Benchmark Early and Red Team Often: A Framework for Assessing and Managing Dual-Use Hazards of AI Foundation Models
Barrett, Anthony M, Jackson, Krystal, Murphy, Evan R, Madkour, Nada, Newman, Jessica
Year of Publication 15.05.2024
Year of Publication 15.05.2024
Get full text
Journal Article
Affirmative safety: An approach to risk management for high-risk AI
Wasil, Akash R, Clymer, Joshua, Krueger, David, Dardaman, Emily, Campos, Simeon, Murphy, Evan R
Published in arXiv.org (14.04.2024)
Get full text
Published in arXiv.org (14.04.2024)
Paper
Can We Manage the Risks of General-Purpose AI Systems?
Barrett, Anthony M, Newman, Jessica, Nonnecke, Brandie, Hendrycks, Dan, Murphy, Evan R, Jackson, Krystal A
Published in Tech Policy Press (05.12.2023)
Get full text
Published in Tech Policy Press (05.12.2023)
Newspaper Article