Joe Benton

Collusion, Matoni et al.

2024, and research sabotage, Benton et al.

2024.

The J++ lens substantially improves readout accuracy over prior workspace lenses.

Thanks to Camila Blanc and Agam Bhatia for sharing their implementation of the R lens.

Thanks to Wes Gurney, Neel Nanda, Camila Blanc, Agam Bhatia, Adam Lowitt, Dylan Plunkett, Heather Demarest, Doria Ivanova, Evzen Wiebital, Julian Meinder, Zach UL, Donato Chrysostomoi, Jake Ward, Victoria Lee, Andy Han, and attendees at the Eleos Concon for useful conversations.

Thanks to Michael Mulit, Jules Schmaltz, Avery Griffin, Mojmir Stehlik, and Joe Benton for additional support.

We are grateful to Anthropic for providing compute for this project.