[FRIAM] Bard and Don Quixote
Steve Smith
sasmyth at swcp.com
Wed May 17 17:27:48 EDT 2023
On 5/17/23 10:47 AM, Marcus Daniels wrote:
>
> There are many idiosyncrasies of me that I would just as soon not
> exist. The new avatar could be the aspirational me!
>
It seems like it might be good if we are going post-human to polyp off
aspirational digital "clones" which can then try to survive in a digital
clone-ecosystem... maybe this could be a way humanity could make a
large (sociocultural) evolutionary lurch forward before we render it in
our genome?
> *From:* Friam <friam-bounces at redfish.com> *On Behalf Of *Prof David West
> *Sent:* Wednesday, May 17, 2023 8:59 AM
> *To:* friam at redfish.com
> *Subject:* Re: [FRIAM] Bard and Don Quixote
>
> My sympathies would be with your friend—until such time as a*/_"clone
> exactly like her ... behavior, words, or even existence..." _/*was
> demonstrated.
>
> "Exactly" is a big word! and I would add "completely."
>
> Even on a single dimension, say use of language, the standard of exact
> and complete is hard to satisfy.
>
> I have no problem believing that a chat-bot could write an academic
> paper or either of my books; put together, and deliver in my voice, a
> lecture ; play bar-trivia at the pub; or carry on a convincing
> conversation. I have no doubt that, in the very near future, the same
> bot might be able to project a video that included mannerisms and
> simulation of the way I pace around a classroom.
>
> But exactitude would require, not only, all the things I do do, and
> the idiosyncrasies in the way that I do them, but also the
> idiosyncrasies of my inabilities: I can never get the crossword clues
> involving popular culture, for example.
>
> If a clone is built that "walks like a duck and quacks like a duck"
> but does not migrate or lay eggs; is it really a duck?
>
> I would concede the equivalence issue of means or mechanisms behind
> the observable; e.g., it does not matter if the observed behavior
> results from electrons in gold wires or electrons in dendrites. But I
> would at least raise the question as to whether, in specific
> instances, a 'subjective' behind the behavior is or is not critical.
>
> For example, and forgive the personal, you have mentioned being in
> pain all of your life. Would it be necessary for a bot to "feel pain"
> as you have in order to "act exactly like you?" Or is there an
> "algorithmic equivalent" possible for the bot to utilize in order to
> obtain unerring verisimilitude?
>
> Then there is the whole question of experience in general. Would
> */_I_/* really be */_me_/*, sans the LSD trips over the years? If not,
> then how will the bot "calculate" for itself, identical or at least
> highly similar, experience equivalents.
>
> Even if, in principle, it were possible to devise algorithms and
> programs that did result in behavior that mimicked Dave at every stage
> of its existence, will those algorithms be invented and programs
> written before the heat death of the universe? You cannot attempt to
> finesse this quest by invoking "self-learning" because then you need a
> training set that is at least as extensive as the 75 year training set
> that the mechanism you would have me be, has utilized to become me.
>
> I might agree that, in principle,*/_"A bot that acts indistinguishably
> from how you act *is* you," _/*I think the implication of the word
> "indistinguishably" is a bar that will never be attained.
>
> davew
>
> On Tue, May 16, 2023, at 6:46 PM, glen wrote:
>
> > That's a great point. To be honest, anyone who is accurately mimicked by
>
> > a bot should be just fine with that mimicry, leveraging the word
>
> > "accurate", of course. I mean, isn't that a sci-fi plot? Your bot
>
> > responds to things so that you don't have to.
>
> >
>
> > A friend of mine recently objected that "algorithms" are "reductive". I
>
> > tried to argue that algorithms (in the modern sense of The Algorithm)
>
> > can be either reductive or expansive (e.g. combinatorial explosion). But
>
> > she was having none of it. I think her position boiled down to the idea
>
> > that humans are complex, multi-faceted, deep creatures. And taking 1 or
>
> > few measurements and then claiming that represents them in some space
>
> > reduces the whole human to a low-dim vector.
