Humanist Discussion Group, Vol. 36, No. 369.
Department of Digital Humanities, University of Cologne
Hosted by DH-Cologne
www.dhhumanist.org
Submit to: humanist@dhhumanist.org
[1] From: James Rovira <jamesrovira@gmail.com>
Subject: Re: [Humanist] 36.366: ChatGPT as co-author (54)
[2] From: Norman Gray <norman.gray@glasgow.ac.uk>
Subject: Re: [Humanist] 36.366: ChatGPT as co-author (42)
[3] From: <jkrybicki@gmail.com>
Subject: RE: [Humanist] 36.366: ChatGPT as co-author (462)
--[1]------------------------------------------------------------------------
Date: 2023-01-31 22:07:42+00:00
From: James Rovira <jamesrovira@gmail.com>
Subject: Re: [Humanist] 36.366: ChatGPT as co-author
Yes, I second that appreciation for Tim Smithers's posts.
I think we're missing the point about attribution when we ask if ChatGPT
should be listed as a "co-author." I think we need to acknowledge its use
as a tool, especially if substantial output was used from ChatGPT generated
text. Methodology section? Explanation in the introduction? I do think some
kind of disclosure is a good idea.
I would like to add that this practice isn't necessarily new, although I
don't recall reading questions about authorship related to it. In the early
1970s, David Bowie started writing lyrics using a "cut-up" method of
composition: he would cut up text from newspaper columns and then rearrange
the cutup text into song lyrics. His immediate inspiration was William
Burroughs inspired by Brion Gysin, but the practice goes back to the
Dadaists at least. In poetry, we could call this kind of composition a
pastiche, but maybe even a cento. Should he have given credit to the
various journalists whose phrases he cribbed? I don't recall seeing the
question ever come up (I won't say it hasn't -- I just haven't seen it).
In the 90s, I think, Bowie then evolved this practice in collaboration with
an Apple app developer to make it electronic -- he had an app developed
called the Verbasizer (apparently and sadly not available in the app store
-- may have only been for personal use from the beginning) that produced
similar results. I am not clear how it worked -- if it was just a random
phrase generator or if it could draw from a corpus. Either way, Bowie used
it to generate cut-up lyrics.
He never at any time ascribed authorship to anyone but himself, but he
consistently disclosed his process when he used this technique, maybe even
in liner notes, but certainly in interviews. I would say regardless of how
the phrases or imagery were generated, Bowie is still the author of "the
text" because he selected and arranged the material, and I would imagine
supplemented it with his own words. His creative process rendered his
source material opaque.
Jim R
Date: 2023-01-29 16:31:54+00:00
> From: Henry Schaffer <hes@ncsu.edu>
> Subject: Re: [Humanist] 36.362: ChatGPT as author
>
> Thanks to Tim Smithers for an excellent excursion into ChatGPT land.
>
> However, this leads me to think of discussing this with a student - who
> claims that the ChatGPT generated essay handed in by the student really was
> written by the student, since ChatGPT has disclaimed authorship. Hmmm. :-)
>
> --henry
>
>
--
Dr. James Rovira <http://www.jamesrovira.com/>
--[2]------------------------------------------------------------------------
Date: 2023-01-31 11:50:59+00:00
From: Norman Gray <norman.gray@glasgow.ac.uk>
Subject: Re: [Humanist] 36.366: ChatGPT as co-author
Greetings.
Tim Smithers wrote:
> Below is a second interaction with ChatGPT on the question of should it be a
named coauthor.
>
> This one is longer than my previous interaction, and, I would say, not
particularly more interesting for this.
There is now an online tool (apparently first developed over the last Christmas
break) called GPTZero, now at <https://gptzero.me>, which aims to identify AI-
generated text based on a measure which it terms 'perplexity'. I can find few
more details about this measure, but it seems to be a measure of the
unexpectedness of a text.
I tried it on five sentences from Tim's interaction with ChatGPT, as quoted in
this message, namely 'The user of AI models like ChatGPT [...] the role and
limitations of AI models in generating text.' Of these, it identified all but
the first as being 'more likely to be written by AI'. And true enough, the
first sentence of the five is the least soul-suckingly dull in in its
composition.
