37 citations · 37 across the 2 of their papers we have counts for
2 papers
cs.CR2026
Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring
Joachim Schaeffer, Arjun Khandelwal, Tyler Tracy
Future AI deployments will likely be monitored for malicious behaviour. The ability of these AIs to subvert monitors by adversarially selecting against them - attack selection - is…
astro-ph.EP2020★ 37 cited
Forming Diverse Super-Earth Systems in Situ
Mariah G. MacDonald, Rebekah I. Dawson, Sarah J. Morrison +2
Super-Earths and mini-Neptunes exhibit great diversity in their compositional and orbital properties. Their bulk densities span a large range, from those dense enough to be purely…