A Redhead Walks into a Bar: Experiences of Writing Fiction with Artificial Intelligence
Open accessAbstract
Human creativity has been often aided and supported by artificial tools, spanning traditional tools such as ideation cards, pens, and paper, to computed and software. Tools for creativity are increasingly using artificial intelligence to not only support the creative process, but also to act upon the creation with a higher level of agency. This paper focuses on writing fiction as a creative activity and explores human-AI co-writing through a research product, which employs a natural language processing model, the Generative Pre-trained Transformer 3 (GPT-3), to assist the co-authoring of narrative fiction. We report on two progressive – not comparative – autoethnographic studies to attain our own creative practices in light of our engagement with the research product: (1) a co-writing activity initiated by basic textual prompts using basic elements of narrative and (2) a co-writing activity initiated by more advanced textual prompts using elements of narrative, including dialects and metaphors undertaken by one of the authors of this paper who has doctoral training in literature. In both studies, we quickly came up against the limitations of the system; then, we repositioned our goals and practices to maximize our chances of success. As a result, we discovered not only limitations but also hidden capabilities, which not only altered our creative practices and outcomes, but which began to change the ways we were relating to the AI as collaborator.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Only a handful of user studies have investigated how professional writers perceive and use AI systems.
“Yet, only a handful of user studies have investigated how professional writers perceive and use AI systems [13,27,28]”
From Playwriting with Large Language Models: Perceived Features, Interaction Strategies and Outcomes (2024) · cites this paper as [28]
The Methodology and §4.2 describe two autoethnographic studies of how the authors used and experienced an AI fiction-writing system, including work by a literary scholar trained in creative writing. The paper describes the authors as creative professionals in design and literary studies, but does not establish that they are professional writers or that only a handful of such studies exist. (LLM, conf=0.82)
Experimental — accuracy not yet measuredEmpirical studies describing how users evaluate LLMs are still a minority and difficult to generalise due to variation of participants, methods, systems, and disciplinary perspectives.
“Empirical studies describing how users evaluate LLMs are still a minority and difficult to generalise due to a variation of participants, methods, systems, and disciplinary perspectives [13,27,28,38,47].”
From Playwriting with Large Language Models: Perceived Features, Interaction Strategies and Outcomes (2024) · cites this paper as [28]
The Introduction and Methodology describe two autoethnographic studies of the authors’ experiences co-writing fiction with GPT-3, so this paper provides an example of empirical work on users’ experiences with an LLM. It does not establish that such studies are a minority or that variation in participants, methods, systems, and disciplines makes their findings difficult to generalise; the Methodology says its goal was not a UX evaluation of the system. (LLM, conf=0.82)
Experimental — accuracy not yet measuredMany technical limitations hamper the application of LLMs to creative writing, including short memory, lack of semantic coherence, and common-sense and contextual awareness.
“However, many technical limitations hamper the application of LLMs to creative writing.They include short memory [36,40], lack of semantic coherence [28,40], and common-sense and contextual awareness [36,38].”
From Playwriting with Large Language Models: Perceived Features, Interaction Strategies and Outcomes (2024) · cites this paper as [28]
The Introduction says the language models studied lack semantic cohesiveness, and §5.1 describes GPT-3 drifting away from a story’s opening after its first sentences. Those passages support the creative-writing coherence limitation, but they do not establish the separately cited claim that the models have short memory. The common-sense and contextual-awareness limitation is cited to other sources, not this paper. (LLM, conf=0.84)
Experimental — accuracy not yet measuredIn contrast with [28], participants did not associate creative ability with the machine.
“In contrast with [28], participants did not associate creative ability with the machine.”
From Playwriting with Large Language Models: Perceived Features, Interaction Strategies and Outcomes (2024) · cites this paper as [28]
The machine could not understand story cohesion and lacked semantic comprehension.
“The machine could not understand story cohesion [36] and lacked semantic comprehension [28,40].”
