Outer Alignment

Applied to PRISM: Perspective Reasoning for Integrated Synthesis and Mediation (Interactive Demo) by Anthony Diamond 3d ago

Applied to A Universal Prompt as a Safeguard Against AI Threats by Zhaiyk Sultan 4d ago

Applied to Maintaining Alignment during RSI as a Feedback Control Problem by Beren Millidge 12d ago

Applied to The Theoretical Reward Learning Research Agenda: Introduction and Motivation by Joar Skalse 14d ago

Applied to Does human (mis)alignment pose a significant and imminent existential threat? by jr 19d ago

Applied to Unaligned AGI & Brief History of Inequality by ank 20d ago

Applied to Intelligence–Agency Equivalence ≈ Mass–Energy Equivalence: On Static Nature of Intelligence & Physicalization of Ethics by ank 20d ago

Applied to Places of Loving Grace [Story] by ank 23d ago

Applied to Artificial Static Place Intelligence: Guaranteed Alignment by ank 1mo ago

Applied to Static Place AI Makes Agentic AI Redundant: Multiversal AI Alignment & Rational Utopia by ank 1mo ago

Applied to Rational Utopia & Narrow Way There: Multiversal AI Alignment, Non-Agentic Static Place AI, New Ethics... (V. 4) by ank 1mo ago

Applied to How will we update about scheming? by raztronaut 1mo ago

Applied to Alignment Can Reduce Performance on Simple Ethical Questions by Daan Henselmans 1mo ago

Applied to Tetherware #1: The case for humanlike AI with free will by Jáchym Fibír 1mo ago

Applied to The Road to Evil Is Paved with Good Objectives: Framework to Classify and Fix Misalignments. by Shivam Arora 1mo ago

Applied to Disproving the "People-Pleasing" Hypothesis for AI Self-Reports of Experience by rife 2mo ago

Applied to Popular materials about environmental goals/agent foundations? People wanting to discuss such topics? by Q Home 2mo ago

Applied to "Pick Two" AI Trilemma: Generality, Agency, Alignment. by Black Flag 2mo ago

Applied to I Recommend More Training Rationales by Gianluca Calcagni 2mo ago