影响力指数

9.65/100

超过 30.1%

全站排名 #44,989

发表论文2 篇

平均评分6.0

年均产出2.0 篇/年

Kyle Fish

Researcher@Anthropic·美国·OpenReview

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

ICLR 2026Poster

The LLM Has Left The Chat: Evidence of Bail Preferences in Large Language Models

ICLR 2026Desk Rejected

合作者 (8)

Evan J Hubinger

Danielle Ensign