Abhimanyu Pallavi Sudhir

(The original title for this was "Markets are equivalent to stuff", because I also demonstrate market-MDP/Bellman and market-backprop analogies. While those scratched an itch I've long had, the more important result is the headline one. Part of my work at MATS in Richard Ngo's stream.) 1. setup and price recursion/backprop...

(This article broadly explains mirror ascent, continuous Bayesian inference and information geometry in full. Title refers to the result in section 3. Part of my work at MATS in Richard Ngo's stream.) Contents: 1. generalized entropies and Bregman divergence 2. mirror ascent 3. reward is hyperstitional information 4. continuous-time mirror...

Counterfactual mugging is the typical problem used to motivate updateless decision theory: > Omega flips a coin. If Heads, it asks you for $1. If Tails, it offers you $5 only if it predicts you would have given it the $1 had the coin come up Heads. Counterfactuals are confusing...

TL;DR: Pareto indifference = "the super-agent must aggregate not only the agents' utilities but also their risk aversion levels" (where "aggregating agents' risk aversions" means "taking inequality aversion to be the risk aversion of an agent behind the veil of ignorance". Take some agents with utility functions . In general...

Recent discourse surrounding Jevon’s paradox provides an opportunity to flesh out the precise intuitions behind marginalist economics and how concepts like “elasticity” arise naturally from agent/graph-based first principles. Say you have resource x (e.g. compute) with cost C(x) that produces good y (e.g. AI), with utility function U(x) via production...

I’m listing some “ways to think about alignment”. I’m not sure how much of the “whole problem” each of these individually captures, but they are intended to be very well-motivated, fundamental problems which can: 1. demonstrate to an honest skeptic that there is “something here”, it’s not just hand-wavy sci-fi...

Markets for information are inefficient, in large part due to the Buyer’s Inspection Paradox: you can’t “inspect” information like you would any other good before buying — the moment you inspect the information, you have obtained it and cannot return it. More generally, the problem is an inability to reliably...