Evan Hubinger

基本信息

浏览量：170

职业迁徙

个人简介

AI safety research scientist at Anthropic. Previously AI safety Research Fellow at the Machine Intelligence Research Institute, and experience at OpenAI, Google, Yelp, and Ripple. Author of the Coconut programming language.

研究兴趣

论文共 15 篇作者统计合作学者相似作者

按年份排序按引用量排序主题筛选期刊级别筛选合作者筛选合作机构筛选

Auditing Language Models for Hidden Objectives

Samuel Marks,Johannes Treutlein, Trenton Bricken, Jack Lindsey, Jonathan Marcus, Siddharth Mishra-Sharma, Daniel M. Ziegler, Emmanuel Ameisen, Joshua Batson, Tim Belonax, Samuel R. Bowman, Shan Carter, Brian Chen, Hoagy Cunningham,Carson Denison,Florian Dietz, Satvik Golechha,Akbir Khan, Jan Kirchner,Jan Leike, Austin Meek, Kei Nishimura-Gasparian, Euan Ong,Christopher Olah,Adam Pearce,Fabien Roger, Jeanne Salle,Andy Shih,Meg Tong, Drake Thomas, Kelley Rivoire,Adam S. Jermyn, Monte MacDiarmid,Tom Henighan,Evan Hubinger

CoRR (2025)

引用0浏览0EI引用

Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models