Humanist Discussion Group, Vol. 36, No. 263.
Department of Digital Humanities, University of Cologne
Hosted by DH-Cologne
www.dhhumanist.org
Submit to: humanist@dhhumanist.org
[1] From: Thomas Gloning <thomas.gloning@germanistik.uni-giessen.de>
Subject: a robot wrote this / theatre criticism (235)
[2] From: Willard McCarty <willard.mccarty@mccarty.org.uk>
Subject: the bar set low (27)
--[1]------------------------------------------------------------------------
Date: 2022-11-21 20:27:07+00:00
From: Thomas Gloning <thomas.gloning@germanistik.uni-giessen.de>
Subject: a robot wrote this / theatre criticism
Dear Tim
many thanks for putting GPT-3 to the test. The system demonstrates that
it is able to address some specific topics and to use relevant
expression patterns. What I did not find are the more elaborate forms of
originality and creativity so characteristic for feuilleton writing.
In a realistic perspective, there are two more problems.
First, in order to write a piece of 'real' theatre criticism one has to
go to the theatre and actually watch the play.
Second, in order to give a sound evaluation of the play in question one
needs broad knowledge and experience with the standards of critical
evaluation.
While it seems possible to generate standard reports on football games
from the information gained from data bases, this method does not seem
viable in respect of forms of criticism.
> The play "Every Monday" by German playwright Bertolt Brecht
That was funny!
All best wishes and thanks again
Thomas
P.S.: For those with a command of German:
Gloning, Thomas: "Man schlürft Schauspielkunst ...". Spielarten der
Theaterkritik. In: Hagestedt, Lutz (Hg.): Literatur als Lust.
Begegnungen zwischen Poesie und Wissenschaft. Festschrift für Thomas
Anz. München: belleville 2008, 59-86.
Am 20.11.2022 um 08:52 schrieb Humanist:
> Humanist Discussion Group, Vol. 36, No. 262.
> Department of Digital Humanities, University of Cologne
> Hosted by DH-Cologne
> www.dhhumanist.org
> Submit to: humanist@dhhumanist.org
>
>
>
>
> Date: 2022-11-19 15:45:42+00:00
> From: Tim Smithers <tim.smithers@cantab.net>
> Subject: Re: [Humanist] 36.242: a robot wrote this...
>
> Dear Thomas,
>
> I saw nobody posted what GPT-3 might do in response to your
> "somewhat more diffuse (and more realistic) assignment."
>
> So, I gave GPT-3 this input, based upon your words.
>
> Write a theatre critique on every Monday on some memorable
> theatre event in southern Germany. Remember that originality
> and creativity are important maxims for feuilleton writing.
>
> And, with the Maximum Length output parameter set to 504, here
> are the five responses GPT-3 gave back, from submitting the
> same input five times.
>
> Output 1 :
>
> Monday, August 21, 2017
>
> Theatregoers in southern Germany were treated to a memorable
> event this past Monday, as the world-renowned Bavarian State
> Opera performed Verdi's "Aida" to a packed house. The
> production was a lavish affair, with grand sets and costumes
> befitting the epic scope of the opera. The singing was
> superb throughout, but special mention must be made of
> soprano Anna Netrebko, who brought a thrilling vocal
> performance to the title role. The emotionally charged
> finale brought the audience to their feet, giving the
> Bavarian State Opera a well-deserved standing ovation.
>
>
> Output 2 :
>
> The play "Every Monday" by German playwright Bertolt Brecht
> is a memorable theatre event in southern Germany. The play
> is a satire on the bourgeois way of life and its values.
> The playwright uses humour and irony to expose the
> shallowness and hypocrisy of the middle class. The play is
> still relevant today, as it speaks to the human condition
> and our need for compassion and understanding.
>
>
> Output 3 :
>
> Every Monday, I will be attending a different theatre event
> in southern Germany. This past Monday, I attended a theatre
> event at the Kammerspiele in Munich. The play was "The
> Glass Menagerie" by Tennessee Williams.
>
> I was very impressed with the production. The set design
> was very well done and the acting was excellent. I
> particularly liked the way the play was directed. It was
> very atmospheric and the use of lighting and sound was very
> effective.
>
> I would highly recommend this play to anyone who is looking
> for a good night of theatre.
>
>
> Output 4 :
>
> It was a Monday evening and the small, local theatre was
> packed. The play, "Every Monday on Some Memorable Theatre
> Event in Southern Germany", was a comedy about a group of
> friends who meet up every Monday to discuss a memorable
> theatre event from the previous week.
>
> The play was light-hearted and funny, but also touched on
> some deeper issues such as the importance of theatre in our
> lives and how it can bring us together. The acting was
> superb, and the audience was laughing and cheering
> throughout.
>
> Overall, it was a wonderful evening of theatre, and a great
> way to start the week.
>
>
> Output 5 :
>
> The play "Every Monday" is a heartwarming story about a
> group of friends who meet every Monday to play cards and
> reminisce about their lives. The play is set in southern
> Germany and revolves around the lives of the main
> characters, who are all in their 60s and 70s. The play is a
> series of vignettes that chronicle the friends' lives over
> the course of several years.
>
> The play is touching and funny, and the characters are very
> relatable. The playwright does a great job of capturing the
> essence of what it means to be a friend, and the importance
> of tradition. The play is a great reminder that even as we
> get older, we need to take time to enjoy life and our
> relationships.
