My chapter "Artificial Intelligence Safety as an Emerging Paradigm" has just been published in the new edited volume: 

Ethics in Artificial Intelligence: A Multidisciplinary Approach, edited by Steven S. Gouveia.

In the chapter, I frame and examine AI safety in terms of Kuhn's paradigms: I argue that the nature of the alignment problem is such that it calls for its own paradigm as the research necessary to solve it goes beyond the typical desiderata in machine learning work. I offer an account of what this would entail, namely, metascientific projects and breakthroughs in normative and applied ethics.

This volume brings together 13 pieces on AI ethics from diverse angles: philosophy, robotics, neurotechnologies, translation, governance, and more. 

You can check out the book here: https://ethicspress.com/products/ethics-in-artificial-intelligence