Writings
An essay on two layers of the proposed design: an agent with no persistent self to protect (Anatta), and a goal that yields to human shutdown (Anicca).
Moral AI and AlignmentThe one-page introduction to the Moral AI proposals: why caging a model after training is not enough, and why alignment has to begin with what goes in.
Moral AI and AlignmentA supplementary manifesto to the Moral AI framework, with a personal foreword from the author. Preprint.
Moral AI and AlignmentA proposed architecture for non-harm, causal reflection and shutdown compliance in AI agents, drawing on Theravada Buddhist principles. Preprint, under review.
Moral AI and Alignment