Quantifying the Bitter Lesson: How Safety Benchmarks Measure Capabilities Instead of Safety

Authors: Richard Ren, Steven Basart, Adam Khoja, Alexander Pan, Alice Gatti, Long Phan, Xuwang Yin, Mantas Mazeika, Gabriel Mukobi, Ryan Kim, Stephen Fitz, Dan Hendrycks

Abstract

No abstract is available for this paper.

Open original