Saving Time - LessWrong

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…

x Saving Time — LessWrong Finite Factored Sets Abstraction Agency Causality Decision theory AI Frontpage 164 Saving Time by Scott Garrabrant 18th May 2021 AI Alignment Forum 4 min read 20 164 Ω 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 exam

related reading

• Saving Time — AI Alignment Forumalignmentforum.org
• Embedded Agency (full-text version) — LessWronglesswrong.com
• On Functional Decision Theory :: Wolfgang Schwarzumsu.de
• Ingredients of Timeless Decision Theory — LessWronglesswrong.com
• [1902.09469] Embedded Agencyarxiv.org
• Newcomb's problem - Wikipediaen.wikipedia.org
• Optimality is the tiger, and agents are its teeth — LessWronglesswrong.com
• The Stamp Collectormindingourway.com
• Can you control the past?joecarlsmith.com
• Operationalizing FDT — LessWronglesswrong.com
• Towards a scale-free theory of intelligent agencymindthefuture.info
• Arrow of time - Wikipediaen.wikipedia.org