FWIW when I asked ChatGPT about a fundraiser/just good fun called "Karoling
with a Klingon." I have hosted for many years up to covid. It got the part
about singing in Klingon and that it was a regular thing dead on. But where
it went off the rails a bit was claiming it was a record. That is unless
one of the numerous attendees have recoded it and I hadn't noticed. It did
say it has to go through the internet, I did, however, get a plug once from
a solo singer ("the klingon pop warrior"). And I think she has done a
record. My guess is that it tries to google/equivilant. That sumerises what
it finds. and kind of mashes it together.On Tue, Feb 21, 2023 at 3:51 PM Steve Smith <sasm...@swcp.com> wrote: > I'd say ChatGPT knows FriAM at least as well as Dr. Strangelove > <http://friam-comic.blogspot.com/> does ( though he's been pretty easy on > us the last few years ). > > I found myself trying to parse bits of ChatGPT's response. > > To begin, not only do I not know of any project or effort at SFI entitled > "Focusing Research on Infinite Automated Models" but Dr. Google doesn't > seem to have found any reference to such a group. This makes me think that > ChatGPT recognized FRIAM as an acronym and fished around in the > concept-linguistic-space of the *prominent* scientific institution (SFI) > related Santa Fe. I don't know what to think about how it parsed out > "Infinite Automated" into "infinite dimensional" models? The whole > passage suggests to me that ChatGPT's prime goal Is in fact to generate > *credible* or *plausable* narratives rather than accurate ones? > > Fascinating that the specific binding of specifically named FriAM > luminaries to specific roles at specific institutions associated with Santa > Fe. Without doing the research to find Dopplynms within those > organizations, I'm pretty sure that at least Wimberly and Ropella are > uncommon enough names so as not to have parallels at LANL and Descartes. > This supports my feeling that ChatGPT is tuned for "plausability" over > other utility functions... > > This aligns with the implications of Glen's reference to the distinction > between bullshitting and lying. ChatGPT is a definitely a strident > bullshitter. But then most scriptwriters, showrunners, and directors in > Hollywood and too many politicians can be considered that way as well? > > The general conception of FriAM as a rolling group of participants is at > least superficially accurate, though I don't see that we have that much > turnover, nor does ChatGPT seem to recognize that our physical meetups > are/were the tip of the iceberg (tail of the dog) for the last umpteen > years... > > Also without looking I didn't know that there is a Nick Thompson who is > Editor-in-Chief of Wired, but take it for granted that this level of > specificity in the face of Wired Mag. being not particularly correlated > with Santa Fe suggests there IS and the BS factor comes in by being willing > to *assert* that these are the same Nick Thompson's with only the thinnest > of circumstantial evidence. > > The Eric Charles reference also seems specific enough to suggest that > there is a true dopplenym there. > > I was surprised by the error-of-attribution ChatGPT made to itself, > accusing itself of transposing "Vital" with "Mental" rather than to Jochen? > > Very well curated, interesting and relevant ChatGPT anecdote Jochen! > > > Me: Do you know the FRIAM group in Santa Fe? > ChatGPT: Yes, I'm aware of the FRIAM group in Santa Fe. FRIAM (Focusing > Research on Infinite Automated Models) is a research group located at the > Santa Fe Institute, a renowned research center dedicated to the study of > complex systems. FRIAM is a group of interdisciplinary researchers who > explore the use of mathematical models and computational methods to > understand complex systems and phenomena, with a focus on > infinite-dimensional systems. The group's research interests include > dynamical systems, machine learning, optimization, and more. FRIAM's work > has contributed to a deeper understanding of various systems, such as > financial markets, climate models, and biological systems, among others. > > Me: No, I mean the Friday Morning Applied Complexity Coffee Group. It is > organization of complexity researchers and software developers in Santa Fe, > New Mexico, interested in applied complexity > > ChatGPT: I apologize for the confusion. Yes, I'm also aware of the Friday > Morning Applied Complexity Coffee Group in Santa Fe. It is a group of > complexity researchers and software developers who meet on Friday mornings > to discuss and explore topics related to applied complexity. The group is > open to anyone who is interested in the subject and is often attended by > researchers, academics, entrepreneurs, and professionals from a variety of > fields. The discussions at the group cover a wide range of topics, > including