From Playwriting with Large Language Models: Perceived Features, Interaction Strategies and Outcomes (2024) · cites this paper as [28]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
The citation lists haven’t been fetched yet
References 57 · Cited by 54
Research works printed but not linked: 10
- [8]8. Jeffrey Bardzell. 2007. Creativity in Amateur Multimedia : Popular Culture, Critical Theory, and HCI. Human Technology: An Interdisciplinary Journal on Humans in ICT Environments (2007). https://jyx.jyu.fi/handle/123456789/20201 Accepted: 2009-06-02T11:52:40Z Publisher: University of Jyväskylä, Agora Center.
- [15]15. BigScience Workshop. 2022. BLOOM (Revision 4ab0472). https://doi.org/10. 57967/hf/0003
- [21]21. Pedro Campos, Frederica Gonçalves, Michael Martins, Miguel Campos, and Paulo Freitas. 2014. Second look: combining wearable computing and crowdsourcing to support creative writing. In Proceedings of the 8th Nordic Conference on Human- Computer Interaction: Fun, Fast, Foundational (NordiCHI '14). Association for Computing Machinery, New York, NY, USA, 959-962. https://doi.org/10.1145/ 2639189.2670250
- [22]22. Alison Cawsey. 2003. Explanation and Interaction (ACL-MIT Series in Natural Language Processing): The Computer Generation of Explanatory Dialogues. A Bradford Book, Place of publication not identified.
- [37]37. Ursula K. Le Guin. 2015. Steering The Craft: A Twenty-First-Century Guide to Sailing the Sea of Story (reprint edition ed.). Harper Perennial, Boston ; New York.
- [45]45. Peter Lamarque and Stein Haugom Olsen. 1996. Truth, Fiction, and Literature: A Philosophical Perspective. Oxford University Press, Oxford. https://doi.org/10. 1093/acprof:oso/9780198236818.001.0001
- [46]46. Anne Lamott. 1995. Bird by Bird: Some Instructions on Writing and Life (1st paperback edition ed.). Anchor, New York.
- [53]53. Ramon Lopez de Mantaras and Josep Lluis Arcos. 2002. AI and Music: From Composition to Expressive Performance. AI Magazine 23, 3 (Sept. 2002), 43-43. https://doi.org/10.1609/aimag.v23i3.1656 Number: 3. · DOI
- [57]57. David G. Novick and Stephen Sutton. 1997. What is mixed-initiative interaction. In In Procedings of the AAAI Spring Symposium on Computational Models for Mixed Initiative Interaction. 114-116.
- [67]67. Jerome Stern. 1991. Making Shapely Fiction (1/29/01 edition ed.). W. W. Norton & Company.
- Authors
- Ghajargar, M., Bardzell, J., & Lagerkvist, L.
- Affiliations
- Malmö University (SE)
- Pennsylvania State University (US)
- Venue
- Proceedings of the 25th International Academic Mindtrek Conference
- Publisher
- ACM
- Published
- 2022-11-16
- Pages
- 230-241
- OpenAlex
- W4308623154
- Cited by
- 54
- References
- 57
- Citations by year
- 2026: 7 · 2025: 17 · 2024: 21 · 2023: 9
- FWCI
- 87.36
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- International Academic Mindtrek Conference (Mindtrek) (publishedVersion, other-oa)
- KTH Publication Database DiVA (KTH Royal Institute of Technology) (submittedVersion, other-oa)
- Topics
- Social Sciences › Political Science and International Relations › Literary and Philosophical Studies
- Social Sciences › Arts and Humanities › Visual Arts and Performing Arts › Artistic and Creative Research
- Physical Sciences › Computer Science › Artificial Intelligence › Artificial Intelligence in Games
- Keywords
- fiction writing, GPT-3, creative practice, AI as collaborator, autoethnography, narrative fiction, natural language processing, metaphor, creative tools, human-AI collaboration
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
