"Scalable AI Safety via Doubly-Efficient Debate."

Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras (2023)

Details and statistics

DOI: 10.48550/ARXIV.2311.14125

access: open

type: Informal or Other Publication

metadata version: 2023-11-30

a service of  Schloss Dagstuhl - Leibniz Center for Informatics