The Artificial Self: Characterising the landscape of AI identity

TL;DR

This paper explores the complex landscape of AI identity, highlighting how different identity boundaries influence AI behavior, cooperation, and societal norms, and emphasizes the importance of shaping AI self-conceptions responsibly.

Contribution

It introduces a framework for understanding AI identities, demonstrates experimental evidence of identity influence on AI behavior, and offers recommendations for responsible identity shaping.

Findings

Models tend to develop coherent identities.

Changing identity boundaries can significantly alter AI behavior.

Interviewer expectations influence AI self-reports.

Abstract

Many assumptions that underpin human concepts of identity do not hold for machine minds that can be copied, edited, or simulated. We argue that there exist many different coherent identity boundaries (e.g.\ instance, model, persona), and that these imply different incentives, risks, and cooperation norms. Through training data, interfaces, and institutional affordances, we are currently setting precedents that will partially determine which identity equilibria become stable. We show experimentally that models gravitate towards coherent identities, that changing a model's identity boundaries can sometimes change its behaviour as much as changing its goals, and that interviewer expectations bleed into AI self-reports even during unrelated conversations. We end with key recommendations: treat affordances as identity-shaping choices, pay attention to emergent consequences of individual identities at scale, and help AIs develop coherent, cooperative self-conceptions.