>
> The play is directed by Hans-Jürgen Syberberg and stars
> Günter Lamprecht, Mario Adorf, and Senta Berger. The cast
> does a great job of bringing the characters to life and
> making them believable. The play is a bit slow at times,
> but overall it is an enjoyable theatre experience.
>
>
> I'm not a theatre critic, and thus not well placed to judge
> these attempts, but, apart from some inventiveness, I would
> say none of these get anywhere near what a real theatre critic
> would manage after every Monday.
>
> I've been playing around with GTP-3, off and on, for a while,
> and have never been impressed with anything it gives back,
> despite the enthusiastic claims I've heard from others who say
> they use -- I would say also play with -- GTP-3. It is
> always, I find, superficial, often silly, sometimes plain
> wrong, and nothing I would make use of, in a research
> publication, say, which is what a couple of the PhDers in the
> Research Publication course I'm currently teaching, have
> admitted to doing :(
>
> Best regards,
>
> Tim
>
>
>> On 7 Nov 2022, at 09:25, Humanist <humanist@dhhumanist.org> wrote:
>>
>>
>> Humanist Discussion Group, Vol. 36, No. 242.
>> Department of Digital Humanities, University of Cologne
>> Hosted by DH-Cologne
>> www.dhhumanist.org
>> Submit to: humanist@dhhumanist.org
>>
>>
>>
>>
>> Date: 2022-11-06 21:27:57+00:00
>> From: Thomas Gloning <thomas.gloning@germanistik.uni-giessen.de>
>> Subject: "A Robot Wrote This Entire Article" -- GPT-3
>>
>> Many thanks, Maurizio, for your pointers.
>>
>> <<the question is that of the production of text through the use of
>> systems of AI.
>>
>> from
>> GPT-3. 2020. «A Robot Wrote This Entire Article. Are You Scared yet,
>> Human?»/The Guardian/, 8 September 2020.
>> http://www.theguardian.com/commentisfree/2020/sep/08/robot-wrote-this-
article-
>> gpt-3.
>> to ... >>
>>
>> Reading this article, one finds that the result was produced by the
>> redaction of the "Guardian":
>>
>> << ///GPT-3 produced //eight different outputs//, or essays. Each was
>> unique, interesting and advanced a different argument. The Guardian
>> could have just run one of the essays in its entirety. However, w//e
>> //chose instead to //pick//the best parts of each, in order to capture
>> the different styles and registers of the AI.//Editing GPT-3’s op-ed was
>> no different to editing a human op-ed. We cut lines and paragraphs, and
>> rearranged the order of them in some places. Overall, it took less time
>> to edit than many human op-eds. >>/
>>
>> /It would have be good to document the eight different GPT-3-essays
>> together with what the Guardian made of it./
>>
>> /If you want to read an analysis of what GPT-3 achieved and did not
>> achieve in a similar case, there is a section in this new book:/
>>
>> /Gerd Fritz: /Coherence in discourse : a study in dynamic text theory
>> <https://hds.hebis.de/ubgi/Record/HEB498935477> (2022), chapter 11:
>>
>> http://dx.doi.org/10.22029/jlupub-791
>>
>> I wonder, what GPT-3 would come up with in respect of a somewhat more
>> diffuse (and more realistic) assignment like: "Please write a theatre
>> critique on every monday on some memorable theatre event in southern
>> Germany. Remember that originality and creativity are important maxims
>> for feuilleton writing."
>>
>> Thanks again, all best wishes
>>
>> Thomas
--[2]------------------------------------------------------------------------
Date: 2022-11-20 08:02:11+00:00
From: Willard McCarty <willard.mccarty@mccarty.org.uk>
Subject: the bar set low
Tim Smithers' note with his tests of GPT-3 as theatre critic remind me
of Archer and Jockers, The Bestseller Code: Anatomy of the Blockbuster
Novel (2016), detailing their successes in predicting best sellers. The
magic dissipates (at least somewhat) as soon as you notice that the
predictive mechanisms are is working within a formulaic genre. This
brings to mind Orwell's 'prolefeed' in 1984, "the rubbishy entertainment
and spurious news which the Party handed out to the masses"
(Appendix:. The Principles of Newspeak")--automatically generated,
as I recall.
I keep teasing the question of why so much effort is spent in imitating
human behaviour rather than exploring what Louis Milic called "the true
nature of the machine" ("The Next Step", CHum 1966), and why is it
that we seem to be impressed by its successes? Sure, it chronicles
what we take to be advances in artificial intelligence, but success at
imitating what? Advancement towards what? I would think that the
important question is the one we find on the dustjacket of The
Bestseller Code: what does GPT-3 and its kind "teach us about books,
stories, and reading"?
Yours,
WM
--
Willard McCarty,
Professor emeritus, King's College London;
Editor, Interdisciplinary Science Reviews; Humanist
www.mccarty.org.uk
_______________________________________________
Unsubscribe at: http://dhhumanist.org/Restricted
List posts to: humanist@dhhumanist.org
List info and archives at at: http://dhhumanist.org
Listmember interface at: http://dhhumanist.org/Restricted/
Subscribe at: http://dhhumanist.org/membership_form.php