>
> >
>
> > So, for her, I can imagine even if she were cloned and her clone acted
>
> > exactly like her, she would never accept that clone's behavior, words,
>
> > or even existence as actually *being* her. There's some sense of agency
>
> > or an inner world, or whatever, that accuracy becomes moot. It's the
>
> > qualia that matter, the subjective sense of free will ... metaphysical
>
> > nonsense.
>
> >
>
> > A bot that acts indistinguishably from how you act *is* you. I guess I'm
>
> > dangerously close to claiming that GPT-4 and Bard actually are
>
> > sentient/conscious. *8^O
>
> >
>
> > On 5/16/23 11:50, Marcus Daniels wrote:
>
> >> I don’t really get it. Trump can go on a TV town hall and lie, and
>
> >> those folks just lap it up. Sue a company for learning some fancy
>
> >> patterns? Really? If someone made a generative model of, say, Glen’s
>
> >> visual appearance and vocal mannerisms and gave him a shtick that didn’t
>
> >> match up with his past remarks, I think I’d notice it right away. If
>
> >> a GPT-X could fake Eric Smith, I can safely take the blue pill. Some
>
> >> of our transactions will probably require more cryptographic signing.
>
> >> Fine, they probably should have already.
>
> >>
>
> >> *From:* Friam <friam-bounces at redfish.com> *On Behalf Of *Steve Smith
>
> >> *Sent:* Tuesday, May 16, 2023 11:33 AM
>
> >> *To:* friam at redfish.com
>
> >> *Subject:* Re: [FRIAM] Bard and Don Quixote
>
> >>
>
> >> Jochen -
>
> >>
>
> >> Very interesting framing... as a followup I took the converse
>
> >> (inverse?) question To GPT4..
>
> >>
>
> >> /If we consider an LLM (Large Language Model) as the Sancho Panza to
>
> >> the Don Quixote of its human users, we can explore a couple of
>
> >> potential aspects:/
>
> >>
>
> >> 1. /Grounding and Practicality: Sancho Panza is known for his
>
> >> grounded perspective and practicality, which complements Don
>
> >> Quixote's idealism. Similarly, an LLM can provide factual
>
> >> information, context, and practical insights to guide and
>
> >> support human users in their interactions. It can offer a wealth
>
> >> of knowledge and help bridge gaps in understanding, serving as a
>
> >> pragmatic companion./
>
> >> 2. /Balancing Imagination and Realism: Don Quixote embodies
>
> >> imagination and creative thinking, while Sancho Panza offers a
>
> >> more realistic viewpoint. Similarly, an LLM can enhance human
>
> >> creativity by generating imaginative ideas and expanding
>
> >> possibilities. At the same time, it can bring rationality and
>
> >> critical thinking, ensuring that the generated content aligns
>
> >> with facts and reason./
>
> >> 3. /Providing Different Perspectives: Sancho Panza often offers
>
> >> alternative viewpoints and challenges Don Quixote's romanticized
>
> >> notions. Similarly, an LLM can present diverse perspectives,
>
> >> consider different angles, and engage in nuanced discussions
>
> >> with human users. It can help users explore varying opinions and
>
> >> broaden their understanding of complex topics./
>
> >> 4. /Ethical Guidance: Sancho Panza acts as a moral compass,
>
> >> advising Don Quixote on the right course of action. In a similar
>
> >> vein, an LLM can provide ethical guidance by highlighting
>
> >> potential biases, promoting inclusivity, and encouraging
>
> >> responsible use of language and information. It can contribute
>
> >> to creating a more informed and ethical digital environment./
>
> >>
>
> >> /However, it's important to note that an LLM, as a machine learning
>
> >> model, lacks human experiences, emotions, and deeper understanding.
>
> >> While it can offer valuable assistance, it may not fully grasp the
>
> >> complexities of human interactions or possess the wisdom and
>
> >> empathetic qualities of a human companion like Sancho Panza.
