0

Jonathan Ng

Papers
1

Cite

Notes

Only stored in your browser.

Attribution

Affiliations & profile
Semantic Scholar
Attribution policy →
1papers

Authored papers

1

Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark

arXiv 2023

2023

Affiliations

No known affiliations.

Frequent co-authors

9

from 1 papers

Alexander Pan

1 shared paper

Andy Zou

founder

1 shared paper

Dan Hendrycks

director

1 shared paper

HANLIN ZHANG

1 shared paper

Jun Shern Chan

1 shared paper

Nathaniel Li

grad-student

1 shared paper

Scott Emmons

1 shared paper

Steven Basart

researcher

1 shared paper

Thomas Woodside

1 shared paper