Outer Alignment

Applied to Formalizing «Boundaries» with Markov blankets + Criticism of this approach by Chipmonk 12d ago

Applied to A Case for AI Safety via Law by JWJohnston 12d ago

Applied to Recreating the caring drive by Catnee 25d ago

Applied to You can't fetch the coffee if you're dead: an AI dilemma by hennyge 1mo ago

Applied to Democratic Fine-Tuning by Joe Edelman 1mo ago

Applied to Enhancing Corrigibility in AI Systems through Robust Feedback Loops by Justausername 1mo ago

Applied to Embedding Ethical Priors into AI Systems: A Bayesian Approach by Justausername 2mo ago

Applied to Is there any existing term summarizing non-scalable oversight methods in outer alignment? by Allen Shen 2mo ago

Applied to Preference Aggregation as Bayesian Inference by Beren Millidge 2mo ago

Applied to Autonomous Alignment Oversight Framework (AAOF) by Justausername 2mo ago

Applied to Supplementary Alignment Insights Through a Highly Controlled Shutdown Incentive by Justausername 2mo ago

Applied to Simple alignment plan that maybe works by Iknownothing 2mo ago

Applied to Task decomposition for scalable oversight (AGISF Distillation) by Charbel-Raphael Segerie 3mo ago

Applied to [Linkpost] Introducing Superalignment by Beren Millidge 3mo ago

Applied to Slaying the Hydra: toward a new game board for AI by Prometheus 3mo ago

Applied to A Multidisciplinary Approach to Alignment (MATA) and Archetypal Transfer Learning (ATL) by Miguel de Guzman 3mo ago

Applied to Partial Simulation Extrapolation: A Proposal for Building Safer Simulators by marc/er 3mo ago

Applied to Why "AI alignment" would better be renamed into "Artificial Intention research" by chaosmage 4mo ago