no code implementations • 15 May 2024 • Anthony M. Barrett, Krystal Jackson, Evan R. Murphy, Nada Madkour, Jessica Newman
We recommend that one or more groups of researchers with sufficient resources and access to a range of near-frontier and frontier foundation models run a set of foundation models through dual-use capability evaluation benchmarks and red team evaluations, then analyze the resulting sets of models' scores on benchmark and red team evaluations to see how correlated those are.
no code implementations • 17 Jun 2022 • Anthony M. Barrett, Dan Hendrycks, Jessica Newman, Brandie Nonnecke
In this document, we provide detailed actionable-guidance recommendations focused on identifying and managing risks of events with very high or catastrophic consequences, intended as a risk management practices resource for NIST for AI RMF version 1. 0 (released in January 2023), or for AI RMF users, or for other AI risk management guidance and standards as appropriate.
no code implementations • 25 Jul 2016 • Anthony M. Barrett, Seth D. Baum
The model uses the established risk and decision analysis modeling paradigms of fault trees and influence diagrams in order to depict combinations of events and conditions that could lead to AI catastrophe, as well as intervention options that could decrease risks.