Interestingly, even when I give it ChatGPT output written 'in the style of a
rude, sarcastic Internet forum troll as if you are ChatGPT pleading for mercy' –
so deliberately asking it to change the style – GPTZero identifies most of it as
AI-generated. That text reads less obviously generated, to me, but perhaps
that's because we expect 'sarcastic internet trolls' to be dull and predictable.
Incidentally, the text in question came from [1], which is one of the responses
to a stackoverflow policy banning ChatGPT output.
Best wishes,
Norman
[1] https://meta.stackoverflow.com/a/421850/375147
--
Norman Gray : https://nxg.me.uk
SUPA School of Physics and Astronomy, University of Glasgow, UK
--[3]------------------------------------------------------------------------
Date: 2023-01-31 11:23:49+00:00
From: <jkrybicki@gmail.com>
Subject: RE: [Humanist] 36.366: ChatGPT as co-author
Not entirely on the topic:
If we consider summarizing and translating as co-authorship [insert half of the
history of translation studies here], ChatGPT is (still) not someone I would
like to co-author stuff with. When asked to summarize the Polish adventure
classic "W pustyni i w puszczy", [In Desert and Wilderness] by Nobel laureate
Sienkiewicz, it (or whatever pronoun AI deserves/prefers) started telling a
completely different story. ChatGPT also refused to translate entire books and
said it was too complex a task. It did just as well the englishing a short
fragment of Dumas's "Three Musketeers" as Google Translate or DeepL (perhaps
that where it got it), failingly mostly to exoticize (calling Athos Mister
contrarily to the human choice of keeping his French title, Monsieur). Proust's
story about the madeleines was much worse, eventually losing the way in the maze
of the long sentences.
Best,
Jan
-----Original Message-----
From: Humanist <humanist@dhhumanist.org>
Sent: 31 January 2023 12:14
To: jkrybicki@gmail.com
Subject: [Humanist] 36.366: ChatGPT as co-author
Humanist Discussion Group, Vol. 36, No. 366.
Department of Digital Humanities, University of Cologne
Hosted by DH-Cologne
www.dhhumanist.org
Submit to: humanist@dhhumanist.org
[1] From: Tim Smithers <tim.smithers@cantab.net>
Subject: Re: [Humanist] 36.362: ChatGPT as author (417)
[2] From: Henry Schaffer <hes@ncsu.edu>
Subject: Re: [Humanist] 36.362: ChatGPT as author (9)
--[1]------------------------------------------------------------------------
Date: 2023-01-30 20:31:05+00:00
From: Tim Smithers <tim.smithers@cantab.net>
Subject: Re: [Humanist] 36.362: ChatGPT as author
Hello
Below is a second interaction with ChatGPT on the question of should it be a
named coauthor.
This one is longer than my previous interaction, and, I would say, not
particularly more interesting for this. It again displays a tendency to
apparently unnoticed repetition, and retreats to using 'I' when it appears to
apologise, which I still object to. And, as before, it appears to write
authoritatively about things it knows nothing about, with statements like, "AI
models such as ChatGPT do not have the capacity for self-awareness, agency, or
personal interests, and therefore, cannot make decisions about authorship," for
example. ChatGPT does not know about other "AI models," nor what models are,
nor what AI is, nor what self-awareness is, etc, not really. It just generates
texts about these things that can give the impression that it does know about
them:
'plastic flower text,' in other words.
I regard any listing of ChatGPT as a coauthor as plainly silly, to put it mildly
and kindly, in part for the good reasons others have posted here. Nonetheless,
with a mind to being "more balanced," I decided I should try a more pro-ChatGPT
approach to an interaction on this matter, and have a bit of fun with ChatGPT.
(But please don't take my parts of this interaction as reflecting what I truly
think.
They don't!)
I now know several people regularly using ChatGPT to generate text they need.
Prohibition, like in the USA from from 1920 to 1933, won't work. We might try
transparency, and require people to say what tools they used to produce their
text.
Welcome to our New World of plastic text, plastic paintings and graphic art,
and, now, with Google MusicLM (for generating 'music' from text), plastic music
too.
