Dear friends,
I am pleased to announce two new research papers, both on ethics topics related to artificial intelligence. One addresses a challenge for AI ethics concepts such as value alignment and human compatibility. The other presents a foundational study of the ethics of diversity, with implications for the ethics of advanced AI. These topics are important in their own right and are also important for global catastrophic risk given the high stakes and potential for conflict over AI.
Sincerely,
Seth Baum
Executive Director
Manipulating Societal Values
AI ethics concepts like value alignment propose something similar to democracy, aggregating individual values into a social choice. This paper, published in the journal AI and Ethics, explores the potential for AI systems to be manipulated in ways analogous to sham elections in authoritarian regimes.
View the paper: Manipulating aggregate societal values to bias AI social choice ethics
The Ethics Of Diversity
Diversity is a major ethics concept, but it is remarkably understudied. This paper, published in the journal Inquiry, presents a foundational study of the ethics of diversity. It adapts ideas about biodiversity and sociodiversity to the overall category of diversity. It also presents three new thought experiments, with implications for AI ethics.
View the paper: On the intrinsic value of diversity