✳flâneur — a map of the web's best reading
The Shard Theory of Human Values
turntrout.com · 8,068 words · saved by 10 readers
Human values are shaped by simple reward circuitry. Shard theory explains how these shards give rise to complex behaviors, such as altruism.
Table of Contents 1 . Neuroscientific assumptions 2 : Reinforcement events shape human value shards 3 . Explaining human behavior using shard theory Altruism is contextual Friendship strength seems contextual Milgram is also contextual Sunflowers and timidity We think that many biases are convergently produced artifacts of the human learning process & environment Why people can’t enumerate all their values Content we aren’t (yet) discussing Conclusion Citation Appendix A: The formation of the world model Appendix B: Terminology Shards are not full subagents “Values” “Shard Theory” Appendix C:
Explore this link on the map →saved by
- Raayan Dhar
- Aaron Pham
- Lydia Nottingham
- Gloria Ma
- Sudarsh K
- Brooke Joseph
- Yudhister Joel Kumar
- Chloe Nguyen
- Julian H
- Will Anderson
related reading
- The shard theory of human values — LessWronglesswrong.com
- The shard theory of human values — AI Alignment Forumalignmentforum.org
- A Crash Course in the Neuroscience of Human Motivation — LessWronglesswrong.com
- Shard Theory — AI Alignment Forumalignmentforum.org
- Shard Theory in Nine Theses: a Distillation and Critical Appraisal — AI Alignment Forumalignmentforum.org
- A Shard Theory of Everything - by Jason Hausenloyfirstscattering.com
- Understanding and avoiding value drift — LessWronglesswrong.com
- The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
- Reward is not the optimization target — LessWronglesswrong.com
- Contra shard theory, in the context of the diamond maximizer problem — LessWronglesswrong.com
- The Computational Anatomy of Human Values — LessWronglesswrong.com
- Have You Tried Thinking About It As Crystals? — LessWronglesswrong.com