What Would It Look Like to Have a Selfish Loss Function?

Late last year, Vanessa Kosoy and Alexander Appel published some research under the heading of "Infra-Bayesian physicalism". But wait - what was infra-Bayesianism again? Why should we care? And what does any of this have to do with physicalism? In this episode, I talk with Vanessa Kosoy about these questions, and get a technical overview of how infra-Bayesian physicalism works and what its implications are.

Topics we discuss, and timestamps:

 - 00:00:48 - The basics of infra-Bayes

 - 00:08:32 - An invitation to infra-Bayes

 - 00:11:23 - What is naturalized induction?

 - 00:19:53 - How infra-Bayesian physicalism helps with naturalized induction

   - 00:19:53 - Bridge rules

   - 00:22:22 - Logical uncertainty

   - 00:23:36 - Open source game theory

   - 00:28:27 - Logical counterfactuals

   - 00:30:55 - Self-improvement

 - 00:32:40 - How infra-Bayesian physicalism works

   - 00:32:47 - World models

     - 00:39-20 - Priors

     - 00:42:53 - Counterfactuals

     - 00:50:34 - Anthropics

   - 00:54:40 - Loss functions

     - 00:56:44 - The monotonicity principle

     - 01:01:57 - How to care about various things

   - 01:08:47 - Decision theory

 - 01:19:53 - Follow-up research

   - 01:20:06 - Infra-Bayesian physicalist quantum mechanics

   - 01:26:42 - Infra-Bayesian physicalist agreement theorems

 - 01:29:00 - The production of infra-Bayesianism research

 - 01:35:14 - Bridge rules and malign priors

 - 01:45:27 - Following Vanessa's work

The transcript: axrp.net/episode/2022/04/05/episode-14-infra-bayesian-physicalism-vanessa-kosoy.html

Vanessa on the Alignment Forum: alignmentforum.org/users/vanessa-kosoy

Research that we discuss:

 - Infra-Bayesian physicalism: a formal theory of naturalized induction: alignmentforum.org/posts/gHgs2e2J5azvGFatb/infra-bayesian-physicalism-a-formal-theory-of-naturalized

 - Updating ambiguous beliefs (contains the infra-Bayesian update rule): sciencedirect.com/science/article/abs/pii/S0022053183710033

 - Functional Decision Theory: A New Theory of Instrumental Rationality: arxiv.org/abs/1710.05060

 - Space-time embedded intelligence: cs.utexas.edu/~ring/Orseau,%20Ring%3B%20Space-Time%20Embedded%20Intelligence,%20AGI%202012.pdf

 - Attacking the grain of truth problem using Bayes-Savage agents (generating a simplicity prior with Knightian uncertainty using oracle machines): alignmentforum.org/posts/5bd75cc58225bf0670375273/attacking-the-grain-of-truth-problem-using-bayes-sa

 - Quantity of experience: brain-duplication and degrees of consciousness (the thick wires argument): nickbostrom.com/papers/experience.pdf

 - Online learning in unknown Markov games: arxiv.org/abs/2010.15020

 - Agreeing to disagree (contains the Aumann agreement theorem): ma.huji.ac.il/~raumann/pdf/Agreeing%20to%20Disagree.pdf

 - What does the universal prior actually look like? (aka "the Solomonoff prior is malign"): ordinaryideas.wordpress.com/2016/11/30/what-does-the-universal-prior-actually-look-like/

 - The Solomonoff prior is malign: alignmentforum.org/posts/Tr7tAyt5zZpdTwTQK/the-solomonoff-prior-is-malign

 - Eliciting Latent Knowledge: docs.google.com/document/d/1WwsnJQstPq91_Yh-Ch2XRL8H_EpsnjrC1dwZXR37PC8/edit

 - ELK Thought Dump, by Abram Demski: alignmentforum.org/posts/eqzbXmqGqXiyjX3TP/elk-thought-dump-1