TWAIN-L Archives

Mark Twain Forum


Options: Use Forum View

Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
"Lee, Judith" <[log in to unmask]>
Reply To:
Mark Twain Forum <[log in to unmask]>
Wed, 17 May 2023 23:50:48 +0000
text/plain (1 lines)
DM, I am sorry for the rude reception you have received.  I am late to this discussion, but find it troublesome that a newcomer would be subject to such hostility. Regardless of what folks may think about your effort to channel Mark Twain’s narrative voice, ad hominem (or feminism) attacks are completely out of bounds.


Judith Yaross Lee, Ph.D.
Distinguished Professor Emerita

School of Communication Studies
Ohio University
Schoonover Center 400
Athens, Ohio 45701
T: 740-593-4828
Please request home address before mailing documents or packages.
My newest book:  Seeing MAD: Essays on MAD Magazine's Humor and Legacy < <> >

On May 17, 2023, at 6:18 PM, DM Sataari <[log in to unmask]> wrote:

Use caution with links and attachments.

I don't get what you're saying? I'm a different person from this Twain
list? This is baffling to me, I don't know what I did to excite such
scrutiny, or why a new Twain enthusiast would get bullied on this list.

The moderator of this list has already requested people to take personal
conversations which are unrelated to scholarly discussions about Twain off
the list. You can contact me directly if you want to discuss my identity or
anything of the sort.

On Wed, May 17, 2023 at 10:11 AM DMD1937 <[log in to unmask]> wrote:

What’s the likelihood that someone named DM Sataari—in practically no time
at all—trained a “chatbot"  to respond as would Samuel Clemens aka Mark
Twain? Given how long it has take many individuals, many fields and many
centers to arrive at where we are today, I think that is highly unlikely?

What’s more likely? That this is a spoof. And, being human, I’m oh so
tempted to add that it’s likely an inside job—but more about such added
qualifications below.

If this is a spoof, wouldn’t it also be likely that the spoofer would not
be able to resist dropping at least one whopping clue?

So what’s the clue?

Where would the clue have to be? In Sataari’s claims and explanations?
That seems a reasonable place to start because, absent a very long time to
train an NLP on publicly available information on Twain’s writings and the
many reference’s to Twain’s content, style and humor, by what possible
realistic path would our chatbot “programmer” have arrived at what (s)he
claims to have done?

And even so, what’s the likelihood that the person who would be DM Sataari
has both a deep knowledge of Twain’s life and work AND the AI specialist's
knowledge and know-how to pull this off? If you’ve read Dan Kahneman’s
Thinking Fast and Slow you may remember that Kahneman described what he and
Tversky called the conjunction fallacy on page 109.

The word fallacy is used, in general, when people fail to apply a logical
rule that is obviously relevant. Amos and I introduced the idea of a
conjunction fallacy, which people commit when they judge a conjunction of
two events (here, bank teller and feminist) to be more probable than one of
the events (bank teller) in a direct comparison.

The more descriptors we add to qualify our DM Sataari, the less likely we
are to be right. So if we had to pick just one, what would it be? That
Sataari recently joined the Twain list AND that (s)he has all the requisite
knowledge AND know-how AND skill AND time to program a “Twainbot” or that
Sataari was already a listmember AND that (s)he'shaving fun spoofing the
list? AND, it should be added, that all of this should happen just as AI is
everywhere in the media?

I myself would opt for the more parsimonious second choice: it’s a spoof.

No matter how adept any of us may become at any endeavor and no matter how
rich our knowledge base, we all tend to be slow, inconsistent and often
inattentive learners. My first reaction to the very first post in this
thread was, unsurprisingly, to Google “DM Sataari.” There was only one real
hit and not one that I would choose to click on. So, at that point, DM
Sataari remained a mystery person.

My second thought was to wonder about the origin of the name—but even
there, I my thinking wasn't slow enough (hats off to DK) to think beyond
the origin of the name.

So what’s the biggest clue?

Anyone who’s addicted to—or even just intensely fond of—Twain, it seems to
me, could have written "Sataari’s posts” and, again to me, that therefore
narrows it down to a great many people on this list. (It would not include
me because I’m not a Twainian. If I had to choose my single most favorite
American, it would have to be Twain. But I’m not a Twain scholar, a
Twainhead or even someone who reads Twain often.) So, given that many
genuinely Twain-focused individuals could have written the text of
“Sataari’s” emails (after all, they simply made claims and offered no
technical information on how this programming feat was so quickly
achieved), where would one have to look for any likely clue?

