The Computational Anatomy of Human Values - LessWrong

Tldr: Human values are primarily linguistic concepts encoded via webs of association and valence in the cortex learnt through unsupervised (primarily linguistic) learning. These value concepts are bo…

x The Computational Anatomy of Human Values — LessWrong Human Values Outer Alignment Value Learning AI Rationality World Modeling Frontpage 76 The Computational Anatomy of Human Values by beren 6th Apr 2023 AI Alignment Forum 36 min read 30 76 Ω 29 This is crossposted from my personal blog . Epistemic Status : Much of this draws from my studies in neuroscience and ML. Many of the ideas in this post are heavily inspired by the work of Steven Byrnes and the authors of Shard Theory . However, it speculates quite a long way in advance of the scientific frontier and is almost certainly incorrect in

related reading

• The shard theory of human values — LessWronglesswrong.com
• The Shard Theory of Human Valuesturntrout.com
• Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
• Value Learning Needs a Low-Dimensional Bottleneck — LessWronglesswrong.com
• The shard theory of human values — AI Alignment Forumalignmentforum.org
• The behavioral selection model for predicting AI motivations — LessWronglesswrong.com
• A Crash Course in the Neuroscience of Human Motivation — LessWronglesswrong.com
• Value systematization: how values become coherent (and misaligned) — LessWronglesswrong.com
• Language Models in Plato's Cave - by Sergey Levinesergeylevine.substack.com
• Alignment By Default — AI Alignment Forumalignmentforum.org
• Alignment & Succession: Morality Lives in the Human Individualnosetgauge.com
• My computational framework for the brain — LessWronglesswrong.com