-linear and simultaneous understanding of time. As
Dr. Banks learns Heptapod B, she begins to perceive time in the
same way the Heptapods do, changing her understanding of her own
life and human cognition. The novella demonstrates the duality
between the systems of cognition by showing how the Heptapod
language provides a bridge between human linear perception of time
and the Heptapods' non-linear perception.
2.
"The Sparrow" by Mary Doria Russell: This novel follows a Jesuit
priest named Emilio Sandoz and a group of explorers who travel to
the planet Rakhat to make contact with two different alien
species, the Runa and the Jana'ata. The boundary spanning object
in this story is music, which serves as a means of communication
and connection between the humans and the alien species. As the
characters learn the different musical systems and vocalizations
of the Runa and the Jana'ata, they begin to understand the social,
cultural, and cognitive structures of the alien societies. Music,
in this case, represents the duality between the systems of
cognition by highlighting the similarities and differences between
human culture and the complex, intertwined societies of the Runa
and the Jana'ata. Through the exploration of music as a universal
language, the novel delves into the challenges of communication
and understanding between species with disparate cognitive systems.
In both of these science fiction works, the boundary spanning objects
(Heptapod B language in "Story of Your Life" and music in "The
Sparrow") serve as tools for facilitating communication between
different conscious life forms, highlighting the duality between their
systems of cognition and illustrating how understanding can be reached
despite their differences.
On Thu, Apr 6, 2023, 8:27 AM Steve Smith <sasm...@swcp.com> wrote:
I have been reading Jeff Hawkins' _1000 Brains_ which is roughly
*his*
take on AI from the perspective of the Neuroscience *he* has been
doing
for a few decades, including building models of the neocortex.
What struck me strongly was how much *I* expect anything I'd want to
call artificial *consciousness* to engage in "co-munnication" in the
strongest sense. Glen regularly admonishes us that
"communication" may
be an illusion and something we don't actually *do* or maybe more
to the
the point "it doesn't mean what we think it means"?
So for all the parlor tricks I've enjoyed playing with chatGPT and
DALL-E and maybe even more spectacularly the myriad examples *others*
have teased out of those systems, I am always looking for what
sort of
"internal state" these systems are exposing to me in their
"utterances". And by extension, I am looking to see if it is in any
way apprehending *me* through my questions and prompts.
Dialog with chatGPT feels pretty familiar to me, as if I'm conversing
with an unusually polite and cooperative polymath. It is freeing to
feel I can ask "it" any question which I can formulate and can expect
back a pretty *straight* answer if not always one I was hoping for.
"It" seems pretty insightful and usually picks up on the nuances
of my
questions. As often as not, I need to follow up with refined
questions
which channel the answers away from the "mundane or obvious" but
when I
do, it rarely misses a trick or is evasive or harps on something from
it's own (apparent) agenda. It only does that when I ask it
questions
about it's own nature, formulation, domain and then it just seems
blunted as if it has a lawyer or politician intercepting some of
those
questions and answering them for it.
I have learned to "frame" my questions by first asking it to defer
it's
response until I've given it some ... "framing" for the actual
question. Otherwise I go through the other series of steps where I
have to re-ask the same question with more and more context or ask a
very long and convoluted question. At first it was a pleasure to be
able to unlimber my convoluted-question-generator and have it (not
mis)
understand me and even not seem to "miss a trick". As I learned to
generate several framing statements before asking my question, I have
found that I *can* give it too many constraints (apparently) such
that
it respects some/most of my framing but then avoids or ignores other
parts. At that point I have to ask follow-up, elaborating,
contextualizing questions.
I do not yet feel like I am actually seeing into chatGPT's soul or in
any way being seen by it. That will be for a future generation I
suspect. Otherwise it is one hella "research assistant" and
"spitball
partner" on most any topic I've considered that isn't too
contemporary
(training set ended 2021?).
- Steve
On 4/4/23 5:54 PM, Prof David West wrote:
> Based on the flood of stories about ChatAI, it appears:
> - they can 'do' math and 'reason' scientificdally
> - they can generate essays, term papers, etc.
> - they can engage in convincing dialog/conversations
> - as "therapists"
> - as "girlfriends" (I haven't seen any stories about women
falling in love with their AI)
> - as kinksters
> - they can write code
>
> The writing code ability immediately made me wonder if, given a
database of music instead of text, they could write music?
>
> The dialog /conversation ability makes me wonder about more
real-time collaborative interaction, improv acting / comedy? Or,
pair programming? The real-time aspect is critical to my question,
as I believe there is something qualitatively different between
two people doing improv or pair programming than simply engaging
in dialog. I think I could make a much stronger argument in the
case of improv music, especially jazz, but AIs aren't doing that yet.
>
> davew
>
> -. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
> FRIAM Applied Complexity Group listserv
> Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom
https://bit.ly/virtualfriam
> to (un)subscribe
http://redfish.com/mailman/listinfo/friam_redfish.com
> FRIAM-COMIC http://friam-comic.blogspot.com/
> archives: 5/2017 thru present
https://redfish.com/pipermail/friam_redfish.com/
> 1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
-. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom
https://bit.ly/virtualfriam
to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
FRIAM-COMIC http://friam-comic.blogspot.com/
archives: 5/2017 thru present
https://redfish.com/pipermail/friam_redfish.com/
1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
-. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
FRIAM Applied Complexity Group listserv
Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoom
https://bit.ly/virtualfriam
to (un)subscribe http://redfish.com/mailman/listinfo/friam_redfish.com
FRIAM-COMIC http://friam-comic.blogspot.com/
archives: 5/2017 thru present https://redfish.com/pipermail/friam_redfish.com/
1/2003 thru 6/2021 http://friam.383.s1.nabble.com/
