Home » Authors » Juan-Pablo Rivera, Ari Spiesberger, Juan J Vazquez, Arun Jose, Axel Ahlqvist, Adeline Kassler, Meru Gopalan, Sandy Tanwisuth, John Hughes

Juan-Pablo Rivera, Ari Spiesberger, Juan J Vazquez, Arun Jose, Axel Ahlqvist, Adeline Kassler, Meru Gopalan, Sandy Tanwisuth, John Hughes

Public reference bibliography and cataloged PDF materials authored or published by Juan-Pablo Rivera, Ari Spiesberger, Juan J Vazquez, Arun Jose, Axel Ahlqvist, Adeline Kassler, Meru Gopalan, Sandy Tanwisuth, John Hughes.

Found 1 document(s) Page 1 of 1

Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors

Year: 2026 • Source: arxiv.org • Listed PDF

AI control protocols aim to get useful work from models that may be misaligned by monitoring their behaviour. One approach uses a second copy of the same model as the monitor. This avoids relying on a weaker reviewer the...