影响力指数

28.66/100

前 25.9%

全站排名 #16,700

发表论文3 篇

平均评分5.3

年均产出1.5 篇/年

Evan J Hubinger

Researcher@Anthropic·美国·OpenReview

LitmusValues: Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas

ICLR 2026Poster

Open Character Training: Shaping the Persona of AI Assistants Through Constitutional AI

ICLR 2026Rejected

Many-shot Jailbreaking

NeurIPS 2024Poster

合作者 (20)

Ansh Radhakrishnan