semanticscholar8.0 / 10
A Grading Rubric for AI Safety Frameworks
Jide Alaga, Jonas Schuett, Markus Anderljung
Abstract
Evaluation criteria for assessing AI company safety frameworks
Research area
agentic misalignmentagent misalignmentai alignment
Published
2024
Source
semanticscholar
Org
GovAI Oxford
Sign in to read and join the discussion.