Deconfusion

Applied to Trying to isolate objectives: approaches toward high-level interpretability by Arun Jose 3mo ago

Applied to Reward is not the optimization target by Euterpe 5mo ago

Applied to Builder/Breaker for Deconfusion by Raymond Arnold 6mo ago

Applied to Why Do AI researchers Rate the Probability of Doom So Low? by Aorou 6mo ago

Applied to Simulators by janus 7mo ago

Applied to My summary of the alignment problem by Peter Hroššo 8mo ago

Applied to Interpretability’s Alignment-Solving Potential: Analysis of 7 Scenarios by Evan R. Murphy 1y ago

Applied to Clarifying inner alignment terminology by Antoine de Scorraille 1y ago

Applied to The Plan by Multicore 1y ago

Applied to Modelling Transformative AI Risks (MTAIR) Project: Introduction by David Manheim 2y ago

Applied to Approaches to gradient hacking by Adam Shimi 2y ago

Applied to A review of "Agents and Devices" by Adam Shimi 2y ago

Applied to Power-seeking for successive choices by Adam Shimi 2y ago

Applied to Goal-Directedness and Behavior, Redux by Adam Shimi 2y ago

Applied to Applications for Deconfusing Goal-Directedness by Adam Shimi 2y ago

Applied to Traps of Formalization in Deconfusion by Adam Shimi 2y ago

Applied to Musings on general systems alignment by Alex Flint 2y ago

Applied to Alex Turner's Research, Comprehensive Information Gathering by Adam Shimi 2y ago

Applied to The Point of Trade by Adam Shimi 2y ago