Search Results for author:
Found 3 papers, 0 papers with code
Benchmark Early and Red Team Often: A Framework for Assessing and Managing Dual-Use Hazards of AI Foundation Models
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.
Actionable Guidance for High-Consequence AI Risk Management: Towards Standards Addressing AI Catastrophic Risks
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.
A Model of Pathways to Artificial Superintelligence Catastrophe for Risk and Decision Analysis
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.
