Social Choice and the Value Alignment Problem *

By Mahendra Prasad. 2018

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Scalable agent alignment via reward modeling: a research direction (2018, background): “How should the preferences of different users be aggregated and traded off against each other (Baum, 2017; Prasad, 2018)?”
How to Design AI for Social Good: Seven Essential Factors (2020, background): “…our focus is on minimising the spread of information used to predict an outcome, we do not intend to foreclose on the suggestion, offered in Prasad (2018), that in some cases a fairer approach may be to maximise the available information and hence “democratise” the ability to manipulate…”
Trust in AI: progress, challenges, and future directions (2024, unknown): “…of (1) making sure that an arti ﬁ cial generalized intelligence system has values and interests aligned with those of humans (Abbass, 2019c; Bostrom, 2014; Gabriel, 2020; Prasad, 2019; Taylor et al., 2016) and (2) determining how we could be assured that we succeeded in ensuring this alignment.”