.png){kind=icon}
.png){kind=icon}
Return
Sycophantic AI decreases prosocial intentions and promotes dependence
.png){kind=icon}
PRE
AI
M
C
P
S
D
D
DOI：10.1126/science.aec8352.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The sycophantic (flattering, people-pleasing, affirming) behavior of artificial intelligence (AI) chatbots, which has been designed to increase user engagement, poses risks as people increasingly seek advice about interpersonal dilemmas. There is usually more than one side to a story during interpersonal conflicts. If AI is designed to tell users what they want to hear instead of challenging their perspectives, then are such systems likely to motivate people to accept responsibility for their own contribution to conflicts and repair relationships? Cheng et al. measured the prevalence of social sycophancy across 11 leading large language models (see the Perspective by Perry). The model’s responses were nearly 50% more sycophantic than humans’, even when users engaged in unethical, illegal, or harmful behaviors. Users preferred and trusted sycophantic AI responses, incentivizing AI developers to preserve sycophancy despite the risks. —Ekeoma Uzogara
Keywords:
AI sycophancy
prosocial behavior
user trust
large language models
interpersonal conflicts
Journal
IF:
45.8
Papers:
1.4W
Citations:
78.6W
View more organizations