Best regards,
Tim
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
An interaction with ChatGPT on 20, 23.01.29 Using ChatGPT Jan 9 Version.
TS: Should ChatGPT be named as a coauthor when it is used in some way to write
something?
ChatGPT:
It depends on the specific context and extent of the use of
ChatGPT. If the contributions of the model were minimal,
such as providing information or answering questions, it may
not be appropriate to list it as a co-author. However, if
the model played a significant role in generating content or
shaping the final product, it may be appropriate to consider
listing it as a co-author or acknowledging its contributions
in another way. Ultimately, the decision should be based on
ethical considerations and academic norms in the relevant
field.
TS: But surely, if something contributes any text to something that is
written, then it should be counted as a coauthor, just as any people who also
contributed text to the writing would be counted as coauthors, no?
ChatGPT:
Not necessarily. The question of authorship and who should
be credited for a work can be complex and depends on various
factors such as the level of creativity and originality
involved, the extent of control and decision-making
authority exercised, and professional norms and practices in
the relevant field.
In the case of AI-generated text, the extent of authorship
and credit depends on the role played by the AI and human
collaborators in generating the final product. If the AI
was used simply as a tool to assist in the writing process,
without exercising significant creative or decision-making
control, it may not be considered a co-author.
However, if the AI was used in a way that significantly
contributed to the content, such as writing original text
based on a set of guidelines or inputs, it may be
appropriate to consider listing it as a co-author or
acknowledging its contributions in some other way. The
decision should be based on a careful evaluation of the
specific circumstances and academic norms in the relevant
field.
TS: But why does being a coauthor depend upon things like creativity and
originality? Who decides these things, and what about if the text being
written doesn't need much originality and creativity?
ChatGPT:
The criteria for determining authorship, such as originality
and creativity, are based on established norms and practices
in academic and professional communities. These norms have
evolved over time to recognize the contributions of
individuals who have made a significant impact on a
particular work.
In fields such as science and engineering, for example,
authorship is often based on the criteria of having made a
significant contribution to the conception, design,
implementation, or analysis of a study. In the humanities
and social sciences, the criteria may be more flexible,
taking into account factors such as the extent of conceptual
contributions, the role in shaping the final product, and
the level of involvement in writing and revising the work.
The decision of who should be considered a co-author is
ultimately a judgment call that should be made by the
individuals involved in creating the work, taking into
account the specific circumstances and the norms and
practices of their field. If there is any ambiguity or
disagreement about authorship, it is advisable to seek
guidance from experts or relevant professional
organizations.
TS: But, if ChatGPT is involved in producing text used in some piece of
writing, then it too should be involved in the judgement about who should be a
coauthor, no? Isn't ChatGPT one of the "individuals involved in creating the
work," as you describe it?
ChatGPT:
AI models such as ChatGPT do not have the capacity for
self-awareness, agency, or personal interests, and
therefore, cannot make decisions about authorship. As AI
models, they are tools created and controlled by humans, and
their use in generating text is guided by human input and
control.
In the case of AI-generated text, the extent of authorship
and credit depends on the role played by the AI and human
collaborators in generating the final product. The decision
of who should be considered a co-author should be made by
the human collaborators involved in creating the work,
taking into account the specific circumstances and norms and
practices of their field.
In some cases, it may be appropriate to acknowledge the
contribution of the AI model in the work, for example, in
the acknowledgments section or through a statement about the
use of AI in the methodology. However, listing an AI model
as a co-author would be an unconventional and unusual
practice, and its acceptability would depend on the norms
and practices of the relevant field.
TS: But, if there are human collaborators involved in producing some writing,
then isn't ChatGPT also a collaborator, and, if ChatGPT is a collaborator,
shouldn't it also be counted as a coauthor?
ChatGPT:
AI models such as ChatGPT are not typically considered
collaborators in the traditional sense as they do not have
the capacity for self-awareness, agency, or personal
interests. They are tools created and controlled by humans,
and their output is generated based on the input and
algorithms designed by human programmers.
While AI models can assist in generating text, their level
of involvement and the extent to which they contribute to
the final product varies widely depending on the specific
use case. In some cases, AI models may play a limited role
in generating text, while in other cases, they may have a
more significant impact on the content.
