Can I read An overview of 11 proposals for building safe advanced AI on EtoBox?

An overview of 11 proposals for building safe advanced AI by Hubinger, Evan is a scholarly article available to read on EtoBox.

What is An overview of 11 proposals for building safe advanced AI about?

This paper analyzes and compares 11 different proposals for building safe advanced AI under the current machine learning paradigm, including major contenders such as iterated amplification, AI safety via debate, and recursive reward modeling. Each proposal is evaluated on the four components of outer alignment, inner alignment, training competitiveness, and performance competitiveness, of which the distinction between the latter two is introduced in this paper. While prior literature has primarily focused on analyzing individual proposals, or primarily focused on outer alignment at the expense of inner alignment, this analysis seeks to take a comparative look at a wide range of proposals including a comparative analysis across all four previously mentioned components.

Author

Hubinger, Evan

Published

2020

Language

EN