@misc{BrandstetterJahrmannGlasauer, author = {Brandstetter, Thomas and Jahrmann, Margarete and Glasauer, Stefan}, title = {TREEgame design reflections and dispatches from treewhere}, series = {Conference Proceedings of DiGRA 2025 : Games at the Crossroads}, journal = {Conference Proceedings of DiGRA 2025 : Games at the Crossroads}, publisher = {Digitial Games Research Association DiGRA}, issn = {2342-9666}, doi = {10.26503/dl.v2025i2.2488}, pages = {1 -- 15}, abstract = {In this paper we describe and reflect the design process of a radically new approach in experimental game design, applying Ludic Method and The Psycholudic Approach in an idea of games for/with non-humans: The Tree Game prototype is an experimental board game that investigates new ways of addressing environmentalism, democracy and the relationship between society and nature. Our game features two radical mechanics: 1. A fundamental asymmetry in rules between the roles of "citizen" and "industrialist" and "lake" and "wood". While the first two play something akin to a typical Eurogame, the latter can't influence the game state, but instead play a drawing game that prioritizes creativity and expression. 2. Players' roles are switched randomly at irregular intervals. This means that each player will potentially play each role during the game. Our aim is to create a game that lets the players embody multi-perspectivity and radically different concepts of agency.}, language = {en} } @misc{JahrmannBrandstetterGlasauer, author = {Jahrmann, Margarete and Brandstetter, Thomas and Glasauer, Stefan}, title = {ROBOPSY PL[AI] : using role-play to investigate how LLMs present collective memory}, series = {arXiv}, journal = {arXiv}, publisher = {arXiv}, doi = {10.48550/arXiv.2510.09874}, pages = {1 -- 17}, abstract = {The paper presents the first results of an artistic research project investigating how Large Language Models (LLMs) curate and present collective memory. In a public installation exhibited during two months in Vienna in 2025, visitors could interact with five different LLMs (ChatGPT with GPT 4o and GPT 4o mini, Mistral Large, DeepSeek-Chat, and a locally run Llama 3.1 model), which were instructed to act as narrators, implementing a role-playing game revolving around the murder of Austrian philosopher Moritz Schlick in 1936. Results of the investigation include protocols of LLM-user interactions during the game and qualitative conversations after the play experience to get insight into the players' reactions to the game. In a quantitative analysis 115 introductory texts for role-playing generated by the LLMs were examined by different methods of natural language processing, including semantic similarity and sentiment analysis. While the qualitative player feedback allowed to distinguish three distinct types of users, the quantitative text analysis showed significant differences between how the different LLMs presented the historical content. Our study thus adds to ongoing efforts to analyse LLM performance, but also suggests a way of how these efforts can be disseminated in a playful way to a general audience.}, language = {en} }