paper-with-me

홈 › Papers

The Artificial Self: Characterising the landscape of AI identity

2026-03-11 · Raymond Douglas, Jan Kulveit, Ondrej Havlicek, Theia Pearson-Vogel, Owen Cotton-Barratt, David Duvenaud arxiv

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.

📄 PDF Abstract BibTeX arXiv:2603.11353

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Characterising Alzheimer's Disease with EEG-based Energy Landscape Analysis

2021-02-19 · Dominik Klepl, Fei He, Min Wu, Matteo De Marco 외

Alzheimer's disease (AD) is one of the most common neurodegenerative diseases, with around 50 million patients worldwide. Accessible and non-invasive methods of diagnosing and characterising AD are therefore urgently req…

EEGElectroencephalogram (EEG)

A Computational Analysis of Natural Languages to Build a Sentence Structure Aware Artificial Neural Network

2019-06-13 · Alberto Calderone

Natural languages are complexly structured entities. They exhibit characterising regularities that can be exploited to link them one another. In this work, I compare two morphological aspects of languages: Written Patter…

Sentence

Facing Identity: The Formation and Performance of Identity via Face-Based Artificial Intelligence Technologies

2024-10-16 · Wells Lucas Santo

How is identity constructed and performed in the digital via face-based artificial intelligence technologies? While questions of identity on the textual Internet have been thoroughly explored, the Internet has progressed…

Image Generation

Emergence of Self-Identity in AI: A Mathematical Framework and Empirical Study with Generative Large Language Models

2024-11-27 · Minhyeok Lee

This paper introduces a mathematical framework for defining and quantifying self-identity in artificial intelligence (AI) systems, addressing a critical gap in the theoretical foundations of artificial consciousness. Whi…

Characterising the Area Under the Curve Loss Function Landscape

2021-09-29 · Maximilian Paul Niroomand, Conor T Cafolla, John William Roger Morgan, David John Wales

One of the most common metrics to evaluate neural network classifiers is the area under the receiver operating characteristic curve (AUC). However, optimisation of the AUC as the loss function during network training i…