Value Sensitive Design and the Future of Value Alignment in AI

After six decades of research and development, aligning AI systems with our goals, intents, and values remains an elusive objective. How do we make sure that AI models capture our norms and values, understand what we mean or intend, and, above all, do what we want?

This online round-table discussion aims to discuss whether and how VSD can advance AI ethics in theory and practice. A moderated round-table discussion will be held on three guiding propositions (about 20min each):

• Value basis: “Value Sensitive Design implies a clear concept of value that can serve as the target of value alignment“
• Professional practice: “The major practical challenge for including value alignment in existing design and engineering practices will be solved by implementing a VSD approach“
• Evaluation: “There is no reliable measure of whether a given AI technology has been successfully aligned with a target value“

We expect a large audience of AI ethics practitioners and researchers. We will discuss the promises, challenges, and potential of VSD as a methodology for AI ethics and value alignment specifically.

Please check delftdesignforvalues.nl for more information on this event.