Abstract

A major challenge in AI is designing autonomous systems that capture the values of stakeholders, and do so in such away that one can assess the extent to which that system’s behaviour is aligned to those values. In this paper we discuss our response to this challenge that is both practical and built on clear principles. Specifically, we propose eleven heuristics to organise the process of making values operational in the design of particular class of AI systems called online institutions. These are governed systems of interacting communities of human and autonomous artificial agents.

Conference

ConferenceInternational Workshop on Coordination, Organizations, Institutions, and Norms for Governance of Multi-Agent Systems, COINE 2022 co-located with 21st International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2022
Period9/05/229/05/22

Bibliographical note

Funding Information:
Acknowledgements. D’Inverno thanks IIIA-CSIC Barcelona for hosting him during a research sabbatical and his host institution Goldsmiths, University of London for making that possible. Noriega’s work is supported in part by the CIMBVAL project (Spanish government project #TIN2017-89758-R).

Funding Information:
D’Inverno thanks IIIA-CSIC Barcelona for hosting him during a research sabbatical and his host institution Goldsmiths, University of London for making that possible. Noriega’s work is supported in part by the CIMBVAL project (Spanish government project #TIN2017-89758-R).

Keywords

  • Conscientious design
  • Embedding values
  • Online institutions
  • Value alignment
  • Value-sensitive design
  • WIT design pattern

ASJC Scopus subject areas

  • Theoretical Computer Science
  • General Computer Science

Fingerprint

Dive into the research topics of 'Design heuristics for ethical online institutions'. Together they form a unique fingerprint.

Cite this