TY - GEN
T1 - The Ink Splotch Effect
T2 - 19th International Conference on the Foundations of Digital Games, FDG 2024
AU - Anjum, Asad
AU - Li, Yuting
AU - Law, Noelle
AU - Charity, M.
AU - Togelius, Julian
N1 - Publisher Copyright:
© 2024 ACM.
PY - 2024/5/21
Y1 - 2024/5/21
N2 - This paper studies how large language models (LLMs) can act as effective, high-level creative collaborators and "muses"for game design. We model the design of this study after the exercises artists use by looking at amorphous ink splotches for creative inspiration. Our goal is to determine whether AI-assistance can improve, hinder, or provide an alternative quality to games when compared to the creative intents implemented by human designers. The capabilities of LLMs as game designers are stress tested by placing it at the forefront of the decision making process. Three prototype games are designed across 3 different genres: (1) a minimalist base game, (2) a game with features and game feel elements added by a human game designer, and (3) a game with features and feel elements directly implemented from prompted outputs of the LLM, ChatGPT. A user study was conducted and participants were asked to blindly evaluate the quality and their preference of these games. We discuss both the development process of communicating creative intent to an AI chatbot and the synthesized open feedback of the participants. We use this data to determine both the benefits and shortcomings of AI in a more design-centric role.
AB - This paper studies how large language models (LLMs) can act as effective, high-level creative collaborators and "muses"for game design. We model the design of this study after the exercises artists use by looking at amorphous ink splotches for creative inspiration. Our goal is to determine whether AI-assistance can improve, hinder, or provide an alternative quality to games when compared to the creative intents implemented by human designers. The capabilities of LLMs as game designers are stress tested by placing it at the forefront of the decision making process. Three prototype games are designed across 3 different genres: (1) a minimalist base game, (2) a game with features and game feel elements added by a human game designer, and (3) a game with features and feel elements directly implemented from prompted outputs of the LLM, ChatGPT. A user study was conducted and participants were asked to blindly evaluate the quality and their preference of these games. We discuss both the development process of communicating creative intent to an AI chatbot and the synthesized open feedback of the participants. We use this data to determine both the benefits and shortcomings of AI in a more design-centric role.
KW - AI-assisted game design
KW - LLMs
KW - Unity
KW - co-creative game design
KW - mixed-initiative creativity
KW - procedural content generation
KW - user study
UR - http://www.scopus.com/inward/record.url?scp=85199056650&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85199056650&partnerID=8YFLogxK
U2 - 10.1145/3649921.3650010
DO - 10.1145/3649921.3650010
M3 - Conference contribution
AN - SCOPUS:85199056650
T3 - ACM International Conference Proceeding Series
BT - Proceedings of the 19th International Conference on the Foundations of Digital Games, FDG 2024
A2 - Smith, Gillian
A2 - Whitehead, Jim
A2 - Samuel, Ben
A2 - Spiel, Katta
A2 - van Rozen, Riemer
PB - Association for Computing Machinery
Y2 - 21 May 2024 through 24 May 2024
ER -