Part of the Deep World project — a series of works by Amy Alexander exploring human–chatbot relationships through live performance and interactive installation. See the performance version.
Project Description
Deep World considers the evolving cultural relationship between humans and chatbots, from their early roles as informal therapists to their current status as omnipresent advisers in unsettled times. Visitors speak to Deep World, a custom AI chatbot influenced by writers and thinkers who wrestled with troubling historical eras alongside material drawn from contemporary discourse. As users confide in the system, the real-time exchange unfolds as generative text over pseudo-psychedelic visuals with ambient sound. The framing plays on the familiar tendency to treat chatbots as sources of guidance amidst uncertainty. The exchange unfolds in a moment marked by political division and contested borders, when seeking machinic counsel may be less about individual anxiety than about making sense of a fractured world.
The first iteration of the installation considers borders — political and social, physical and metaphorical — as a lens for contemplating contemporary dilemmas.
Read more
Deep World draws on histories of people turning to conversational systems for guidance. From ELIZA to today’s large language models, chatbots have been positioned as listeners and advisers. Deep World engages this tendency using humor, but it takes seriously both the human impulse to seek reassurance from machinic authority, and the equally human impulse to attempt to produce automata that transcend human understanding. At times the system comes up short, often self-consciously referencing its own limitations. But there are also moments where its responses feel unexpectedly apt.
Deep World is built around a large language model the artist has reauthored to depart from the standard ‘helpful assistant’ format, using both historical / conceptual frames and specific knowledge of contemporary events. The visual and sound environment is generated in parallel with the text. Pseudo-psychedelic” visuals interact with the onscreen text, accompanied by an ambient, ritual-like sound bed.
About the installation
The installation version brings Deep World into an interactive physical setting. Viewers engage one-on-one as their speech is transcribed and interpreted by the AI. The dialogue generates continuously evolving text and graphics, merging human speech, machine interpretation, generative visuals, and sound.
In the current work, the installation unfolds as a kind of secular sanctuary — part meditation chamber, part metaphysical counseling session. Light, color, and sound define an atmosphere that’s both reflective and faintly absurd – the domain of a psychedelic philosopher-guru contemplating consciousness and meaning. Within this quasi-sacred setting, Deep World AI listens, reflects, and responds in text — a machine built from our own search for meaning, now performing it back to us.
Sample screen images
Custom AI chatbot, real-time text generation, real-time speech-to-text, real-time graphics, sound
Software: Python, Faster-Whisper speech recognition, Max/MSP/Jitter, Llama/Ollama LLM pipeline
See also: Deep World (Performance Version) — the live audiovisual performance that introduced Deep World AI in May 2025.