Outer Alignment

Applied to Truthful LMs as a warm-up for aligned AGI by Jacob_Hilton at 8d

Applied to My Overview of the AI Alignment Landscape: Threat Models by Neel Nanda at 1mo

Applied to My Overview of the AI Alignment Landscape: A Bird's Eye View by Neel Nanda at 1mo

Applied to Exterminating humans might be on the to-do list of a Friendly AI by RomanS at 1mo

Applied to Information bottleneck for counterfactual corrigibility by tailcalled at 2mo

Applied to Behavior Cloning is Miscalibrated by leogao at 2mo

Applied to AXRP Episode 12 - AI Existential Risk with Paul Christiano by DanielFilan at 2mo

Applied to A positive case for how we might succeed at prosaic AI alignment by Quintin Pope at 2mo

Applied to The AGI needs to be honest by rokosbasilisk at 3mo

Applied to [Proposal] Method of locating useful subnets in large models by Quintin Pope at 3mo

Applied to Collection of arguments to expect (outer and inner) alignment failure? by Ruby at 4mo

Applied to Selection Theorems: A Program For Understanding Agents by Ruby at 4mo

Applied to The Metaethics and Normative Ethics of AGI Value Alignment: Many Questions, Some Implications by Dario Citrini at 4mo

Applied to Alignment via manually implementing the utility function by Chantiel at 4mo

Applied to Distinguishing AI takeover scenarios by Sammy Martin at 4mo

Applied to Call for research on evaluating alignment (funding + advice available) by Beth Barnes at 5mo

Applied to Is it worth making a database for moral predictions? by Jonas Hallgren at 5mo

Applied to Thoughts on a "Sequences Inspired" PhD Topic by goose000 at 7mo

Applied to MIRIx Part I: Insufficient Values by Jozdien at 7mo