Understanding and avoiding value drift — LessWrong

I use the shard theory of human values to clarify what value drift is, how it happens, and how it might be avoided by a highly intelligent agent—even…

x Understanding and avoiding value drift — LessWrong Shard Theory Value Drift Shard Theory Human Values Rationalization Self-Deception AI Rationality Frontpage 48 Understanding and avoiding value drift by TurnTrout 9th Sep 2022 AI Alignment Forum 7 min read 14 48 Ω 23 I use the shard theory of human values to clarify what value drift is, how it happens, and how it might be avoided by a highly intelligent agent—even if that agent doesn't have any control over its future experiences. Along the way, I give a shard theory account of rationalization. Defining "value drift" Recapitulating part of sh

related reading

• The Shard Theory of Human Valuesturntrout.com
• The shard theory of human values — LessWronglesswrong.com
• The shard theory of human values — AI Alignment Forumalignmentforum.org
• Shard Theory — AI Alignment Forumalignmentforum.org
• Shard Theory in Nine Theses: a Distillation and Critical Appraisal — AI Alignment Forumalignmentforum.org
• Contra shard theory, in the context of the diamond maximizer problem — LessWronglesswrong.com
• The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
• Value systematization: how values become coherent (and misaligned) — AI Alignment Forumalignmentforum.org
• Value systematization: how values become coherent (and misaligned) — LessWronglesswrong.com
• Focus on the places where you feel shocked everyone's dropping the ball — LessWronglesswrong.com
• A Shard Theory of Everything - by Jason Hausenloyfirstscattering.com
• Review: Planecrash — LessWronglesswrong.com