Geometric UDT — LessWrong
This post owes credit to discussions with Caspar Oesterheld, Scott Garrabrant, Sahil, Daniel Kokotajlo, Martín Soto, Chi Nguyen, Lukas Finnveden, Viv…
x Geometric UDT — LessWrong Decision theory Open-Minded Updatelessness Updateless Decision Theory Value Learning Rationality Frontpage 29 Geometric UDT by abramdemski 6th Nov 2025 AI Alignment Forum 8 min read 10 29 Ω 17 This post owes credit to discussions with Caspar Oesterheld, Scott Garrabrant, Sahil, Daniel Kokotajlo, Martín Soto, Chi Nguyen, Lukas Finnveden, Vivek Hebbar, Mikhail Samin, and Diffractor. Inspired in particular by a discussion with cousin_it . Short version: The idea here is to combine the Nash bargaining solution with Wei Dai's UDT to give an explicit model of some ideas f
Explore this link on the map →related reading
- UDT shows that decision theory is more puzzling than ever — LessWronglesswrong.com
- On The Independence Axiom — LessWronglesswrong.com
- Updatelessness doesn't solve most problems — LessWronglesswrong.com
- Updateless Decision Theory — LessWronglesswrong.com
- On Functional Decision Theory :: Wolfgang Schwarzumsu.de
- UDT shows that decision theory is more puzzling than ever — AI Alignment Forumalignmentforum.org
- The shard theory of human values — LessWronglesswrong.com
- EDT with updating double counts – The sideways viewsideways-view.com
- Operationalizing FDT — LessWronglesswrong.com
- Open-minded updatelessness — LessWronglesswrong.com
- Why The Focus on Expected Utility Maximisers? — LessWronglesswrong.com
- Pascal's mugging - Wikipediaen.wikipedia.org