NARRATRON is an interactive projector that augments shadow puppetry with AI generated storytelling. Designed by Aria Bao and Yubo Zhao.
Support from the 2021-2022 Alumni Class Funds, the MIT Department of Architecture, and MIT Morningside Academy for Design.
Large Language Models (LLM) have shown an unprecedented ability to generate human-like text and images, answer questions, and perform complex programming tasks, promising to have a profound impact on design. However, these models remain largely ignorant of the world outside of language, lacking context and knowledge of physical objects, our bodies and environments.
Large Language Objects (LLO) are a series of objects and physical interfaces for language models that extend their capabilities beyond the confines of chatbots and graphical user interfaces. By combining models such as ChatGPT, DALL·E, and custom trained classifiers, they reveal a host of new applications for artificial intelligence, from new ways of experiencing music or creating and telling stories, to new forms of playing and communicating.
Developed as part of MIT’s 4.043/4.044 Interaction Intelligence course, these Large Language Objects also provide a glimpse at a new kind of creative process that leverages the capabilities of generative AI from the early stages of concept development to coding, fabrication, and deployment.
VBox is a radio box that uses ChatGPT to take you on a journey into music and culture through the lens of language. Designed by Danning Liang and Artem Laptiev.
AIncense is a praying device powered by ChatGPT and designed to amplify self-motivation through ritual and psychological suggestion. Designed by Youtian Duan and Kai Zhang.