BriefGPT.xyz
Feb, 2025
人类对生成型人工智能对齐的误解：一项实验室实验
Human Misperception of Generative-AI Alignment: A Laboratory Experiment
HTML
PDF
Kevin He, Ran Shorrer, Mengjia Xia
TL;DR
本研究通过激励实验探讨人们在经济决策中对生成型人工智能（GenAI）对齐的认知偏差。研究发现，人们普遍高估了GenAI的选择与人类选择之间的对齐程度，这可能会导致错误的判断和决策。
Abstract
We conduct an incentivized
Laboratory Experiment
to study people's
Perception
of generative artificial intelligence (GenAI)
Alignment
in t
→