OpenAI, The Superalignment Problem, and Human Values.

A simple analogy for superalignment: In traditional machine learning (ML), humans supervise AI systems weaker than themselves (left). To align superintelligence, humans will instead need to supervise AI systems smarter than them (center). We cannot directly study this problem today, but we can study a simple analogy: can small models supervise larger models (right)? (Open … [continue reading]

Beyond The Spirituality-Industrial Complex.

(Motski, 2023) TABLE OF CONTENTS 1. Introduction 2. Religion and Morality 3. The New Apocalypse, The Spirituality-Industrial Complex, The Highest Good, and Morality 4. There’s Always a Constructive, Enabling Alternative To Every Social-Institutional Structure That’s Destructive and Deforming, Even If That Social Institution Seems To Be Eternal or Written-in-Stone 5. Realistically Optimist Dignitarian Humanism as … [continue reading]