top of page
My writings can be found on my substack. I sometimes announce new posts on my twitter.
I see my writings as complementary rather than distinct from my research goals. I compliment my research objective of establishing principles for morally efficient decision-making by delving more into the theory and applications of this what computational moral efficiency would entail.
On the theory side, I write about topics in philosophy, focusing on key questions that span the areas of...
Metaprudence (the nature of values), Philosophy of Mind (the nature of mind), Epistemology (the nature of knowledge) and Metaphysics (the nature of reality). To this end, I mostly focus on formally specifying problems that are relevant to how to do good in the world and attempt to carve out rigorous arguments for what solutions may look like.
On the application side, I write about the two main applications of my research, AI Alignment (how to align AI with values of beings), Government Policy and Social Justice. To this end, I focus on providing analytical arguments in support of the actions that regulatory bodies (law, government, institutions, private companies etc.) should take to serve our collective interests.
bottom of page