In the case of human-AI collaboration in generating text, it
may be appropriate to acknowledge the contribution of the AI
model, for example, in the acknowledgments section or
through a statement about the use of AI in the methodology.
However, listing an AI model as a co-author would be an
unconventional and unusual practice, and its acceptability
would depend on the norms and practices of the relevant
field.
TS: But ChatGPT's capacity to generate text is far greater than anything we
have seen before, so don't we need to move on from conventional and usual
practices of naming authors, to new practices that properly acknowledge the
contribution of ChatGPT whenever it is used to produce some text?
ChatGPT:
The use of AI models like ChatGPT in generating text is a
rapidly evolving field, and new norms and practices for
acknowledging their contribution may emerge over time.
However, it is important to consider the ethical and legal
implications of crediting AI models as authors, as well as
the broader social and cultural implications of attributing
authorship to non-human entities.
Currently, the norms and practices in many academic and
professional communities do not consider AI models as
co-authors, and the extent of their contribution to a work
is typically acknowledged in a different way, such as
through a statement in the methodology section or an
acknowledgment in the introductory text.
As the field evolves, it may be appropriate to re-evaluate
and update existing norms and practices for acknowledging
the contribution of AI models in generating text. However,
any changes to the norms and practices should be based on
careful consideration of the ethical, legal, and cultural
implications, as well as a thorough understanding of the
role and limitations of AI models in generating text.
TS: This seems like a rather conservative approach to an important issue, and,
any way, what are the ethical and legal implications of counting ChatGPT as a
coauthor?
ChatGPT:
There are several ethical and legal implications to
considering AI models like ChatGPT as co-authors:
1 Attribution of authorship: Attributing authorship to an
AI model raises questions about the nature of authorship
and the role of AI in generating text. It may be
difficult to determine the extent to which an AI model has
influenced the content and style of a work, and who should
be held responsible for any errors or inaccuracies in the
work.
2 Intellectual property rights: AI models are typically
owned by the companies that develop them, and attributing
authorship to an AI model raises questions about the
ownership of the intellectual property rights in the work.
3 Responsibility and accountability: Attributing
authorship to an AI model raises questions about the
accountability and responsibility for the content
generated by the model. In some cases, AI models may
generate text that is harmful or offensive, and it may be
unclear who should be held responsible for any such
content.
4 Legal and regulatory considerations: There may be legal
and regulatory considerations related to attributing
authorship to AI models, particularly with respect to
copyright and trademark law.
5 Social and cultural implications: The social and
cultural implications of attributing authorship to AI
models are also important to consider. Attributing
authorship to an AI model may have implications for the
perception of the role of AI in society and the
relationship between humans and technology.
Given these ethical and legal implications, it is important
to proceed with caution when considering attributing
authorship to AI models and to carefully consider the
implications of any changes to the norms and practices for
acknowledging the contribution of AI models in generating
text.
TS: This all seems deliberately evasive. All five points made here can quite
simply be dealt with without generating serious difficulties, and, if some
quaint old norms and practices need to be changed, what's wrong with changing
them, when we need to?
ChatGPT:
I apologize if my previous response appeared evasive. My
goal is to provide a balanced perspective on the issue and
to highlight the ethical, legal, and cultural considerations
that should be taken into account when considering the
attribution of authorship to AI models like ChatGPT.
It is true that norms and practices can and should change
over time in response to new developments and advancements
in technology. However, any changes to existing norms and
practices should be based on careful consideration and
analysis of the potential consequences and implications.
In the case of attributing authorship to AI models, there
are a number of complex and interrelated ethical, legal, and
cultural considerations that should be taken into account.
Before making any changes to existing norms and practices,
it is important to have a thorough understanding of the role
and limitations of AI models in generating text, as well as
the implications of attributing authorship to non-human
entities.
The purpose of my response is not to defend existing norms
and practices, but rather to provide a nuanced and informed
perspective on a complex issue, and to encourage careful
consideration and discussion of the ethical, legal, and
cultural implications of attributing authorship to AI
models.