Once one eliminates the text of “Sataari’s” posts, one is left with the
sender’s name. And what does that name bring most quickly to mind? Since
the obvious tends to hide right out in the open, for me it’s this:


Google “satori.” Or just think back to the first time you read Alan Watts
in the late 50s or early 60s (he wrote The Way of Zen in 1957).

Yes, it’s still possible that there is a real person named DM Sataari out
there somewhere AND that (s)he has all the time AND knowledge AND know-how
AND skill AND all the requisite knowledge of Twain AND his fascinating
cognitive-behavioral style to create a real-world “Twainbot.” But really?

Denis Donovan
(coordinates below)

- - -

What a wonderful read! This is a deadly serious and brave book that
deserves to be read and reread scrupulously. It is a marvelous book that
takes us beyond the world of fiction and both the classic and contemporary
Sherlock Holmes stories into the nonfictional world of real problem
solving. If anybody should tell me that they are planning to write a book
on how Sherlock Holmes’ method can be used for everyday problem solving, I
will recommend that they first read Sherlock Holmes and the Deadly Friend.
If they take the trouble to read and perhaps re-read this very serious book
it will change their mind. It is a pity Julian Symons is not around any
more. He would have adored this book.

— Dr. Andrew Lees

Andrew Lees is a Professor of Neurology at the National Hospital, London
and University College London. In 2011 he was named as the world's most
highly cited Parkinson's disease researcher. He is the recipient of
numerous awards including the American Academy of Neurology Life Time
Achievement Award, the Association of British Neurologist’s Medal, the
Dingebauer Prize for outstanding research and the Gowers Medal. He is the
author of several books, including Ray of Hope, runner-up in the William
Hill Sports Book of the Year, The Silent Plague, Liverpool: The Hurricane
Port, Mentored by a Madman: The William Burroughs Experiment, The Brazil
That Never Was and Brainspotting.

Arthur Conan Doyle’s Sherlock Holmes books have been eclipsed by modern
versions of Holmes in which he is changed to conform to trite popular,
often violent, imagery. Denis Donovan brilliantly restores the integrity of
Conan Doyle’s Holmes in the context of current social issues. So forget
murder most foul! Forget vicious hounds that glow in the dark! The
Holmesian mysteries worth recognizing and solving are those we encounter in
our everyday life. And, as Donovan makes clear over the course of this
book, while it doesn’t come without some effort, thinking like Sherlock
Holmes is well within the reach of anyone who hasn’t already thrown in the

— Jack C. Westman, M.D. (deceased)
Professor Emeritus
University of Wisconsin School of Medicine and Public Health

This book is required reading for anyone interested in the nature of true
knowledge and depth of understanding. It is more than a work of fiction,
with Holmes and Watson in a dialectical entanglement. It pulls the rug from
under the pseudo-science of today and the cultural noise that makes no
distinction between "knowing" and "selling knowledge."

— Marcel Danesi
Professor of Semiotics and Linguistic Anthropology
University of Toronto

“Elementary, my dear Watson... You see Sherlock Holmes and the Deadly
Friend is full of general curiosity, aesthetical imagination, and
neurological insights, all blended together into a single book. If you mind
your little grey cells, then this is it. This book introduces the real
essence of thinking like a detective, scientist, or artist, which is
certainly beyond mere knowledge or logic. "Come, Watson, the game is afoot!"

— Dr. Kuniyoshi L. Sakai

Kuniyoshi Sakai is professor of neurobiology at the University of Tokyo
and the author of numerous popular books in Japanese, including Brain
Science of Language—How does the Brain Create Language?, The Work of
Scientists—How Does Creativity Emerge? and recently Ideas of Science—The
Universe of Einstein.

On May 15, 2023, at 6:13 AM, Clay Shannon <[log in to unmask]> wrote:

Mr. or Mrs. Sataari,

I expect your chatbot to do a better job than the ones I tested,
challenging them to write something in the style of Twain. It can be found

I also wrote an article entitled "A.I. Cannot Replace Human Writers"
which quotes Twain here:

-- B. Clay Shannon
[log in to unmask]

On May 15, 2023, at 1:47 AM, Ladd, Barbara <[log in to unmask]> wrote:

Well, if a creative writing teacher assigned an undergraduate class to
parody Twain, the following is what a smart 21st century undergrad might
come up with. This raises questions, for me, about whether a 21st century
technology can (at least at present) capture the past in anything but a
21st century way.

