[FRIAM] Bard and Don Quixote

Tue May 16 14:50:54 EDT 2023

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/
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20230516/859073e8/attachment.html>