Saving Time — AI Alignment Forum

For the last few years, a large part of my research motivation has been directed at trying to save the concept of time—save it, for example, from all…

x Saving Time — AI Alignment Forum Finite Factored Sets Abstraction Agency Causality Decision theory AI Frontpage 66 Saving Time by Scott Garrabrant 18th May 2021 4 min read 20 66 For the last few years, a large part of my research motivation has been directed at trying to save the concept of time—save it, for example, from all the weird causal loops created by decision theory problems. This post will hopefully explain why I care so much about time, and what I think needs to be fixed. Why Time? My best attempt at a short description of time is that time is causality . For example, in a Pearlia

related reading

• Saving Time — LessWronglesswrong.com
• Alignment remains a hard, unsolved problem — LessWronglesswrong.com
• I Would Have Solved Alignment, But I Was Worried That Would Advance Timelines — LessWronglesswrong.com
• Why Agent Foundations? An Overly Abstract Explanation — LessWronglesswrong.com
• Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
• Embedded Agency (full-text version) — LessWronglesswrong.com
• Faithful, Interpretable Model Explanations via Causal Abstraction | SAIL Blogai.stanford.edu
• Operationalizing FDT — LessWronglesswrong.com
• The Planlesswrong.com
• Ingredients of Timeless Decision Theory — LessWronglesswrong.com
• How to think about slowing AI — EA Forumforum.effectivealtruism.org
• A (Slightly) Mechanistic Theory for Exponentially Increasing AI Time Horizons? — LessWronglesswrong.com