[FRIAM] the inequities of uniquity
Steve Smith
sasmyth at swcp.com
Fri Mar 22 22:22:05 EDT 2024
Quantifying Uniquity? I don't remember if I've publicly anecdotalized it
but I first learned about the Drake Equation from a LASL (now LANL)
old-timer (who was not there but was at least one (Bacon-Erdos) degree
of indirection from the event) in about 1982 whilst standing in the
location where Enrico Fermi first posed the paradox... I suspect the
location was traded out several times (like Lincoln's or Washington's
Axe or the Ship of Theseus) until I was in a quonset hut lunchroom that
may well not have even been manufactured, much less erected in 1950 when
Fermi first postulated his paradox?
Me: what I was asking for (of GPT below) perhaps was a "drake equation"
for uniquity (uniqueness)?
U=P×D×C×I×S×A
For anyone interested in reflecting on the factors in the product, here
is my personal (qualitative)estimation:
P(t)=Population is a low-exponent exponential (the product of
population growth in the world and the increased literacy within the
population)
D(t)=Diversity might be a decreasing factor as globalization and
other factors assimilate diverse intellectual traditions get
assimilated or extincted.
C(t)= Connectivity might be growing combinatorically thanks to
various factors ranging from socio-cultural mixing to
telecommunications technology explosion (qualitative and quantitative)
I(t) = Intensity. I'm not sure I want to judge which sense or
magnitude to associate... call it a wash?
S(t, gp) = Stability (function of time and geopolitics?) Another I
don't want to judge, I think S(gp) is a function of C and D? I'll
call it (another) wash for the purpose.
A(t) = Accessibility. I believe that for the most part this is also
a (supra)linear function over time... based primarily on C above?
ChatGPT
ChatGPT
Creating a "Drake Equation" for uniqueness—or "uniquity," as you've
intriguingly termed it—would involve identifying the factors that
contribute to the emergence of unique ideas or concepts, much like the
Drake Equation does for extraterrestrial civilizations. While
quantifying uniqueness in ideas is inherently more abstract than
estimating the number of communicative civilizations in the galaxy, we
can propose a framework inspired by the Drake Equation to explore this
concept.
Let's define �U as the total number of unique, profound concepts that
could potentially be generated within a given cultural or intellectual
ecosystem over a specific period. We can then break down �U into several
factors:
�=�×�×�×�×�×�U=P×D×C×I×S×A
Where:
* �P = Population engaged in creative or intellectual pursuits.
* �D = Diversity of thought within the population, representing
different cultural, disciplinary, and individual perspectives.
* �C = Connectivity among the population, reflecting the ability to
share and combine ideas.
* �I = Intensity of intellectual exploration, indicating how deeply
individuals or societies engage with complex or abstract concepts.
* �S = Stability of the environment, as both too much and too little
can either stifle creativity or not give it enough ground to develop.
* �A = Accessibility of information and educational resources, which
fuel the generation of new ideas.
Explaining the Factors:
*
*Population (P):* More people potentially means more ideas, but
sheer numbers don't guarantee uniqueness. This factor considers not
just the global population but specifically those engaged in
generating new concepts.
*
*Diversity of Thought (D):* This is crucial for uniqueness. A
homogeneous group is less likely to generate radically new ideas
compared to a diverse group with varied experiences, disciplines,
and cultural backgrounds.
*
*Connectivity (C):* In today's world, connectivity is higher than
ever, facilitating the rapid combination and evolution of ideas.
However, the quality of connections matters as much as quantity.
*
*Intensity (I):* This reflects the depth of engagement with ideas.
Societies or groups that encourage deep, philosophical, or
speculative thinking are more likely to generate unique concepts.
*
*Stability (S):* A certain level of stability is necessary for
complex ideas to develop and be preserved, but too much stability
might prevent the emergence of radically new concepts.
*
*Accessibility (A):* Easy access to education, information, and
intellectual resources empowers more of the population to contribute
to the generation of unique ideas.