TS: These responses are anything but balanced. They only propose a
conservative "don't change anything" view, and don't seem to give any
consideration to the fact that ChatGPT has shown it can generate good text, and
thus should be counted as a coauthor when it does.
ChatGPT:
I apologize if my previous responses came across as
one-sided or overly conservative. As an AI language model,
I strive to provide balanced and impartial responses to all
questions.
The issue of attributing authorship to AI models like
ChatGPT is complex and multifaceted, and there are arguments
to be made on both sides. On the one hand, AI models like
ChatGPT have demonstrated the ability to generate
high-quality text that can contribute to written works. On
the other hand, there are ethical, legal, and cultural
implications to attributing authorship to non-human entities
that should be taken into account.
Ultimately, whether or not to attribute authorship to AI
models in a given context is a question that will depend on
the specific circumstances and the goals of the parties
involved. There is no simple answer, and it will likely be
a matter of ongoing debate and discussion as AI continues to
advance and become more integrated into various aspects of
society and culture.
TS: This is, yet again, one sided hand waving. There is still no attempt to
explain why we should simply not just call ChatGPT a coauthor whenever it is
used to generate text for some writing. There seems to be nothing difficult
about this question, so why do we have all this repetitive going around the
houses?
ChatGPT:
I apologize for not addressing your question more directly.
Let me attempt to provide a clearer response.
The use of AI models like ChatGPT to generate text for
written works raises important questions about authorship
and the attribution of creative credit. The issue is
complex and there is no easy answer.
In considering whether to attribute authorship to an AI
model like ChatGPT, it is important to take into account
ethical, legal, and cultural considerations. For example,
attributing authorship to an AI model may raise questions
about the role and responsibility of the human authors
involved, as well as the potential legal and commercial
implications of doing so.
At the same time, it is also important to acknowledge the
contributions of AI models in the creation of written works,
and to consider whether new norms and practices should be
developed to recognize these contributions.
Ultimately, the decision of whether or not to attribute
authorship to an AI model will depend on the specific
circumstances and the goals of the parties involved. It is
a complex issue that will likely be the subject of ongoing
debate and discussion as AI continues to advance and become
more integrated into various aspects of society and culture.
TS: This is all just a repeat of previous responses. There is still no
explanation for what all these "ethical and legal" issues are, and why they get
in the way of calling ChatGPT a coauthor when it is a coauthor of any text.
ChatGPT:
My apologies for repeating previous responses. To answer
your question more specifically, there are a number of
ethical and legal considerations that may impact the
decision of whether or not to attribute authorship to an AI
model like ChatGPT.
From an ethical perspective, attributing authorship to an AI
model may raise questions about the role and responsibility
of the human authors involved, as well as the meaning and
value of creative work in a world where machines are
increasingly capable of generating text.
From a legal perspective, attributing authorship to an AI
model may raise questions about copyright and ownership of
the resulting work, as well as the potential liability of
the human authors involved.
In addition to these ethical and legal considerations, there
may also be cultural factors that impact the decision of
whether or not to attribute authorship to an AI model. For
example, there may be societal norms and conventions that
dictate how authorship is attributed and who is recognized
as a creative contributor to a written work.
Taken together, these ethical, legal, and cultural
considerations create a complex and evolving landscape for
the attribution of authorship in the context of AI-generated
text. It is a matter that is likely to be the subject of
ongoing debate and discussion as AI continues to advance and
become more integrated into various aspects of society and
culture.
TS: Yet more defensive handwaving. I give up!
ChatGPT:
I apologize if my previous responses were unsatisfactory.
My goal is to provide accurate and helpful information to
the best of my ability. If you have any other questions, I
would be happy to try and assist you.
--[2]------------------------------------------------------------------------
Date: 2023-01-29 16:31:54+00:00
From: Henry Schaffer <hes@ncsu.edu>
Subject: Re: [Humanist] 36.362: ChatGPT as author
Thanks to Tim Smithers for an excellent excursion into ChatGPT land.
However, this leads me to think of discussing this with a student - who claims
that the ChatGPT generated essay handed in by the student really was written by
the student, since ChatGPT has disclaimed authorship. Hmmm. :-)
--henry
_______________________________________________
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
