The study investigates the role of large language models (LLMs) like ChatGPT in game design, focusing on their ability to provide creative inspiration and alternative quality to games compared to human designers. Three prototype games were created across different genres, with participants evaluating the quality and preference of each game. The results highlight the benefits and limitations of AI in a design-centric role, showcasing the potential for collaboration between human designers and AI assistants.
The research delves into collaborative game design systems, exploring how AI agents can interact with game designers to generate or modify aspects of a game. It discusses the extent of interactivity AI agents can have and how they are used by designers, emphasizing the critical exploration of generative systems like LLMs in game content generation.
Furthermore, the study examines designer intent in creative projects such as video games, focusing on how AI assistants can maintain original designer intent while automating certain aspects of game design. It evaluates the communication between AI assistants and human users to understand its impact on game quality and player experience.
Overall, the study sheds light on the potential of AI-assisted game design, highlighting both its strengths and limitations in enhancing creativity and innovation in game development.
In un'altra lingua
dal contenuto originale
arxiv.org
Approfondimenti chiave tratti da
by Asad Anjum,Y... alle arxiv.org 03-06-2024
https://arxiv.org/pdf/2403.02454.pdfDomande più approfondite