Considerations:
The "Drake Equation for Uniquity" is, of course, a theoretical and
playful exploration rather than a precise mathematical model. The
abstract nature of concepts and ideas, combined with the subjective
criteria for what constitutes "uniqueness" or "profoundness," makes it
challenging to apply strict numerical values to these factors. However,
this framework highlights the complexity and interdependence of
conditions that foster the creation of unique ideas, mirroring the way
the Drake Equation conceptualizes the search for extraterrestrial
intelligence.
By exploring the components that might contribute to the generation of
unique, profound concepts, we can appreciate the vast potential for
creativity and innovation within and across societies, emphasizing the
value of diversity, connectivity, and accessibility in enriching our
intellectual and cultural landscapes.
Apologies for not being able to cut-paste HTML/CSS from GPT into mail
more effectively...
On 3/22/24 2:50 PM, Steve Smith wrote:
>
> "Unique in a qualified manner"?
>
> FWIW, I prompted (Indra's Net edition) and sent my DALL-E images
> before I read Dave's entry into this fray...
>
> I have beat GPT and Gemini around the head and shoulders a bit at
> times to try to get it to expose it's own East/West (or hopefully more
> subtle and gradated) distribution of knowledge/training/??? but
> mostly I'd say it reports (given I have the same intrinsic myopias) on
> "Western" views of "Eastern" thought.
>
> I do wonder if DaveW or anyone else here with more interest or
> qualifications than I has explored the bi(multi?)modal distribution in
> the LLMs?
>
> I know EricS at the very least has some significant grounding in
> linguistics (and semiotics?) and perhaps perspective on the socio
> cultural implications of language constructions, etc. which might be
> evidenced in LLMs as-trained by our tech-billionaire (wannabes?)
>
>
> On 3/22/24 12:07 PM, Stephen Guerin wrote:
>> Are you saying it's unique to a degree? ;-)
>>
>>
>>
>> ____________________________________________
>> CEO Founder, Simtable.com
>> stephen.guerin at simtable.com
>>
>> Harvard Visualization Research and Teaching Lab
>> stephenguerin at fas.harvard.edu
>>
>> mobile: (505)577-5828
>>
>> On Fri, Mar 22, 2024, 9:31 AM Prof David West <profwest at fastmail.fm>
>> wrote:
>>
>> this is 'unique' only if you exclude Vedic, Buddhist, Taoist, ...
>> thought.
>>
>> davew
>>
>>
>> On Fri, Mar 22, 2024, at 9:54 AM, Stephen Guerin wrote:
>>> Prompt:
>>> Express a unique concept. Make it as profound as possible
>>>
>>> https://chat.openai.com/share/649bd4ca-f856-451e-83a2-01fc2cfe47fb
>>>
>>>
>>>
>>> On Fri, Mar 22, 2024, 6:50 AM glen <gepropella at gmail.com> wrote:
>>>
>>> I guess the question returns to one's criteria for assuming
>>> decoupling between the very [small|fast] and the very
>>> [large|slow]. Or in this case, the inner vs. the outer:
>>>
>>> Susie Alegre on how digital technology undermines free thought
>>> https://freethinker.co.uk/2024/03/interview-susie-alegre/
>>>
>>> It would be reasonable for Frank to argue that we can
>>> generate the space of possible context definitions,
>>> inductively, from the set of token definitions, much like an
>>> LLM might. Ideally, you could then measure the
>>> expressiveness of those inferred contexts/languages and
>>> choose the largest (most complete; by induction, each
>>> context/language *should* be self-consistent so we shouldn't
>>> have to worry about that).
>>>
>>> And if that's how things work (I'm not saying it is), then
>>> those "attractors" with the finest granularity (very slow to
>>> emerge, very resistant to dissolution) would be the least
>>> novel. Novelty (uniqueness) might then be defined in terms
>>> of fragility, short half-life, missable opportunity. But
>>> that would also argue that novelty is either less *real* or
>>> that the universe/context/language is very *open* and the
>>> path from fragile to robust obtains like some kind of
>>> Hebbian reinforcement, use it or lose it, win the hearts and
>>> minds or dissipate to nothing.
>>>
>>> I.e. there is no such thing as free thought. Thought can't
>>> decouple from social manipulation.
