It’s all about prompt design. Find the right prompt and get lazy. Working with GPT opens up new possibilities to be more efficient when interacting with an AI. But watch out – not every input leads you to your deserved output. While working on “ANA – a theatrical storytelling machine” (which you can try out at the Dramaturgische Gesellschaft conference too) we got fundamental insights into prompt adjustments for taking the best out of GPT3. ChatGPT opened up even more innovative approaches for human-ai interactions, for AI-based coding and workflow adjustments. In this table talk we will deepen our understanding of prompt design and reflect on the possibilities of GPT for dramaturgical reasons.
Table talk in English language
Ilja Mirsky is a dramaturg, media artist (AI and VR/AR) and lecturer. He studied cognitive science and performance studies. He is lecturer on immersive media and digital dramaturgy at the ADK Ludwigsburg and the University of Tübingen. From 2019 till 2022, he has been a dramaturg and recurrent programmer at the Institut für theatrale Zukunftsforschung (ITZ) at the Zimmertheater in Tübingen. Since September 2022 he is working as a dramaturg and digital dramaturg at the Residenztheater Munich.
Dr. Leonid Berov’s scientific and artistic interest is the intersection of autonomous machines, fictional stories and creativity. He holds a PhD in Cognitive Science for his award wining research on how to bridge the gap between Narratology and Computational Story Composition. For the AI installation ANA he transmogrified his findings into an autonomous model of affectivity and emotion-driven storytelling. During the day, Leonid works as a Machine Learning engineer in climate tech, where he helps decarbonize the production of cement and concrete.
Meredith Thomas is an artist and creative technologist based in Berlin. He studied biomedical engineering and science communication at Imperial College London. After moving to Berlin he became interested in creative uses of technology. He has worked as a programmer and an artist to create transmedia experiences in virtual reality, for multimedia installations and for the stage. His work focuses in particular on novel uses of machine learning in creative domains and critiquing the broader technological and cultural manifestations of artificial intelligence.
Chris Ziegler is a Digital Artist on Stage, director and scenographer. He has been developing digital immersive stages and applications for interactive dance productions on stage since the mid-90s at the Center for Art and Media ZKM Karlsruhe. At the music research institute IRCAM Paris in 2006, he was using AI and machine learning in dance and movement research. He initiated and directed the AI theater installation ANA, which is his first text based theater work, supported by Volkswagen Stiftung and developed by Ilja Mirsky, Leonid Berov, Meredith Thomas, Nikolaus Völzow und Gunther Lösel.