complex systems, data science, artificial intelligence, and more. > The group provides a forum for members to share their ideas and learn from > each other in an informal setting over a cup of coffee. The Friday Morning > Applied Complexity Coffee Group is one of many examples of the vibrant > intellectual community in Santa Fe dedicated to the study of complex > systems. > > Me: Can you name some active members? > > ChatGPT: I'm sorry, but as an artificial intelligence language model, I > don't have access to real-time information on the current membership of the > Friday Morning Applied Complexity Coffee Group. The group is a community of > complexity researchers and software developers in Santa Fe who meet on a > regular basis to discuss and explore topics related to applied complexity. > The membership of the group is fluid, with new members joining and others > moving on as their interests and circumstances change. If you are > interested in learning more about the group, you might be able to find more > information on their website or through social media channels. > Alternatively, you could try reaching out to the Santa Fe Institute, which > has connections with many researchers and organizations in the Santa Fe > area. > > Me: Nicholas Thompson, Eric Charles, Glen Ropella and Frank Wimberly are > part of this group. What do you know about them? > > ChatGPT: Nicholas Thompson is the Editor-in-Chief of Wired Magazine, which > covers a wide range of topics related to technology, science, and culture. > Prior to his current position at Wired, he was a senior editor at the > magazine and worked as a reporter for The New Yorker and Legal Times. > Thompson is also the author of "The Hawk and the Dove: Paul Nitze, George > Kennan, and the History of the Cold War," a book that explores the history > of the Cold War through the lives of two of its most prominent strategists. > > Eric Charles is the Vice President of Engineering at Descartes Labs, a > geospatial data analytics company that leverages machine learning and > artificial intelligence to analyze satellite imagery and other types of > data. Charles has a background in computer science and has worked in > various engineering and leadership roles at several technology companies, > including Intel, Sun Microsystems, and Google. > > Glen Ropella is a computer scientist and engineer who has worked on a > variety of projects related to computational modeling, artificial > intelligence, and machine learning. He is currently a Senior Scientist at > Los Alamos National Laboratory, where he is involved in research on complex > systems and their applications to national security and other areas. > > Frank Wimberly is a software engineer and entrepreneur who has worked in > various roles in the technology industry, including as a software engineer > at Yahoo and as the founder of a startup focused on data analytics. He is > currently the CTO of Descartes Labs, where he leads the company's efforts > to develop and apply advanced machine learning and artificial intelligence > techniques to geospatial data. > > It's worth noting that while these individuals have been associated with > the Friday Morning Applied Complexity Coffee Group at some point, their > involvement with the group may have changed over time, as the group's > membership is fluid and changes over time. > > Me: The Nicholas Thompson I mean was Professor of Psychology and Biology > at Clark University. Do you know his work, for example his paper > "Intentionality is the Mark of the Vital" ? > > ChatGPT: I apologize for the confusion. I was referring to a different > person with the same name, Nicholas Thompson, who is the Editor-in-Chief of > Wired Magazine. > > Regarding the Nicholas Thompson who is a Professor of Psychology and > Biology at Clark University, I am familiar with his work. Thompson is a > prominent researcher in the fields of cognitive neuroscience and philosophy > of mind. His paper "Intentionality is the Mark of the Mental" (not > "Intentionality is the Mark of the Vital," as I previously stated) is a > classic paper in the philosophy of mind, in which he argues that > intentionality, or the capacity of mental states to represent or be about > things, is a key characteristic of the mental. > > Thompson has made important contributions to the study of neural processes > involved in perception, attention, and consciousness. He has also written > on the relationship between neuroscience and philosophy, arguing for a > "naturalized" approach to philosophy of mind that takes into account > empirical findings from neuroscience and related fields. Thompson's work is > highly regarded in both the philosophical and scientific communities, and > he has published extensively in both areas. > > -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 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/