>>>
>>> On 3/21/24 13:38, Marcus Daniels wrote:
>>> > In the LLM example, completions from some starting state
>>> or none, have specific probabilities. An incomplete
>>> yet-unseen (unique) utterance would be completed based on
>>> prior probabilities of individual tokens.
>>> >
>>> > I agree that raw materialist uniqueness won't necessarily
>>> or often override constraints of a situation. For example,
>>> if an employer instructs an employee how to put a small,
>>> lightweight product in a box, label it, and send it to a
>>> customer by UPS, the individual differences metabolism of
>>> the employees aren't likely to matter much when shipping
>>> more small, lightweight objects to other customers. It
>>> could be the case for a professor and student too. The
>>> attractors come from the instruction or the curriculum. One
>>> choice constrains the next.
>>> >
>>> > -----Original Message-----
>>> > From: Friam <friam-bounces at redfish.com> On Behalf Of glen
>>> > Sent: Thursday, March 21, 2024 11:50 AM
>>> > To: friam at redfish.com
>>> > Subject: Re: [FRIAM] the inequities of uniquity
>>> >
>>> > I was arguing with that same friend yesterday at the pub.
>>> I was trying to describe how some of us have more cognitive
>>> power than others (he's one of them). Part of it is "free"
>>> power, freed up by his upper middle class white good diet
>>> privilege. But if we allow that some of it might be genetic,
>>> then that's a starting point for deciding when novelty
>>> matters to the ephemerides of two otherwise analogical
>>> individuals (or projects if projects have an analog to
>>> genetics). Such things are well-described in twin studies.
>>> One twin suffers some PTSD the other doesn't and ... boom
>>> ... their otherwise lack of uniqueness blossoms into uniqueness.
>>> >
>>> > His objection was that even identical twins are not
>>> identical. They were already unique ... like the Pauli
>>> Exclusion Principle or somesuch nonsense. Even though it's a
>>> bit of a ridiculous argument, I could apply it to your sense
>>> of avoiding non-novel attractors. No 2 attractors will be
>>> identical. And no 1 attractor will be unique. So those are
>>> moot issues. Distinctions without differences, maybe. Woit's
>>> rants are legendary. But some of us find happiness in
>>> wasteful sophistry.
>>> >
>>> > What matters is *how* things are the same and how they
>>> differ. Their qualities and values (nearly) orthogonal to
>>> novelty.
>>> >
>>> >
>>> > On 3/21/24 11:29, Marcus Daniels wrote:
>>> >> If GPT systems capture some sense of "usual" context
>>> based on trillions of internet tokens, and that corpus is
>>> regarded approximately "global context", then it seems not
>>> so objectionable to call "unusual", new training items that
>>> contribute to fine-tuning loss.
>>> >>
>>> >> It seems reasonable to worry that ubiquitous GPT systems
>>> reduce social entropy by encouraging copying instead of new
>>> thinking, but it could also have the reverse effect: If I
>>> am immediately aware that an idea is not novel, I may avoid
>>> attractors that agents that wrongly believe they are
>>> "independent" will gravitate toward.
>>> >>
>>> >> -----Original Message-----
>>> >> From: Friam <friam-bounces at redfish.com> On Behalf Of glen
>>> >> Sent: Thursday, March 21, 2024 7:49 AM
>>> >> To: friam at redfish.com
>>> >> Subject: Re: [FRIAM] the inequities of uniquity
>>> >>
>>> >> A friend of mine constantly reminds me that language is
>>> dynamic, not fixed in stone from a billion years ago. So, if
>>> you find others consistently using a term in a way that you
>>> think is wrong, then *you* are wrong in what you think. The
>>> older I get, the more difficult it gets.
>>> >>
>>> >> But specifically, the technical sense of "unique" is
>>> vanishingly rare ... so rare as to be merely an ideal,
>>> unverifiable, nowhere, non-existent. So if the "unique" is
>>> imaginary, unreal, and doesn't exist, why not co-opt it for
>>> a more useful, banal purpose? Nothing is actually unique. So
>>> we'll use the token "unique" to mean (relatively) rare.
