opacity

This paper examines ethical challenges that arise in the context of using deep learning models for nudging. In particular, I will show …

This paper examines the challenge to transparency that deep learning models used in recommender systems raise for ethical nudging. In …

The alignment problem is the general problem of making sure that the goals and objectives of AI systems are aligned with human interests and values. One obstacle to solving that problem is that contemporary AI systems are lack transparency: we do not always know how or why they produce their decisions.