People sometimes exhibit a costly preference for humans relative to algorithms, which is often defined as a domain-general algorithm aversion. I propose it is instead driven by biased evaluations of the self and other humans, which occurs more narrowly in domains where identity is threatened and when evaluative criteria are ambiguous.

中文翻译：

---

偏爱人类，而不是算法厌恶

相对于算法，人们有时会表现出对人类的昂贵偏好，这通常被定义为域通用算法厌恶。我建议它是由对自我和其他人的偏见评估驱动的，这在身份受到威胁和评估标准模棱两可的领域中发生得更狭隘。