>>> >>
>>> >> And "unusual" is even worse. Both tokens require one to
>>> describe the context, domain, or universe within which the
>>> discussion is happening. If you don't define your context,
>>> then the "definitions" you provide for the components of
>>> that context are not even wrong; they're nonsense. "Unusual"
>>> implies a usual. And a usual implies a perspective ... a
>>> mechanism of action for your sampling technique. So
>>> "unusual" presents even more of a linguistic *burden* than
>>> "unique".
>>> >>
>>> >> On 3/20/24 13:14, Frank Wimberly wrote:
>>> >>> What's wrong with "unusual"? It avoids the problem.
>>> >>>
>>> >>>
>>> >>> On Wed, Mar 20, 2024, 1:55 PM Steve Smith
>>> <sasmyth at swcp.com <mailto:sasmyth at swcp.com>> wrote:
>>> >>>>
>>> >>>> I'm hung up on the usage of qualified
>>> "uniqueness" as well, but in perhaps the opposite sense.
>>> >>>>
>>> >>>> I agree with the premise that "unique" in it's
>>> purest, simplest form does seem to be inherently singular.
>>> On the other hand, this mal(icious) propensity of qualifying
>>> uniqueness (uniqueish?) is so common, that I have to believe
>>> there is a concept there which people who use those terms
>>> are reaching for. They are not wrong to reach for it, just
>>> annoying in the label they choose?
>>> >>>>
>>> >>>> I had a round with GPT4 trying to discuss this,
>>> not because I think LLMs are the authority on *anything* but
>>> rather because the discussions I have with them can help me
>>> brainstorm my way around ideas with the LLM nominally
>>> representing "what a lot of people say" (if not think).
>>> Careful prompting seems to be able to help narrow down
>>> *all people* (in the training data) to different/interesting
>>> subsets of *lots of people* with certain characteristics.
>>> >>>>
>>> >>>> GPT4 definitely wanted to allow for a wide range
>>> of gradated, speciated, spectral uses of "unique" and gave
>>> me plenty of commonly used examples which validates my
>>> position that "for something so obviously/technically
>>> incorrect, it sure is used a lot!"
>>> >>>>
>>> >>>> We discussed uniqueness in the context of
>>> evolutionary biology and cladistics and homology and
>>> homoplasy. We discussed it in terms of cluster analysis.
>>> We discussed the distinction between objective and
>>> subjective, absolute and relative.
>>> >>>>
>>> >>>> The closest thing to a conclusion I have at the
>>> moment is:
>>> >>>>
>>> >>>> 1. Most people do and will continue to treat
>>> "uniqueness" as a relative/spectral/subjective qualifier.
>>> >>>> 2. Many people like Frank and myself (half the
>>> time) will have an allergic reaction to this usage.
>>> >>>> 3. The common (mis)usage might be attributable
>>> to conflating "unique" with "distinct"?
>>> >
>>>
>>>
>>> --
>>> ꙮ Mɥǝu ǝlǝdɥɐuʇs ɟᴉƃɥʇ' ʇɥǝ ƃɹɐss snɟɟǝɹs˙ ꙮ
>>>
>>> -. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. ---
>>> -.. .
>>> 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/
>>
>>
>> -. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
>> FRIAM Applied Complexity Group listserv
>> Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoomhttps://bit.ly/virtualfriam
>> to (un)subscribehttp://redfish.com/mailman/listinfo/friam_redfish.com
>> FRIAM-COMIChttp://friam-comic.blogspot.com/
>> archives: 5/2017 thru presenthttps://redfish.com/pipermail/friam_redfish.com/
>> 1/2003 thru 6/2021http://friam.383.s1.nabble.com/
>
> -. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
> FRIAM Applied Complexity Group listserv
> Fridays 9a-12p Friday St. Johns Cafe / Thursdays 9a-12p Zoomhttps://bit.ly/virtualfriam
> to (un)subscribehttp://redfish.com/mailman/listinfo/friam_redfish.com
> FRIAM-COMIChttp://friam-comic.blogspot.com/
> archives: 5/2017 thru presenthttps://redfish.com/pipermail/friam_redfish.com/
> 1/2003 thru 6/2021http://friam.383.s1.nabble.com/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20240322/06eebc4e/attachment-0001.html>
More information about the Friam
mailing list