Lecture on January 27, 2025
A Fallibilist Approach to AI Value Alignment
Prof. Dr. Ibo van de Poel (Delft University of Technology, NL)
About the lecture [poster, pdf]
Value alignment is important to ensure that AI systems remain aligned with human intentions, preferences, and values. It has been suggested that it can best be achieved by building AI systems that can track preferences or values in real-time. In my talk, I argue against this idea of real-time value alignment. First, I show that the value alignment problem is not unique to AI, but applies to any technology, thus opening up alternative strategies for attaining value alignment. Next, I argue that due to uncertainty about appropriate alignment goals, real-time value alignment may lead to harmful optimization and therefore will likely do more harm than good. Instead, it is better to base value alignment on a fallibilist epistemology, which assumes that complete certainty about the proper target of value alignment is and will remain impossible. Three alternative principles for AI value alignment are proposed: 1) adopt a fallibilist epistemology regarding the target of value alignment; 2) focus on preventing serious misalignments rather than aiming for perfect alignment; 3) retain AI systems under human control even if it comes at the cost of full value alignment.
About the speaker
Ibo van de Poel is Professor in Ethics and Technology at the Technical University Delft, The Netherlands. He has published on the ethics of newly emerging technologies like Artificial Intelligence, engineering ethics, the moral acceptability of technological risks, design for values, responsible innovation, moral responsibility in research networks, and the idea of new technology as social experiment. He is a member of the Royal Netherlands Academy of Arts and Sciences (KNAW) and one of the PI of the gravitation project ‘Ethics of Socially Disruptive Technologies.’
photo: private
Monday, 27. January 2025, 18:15-19:45 (CET)
Address for joining us on-site:
Flügelbau Ost, 2. OG, Raum O221
Edmund-Siemers-Allee 1
20146 Hamburg
