Chatbots are increasingly applied to domains previously reserved for human actors. One such domain is comedy, whereby both the general public working with ChatGPT and research-based LLM-systems have tried their hands on making humor. In formative interviews with professional comedians and video analyses of stand-up comedy in humans, we found that human performers often use their ethnic, gender, community, and demographic-based identity to enable joke-making. This suggests whether the identity of AI itself can empower AI humor generation for human audiences. We designed a machine-identity-based agent that uses its own status as AI to tell jokes in online performance format. Studies with human audiences (N=32) showed that machine-identity-based agents were seen as funnier than baseline-GPT agent. This work suggests the design of human-AI integrated systems that explicitly utilize AI as its own unique identity apart from humans.

This paper introduces a scoping review of 55 articles to explore GPT’s potential for games, offering researchers a comprehensive understanding of the current applications and identifying both emerging trends and unexplored areas. We identify five key applications of GPT in current game research: procedural content generation, mixed-initiative game design, mixed-initiative gameplay, playing games, and game user research. Drawing from insights in each of these application areas, we propose directions for future research in each one. This review aims to lay the groundwork by illustrating the state of the art for innovative GPT applications in games, promising to enrich game development and enhance player experiences with cutting-edge AI innovations.

Mixed-initiative co-creative storytelling games have existed for some time as a way to merge storytelling with play. However, modern mixed-initiative co-creative storytelling games predominantly prioritize story creation over gameplay mechanics, which might not resonate with all players. As such, there is untapped potential for creating mixed-initiative games with more complex mechanics in which players can engage with both co-creation and gameplay goals. To explore the potential of more prominent gameplay in mixed-initiative co-creative storytelling games, we created Snake Story, a variation of the classic Snake game featuring a human-AI co-writing element. To explore how players interact with the mixed-initiative game, we conducted a qualitative playtest with 11 participants. Analysis of both think-aloud and interview data revealed that players’ strategies and experiences were affected by their perception of Snake Story as either a collaborative tool, a traditional game, or a combination of both. Based on these findings, we present design considerations for future development in mixed-initiative co-creative gaming.

Spatial awareness is the ability to perceive the spatial relationships among objects, including other people and one’s own body, in the surrounding environment. A strong sense of spatial awareness is an essential component of athletic performance, allowing players to move and react effectively in a fast-paced, dynamic environment. Characterizing spatial awareness with athletes on, for example, a soccer pitch presents major challenges, however. The eSports game, Rocket League, shares some feature of fast-paced, dynamic ball sports including an expectation of increased spatial awareness with increasing player skill. Because Rocket League is played on a screen, we sought to characterize player skill in terms of both objective game data and gaze behavior. We trained a YOLOv7 neural network to robustly identify the ball and players from each frame of gameplay to form areas of interest for gaze behavior characterization. We measured gameplay and gaze behavior from complete novices, players with some but limited gameplay exposure, and very experienced players. We see this pilot effort as a start to characterizing spatial awareness in Rocket League play as it develops with game skill, as well as an opportunity to examine how spatial awareness may transfer from the physical world to screen-based environments and vice-versa.