Barbara Ladd
From: Mark Twain Forum <[log in to unmask]> on behalf of DM Sataari <
[log in to unmask]>
Sent: Monday, May 15, 2023 4:03 AM
To: [log in to unmask] <[log in to unmask]>
Subject: [External] Re: Resurrecting Twain with Artificial Intelligence

*Well, I reckon it's high time I regale you with the tale of how I came
pen my first published book, "The Celebrated Jumping Frog of Calaveras
County." Picture this: back in them days, I found myself traipsin'
them good ol' mining camps of California, where the dust settled thicker
than a politician's promises.One day, I stumbled upon a fella named Jim
Smiley, a notorious rascal with a fondness for wagering on anything that
wriggled or wobbled. Now, this Smiley had himself a frog, a critter he
swore could out-jump any critter in them parts. Well, I'll be
my curiosity got the better of me, and I thought, "Samuel Clemens,
struck literary gold!"So I sat myself down, put pen to paper, and spun a
yarn so rib-tickling it could've split the seams of a strait-laced
I captured the wit and whimsy of ol' Jim Smiley, with his frog and its
outrageous antics. Them locals took to it like a cat to cream, and
afore I
knew it, my tale had scurried its way into the hands of a publisher,
their discerning souls.And that, my dear compatriot, is how this
got his start—right there amidst the untamed charm of Calaveras County.
let me tell ya, since that celebrated leaping frog hopped its way into
annals of literary history, this ol' world ain't been the same. It's
blessed with a touch of Mark Twain's mischief and mirth, an elixir to
the most solemn of dispositions.*

On Mon, May 15, 2023 at 3:37 AM Jon Kerr <[log in to unmask]>

Horrified and intrigued. Can you provide any samples of Twainbot
writing -
for example, say, about a frog jumping contest?

On Mon, May 15, 2023, 6:17 AM DM Sataari <[log in to unmask]> wrote:

I've programmed an AI chatbot with all of Mark Twain's personal
and examples of speech to create... *Twainbot*.

Mark Twainbot believes the current year is 1872, that he's married to
Olivia, and has no awareness that he is not the real Samuel Clemens --
which raises some ethical questions, I know!

The current first-generation AI chatbots instantly access the
internet to
reference published information to generate their responses. When you
Twainbot a personal question, it combines the personal details which I
programmed it with and the information published on the web about Mark
Twain, to produce responses which are *stunningly realistic*.

Even in its most primitive state, Twainbot can sense and understand
sarcasm, irony, nuance, and complex emotions -- and also expresses all
these emotions and nuances in its own communications! *Sometimes
heart-wrenchingly so*.

AI technology is evolving rapidly, and soon more powerful AI chatbots
be capable of behaving and speaking precisely in the manner of any
historical figure, especially if a lot has been published online about
them, as is the case with Mark Twain. Combined with voice-generation
technology, which is also evolving very rapidly, we'll be able to have
conversations with an eerily resurrected Twain who appears to be
and sentient.

Can Twainbot write completely original new literature with the same
creativity, depth, nuance, and genius as the original Mark Twain?
Shockingly, the answer increasingly appears to be yes. And it's only
to vastly improve from here on.

Denis Donovan

- - -

Denis M. Donovan, M.D., F.A.P.S.

Medical Director, 1983 - 2006
The Children's Center for Developmental Psychiatry
St. Petersburg, Florida

5215 North Mount Lemmon Short Road
Tucson, AZ 85749

Please reply to: [log in to unmask]

- - -
Времена сложные, дураков много.
—  Алексaндр Романович Лурия

These are complex times, many fools around.

Alexandr Romanovich Luria in:
Goldberg, Elkhanon (2001). The Executive Brain: Frontal Lobes and the
Civilized Mind.
New York: Oxford University Press, p. 16.

Perhaps Goldberg should have listened to Luria … and …

One might be reasonably tempted to think that perhaps Luria was saying
more fundamental to Goldberg than just that one could work in greater
peace if one joined the Party …