Remember Me, Not Save Me: A Collective Memory System for Evolving Virtual Identities in Augmented Reality
Tongzhou Yu, Han Lin
TL;DR
The paper addresses how to form evolving digital identities from collective public dialogue in augmented reality and AI. It introduces Dynamic Collective Memory (DCM), a Narrative Tension mechanism, a State-Reflective Avatar for ambient explainability, and Geo-Cultural Context Anchoring. Deployed at the 2024 Jinan Biennale, it reports stable ISTP personality emergence from over 2,500 interactions and demonstrates how grounding memories in real places enhances authenticity. The work offers a reproducible framework for designing digital entities that balance remembering with forgetting, advancing collective intelligence in public spaces.
Abstract
This paper presents "Remember Me, Not Save Me," an AR & AI system enabling virtual citizens to develop personality through collective dialogue. Core innovations include: Dynamic Collective Memory (DCM) model with narrative tension mechanisms for handling contradictory memories; State-Reflective Avatar for ambient explainability; and Geo-Cultural Context Anchoring for local identity. Deployed at the 2024 Jinan Biennale, the system demonstrated stable personality emergence (ISTP type via Apply Magic Sauce analysis) from over 2,500 public interactions. We provide a framework for designing evolving digital entities that transform collective memory into coherent identity.