>
> >> Therefore, while an LLM can serve as a useful tool, it should be
>
> >> complemented by human judgment and critical thinking to navigate the
>
> >> nuances of real-life situations./
>
> >>
>
> >> I am a couple of hours behind on the live feed Senate hearing on AI
>
> >> <https://www.judiciary.senate.gov/committee-activity/hearings/oversight-of-ai-rules-for-artificial-intelligence> listening in fits and starts between other things:
>
> >>
>
> >> 1. I was definitely impressed with Altman (OpenAI), Montgomery (IBM)
>
> >> and Marcus' (NYU) thoughtful and extrapolative responses rather than
>
> >> perhaps the more usual defensive/deflective/adversarial style that
>
> >> these hearings often have... I don't know who chose this
>
> >> particular lineup but I thought both Montgomery and Marcus made a
>
> >> good complement to Altman. If Google and Microsoft and ??? had been
>
> >> there it might have reflected more "competitive" or "showy" answers?
>
> >> 2. I was impressed with the Senators (compared to my fairly low
>
> >> expectations). Even Kennedy and Hawley managed not to do their
>
> >> usual grandstanding and and snide sniping. Altman handed Hawley's
>
> >> question "why don't we just let people sue you?" (as a mode of
>
> >> regulation/oversight) back to him quite deftly (in the style of "ass
>
> >> with both hands") by responding simply "I know of no reason people
>
> >> CAN'T sue us today if we cause harm". Marcus chipped in pretty well
>
> >> outlining how the current laws that *might* apply are not well
>
> >> suited for many reasons.
>
> >> 3. I felt that all three witnesses walked the fine line on the question
>
> >> of a "moratoriam" fairly deftly, acknowledging that they endorse the
>
> >> spirit of not running headlong and thoughtlessly into the future but
>
> >> at the same time there is no obvious practical way to implement and
>
> >> enforce this, but that they are all enforcing their own limits on
>
> >> how fast (and thoughtlessly?) they might roll out development to the
>
> >> public...
>
> >> 4. In closing Blumenthal suggested having ChatGPT rewrite the lyrics
>
> >> to "Don't Stop" (thinking about tomorrow (McVie-Fleetwood Mac) which
>
> >> I took to heart. I was not impressed with it's results and won't
>
> >> burden the list with it. I'm guessing Blumenthal did *not* actually
>
> >> do that but like Quixote, simply saw the windmill and thought it
>
> >> might be a giant?
>
> >>
>
> >> On 5/16/23 11:30 AM, Jochen Fromm wrote:
>
> >>
>
> >> I have asked Bard ( bard.google.com) today about Don Quixote from
>
> >> Cervantes, and if a large language model would be similar to a Don
>
> >> Quixote without a Sancho Panza.
>
> >>
>
> >> Here is what Bard replied:
>
> >>
>
> >> "In a way, large language models can be seen as Don Quixotes without
>
> >> Sancho Panzas. They are trained on massive amounts of text data, and
>
> >> they are able to generate text, translate languages, write different
>
> >> kinds of creative content, and answer your questions in an
>
> >> informative way. However, they are not always able to distinguish
>
> >> between reality and fiction, and they can sometimes make mistakes or
>
> >> generate text that is not accurate or helpful.
>
> >>
>
> >> Sancho Panza, on the other hand, is a realist who helps Don Quixote
>
> >> to stay grounded in reality. He provides Don Quixote with common
>
> >> sense and practical advice, and he helps him to avoid making mistakes.
>
> >>
>
> >> Large language models could benefit from having a Sancho Panza
>
> >> figure to help them to stay grounded in reality and to avoid making
>
> >> mistakes. This could be done by having a human being or another
>
> >> large language model to review the text that the large language
>
> >> model generates. This would help to ensure that the text is
>
> >> accurate, helpful, and appropriate"
>
> >>
>
> >> -J.
>
> >>
>
> >
>
> > -. --- - / ...- .- .-.. .. -.. / -- --- .-. ... . / -.-. --- -.. .
>
> > 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/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20230517/63afd7b1/attachment.html>
More information about the Friam
mailing list