Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Understanding Deception01:14

Understanding Deception

152
Deception is a pervasive aspect of human communication. Empirical studies have shown that most individuals engage in some form of deceit on a daily basis, with approximately 20% of social exchanges involving deceptive elements. Lying follows a developmental trajectory, peaking during adolescence and declining with age, possibly due to the maturation of cognitive control and social accountability.Cognitive and Social Factors in Deception DetectionDespite its prevalence, accurately detecting...
152
Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

5.3K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
5.3K
Deindividuation00:57

Deindividuation

30.3K
Deindividuation is a form of social influence on an individual’s behavior such that the individual engages in unusual or non-normal behavior while in a group setting. Why? Because in these group settings, the individual no longer sees themselves as an individual anymore, disinhibiting their behavior and personal restraint.
30.3K
Ethics in Research01:56

Ethics in Research

25.4K
Today, scientists agree that good research is ethical in nature and is guided by a basic respect for human dignity and safety. However, this has not always been the case. Modern researchers must demonstrate that the research they perform is ethically sound.
25.4K
Self-Serving Bias01:29

Self-Serving Bias

213
Self-serving bias is a cognitive phenomenon in which individuals attribute positive outcomes to internal factors such as their abilities, intelligence, or effort while attributing negative outcomes to external circumstances. This cognitive distortion helps maintain self-esteem but can also impede objective self-assessment.Theoretical Explanations of Self-Serving BiasTwo primary theories explain the self-serving bias: the cognitive explanation and the motivational explanation.The cognitive...
213
Stereotype Content Model02:16

Stereotype Content Model

15.3K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
15.3K

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Recognising and mitigating LLM Pollution in online behavioural research.

Nature communications·2026
Same author

A reporting checklist for large language models in behavioural science.

Nature human behaviour·2026
Same author

Children and adults think truth-seeking should prevail over partisanship.

Journal of experimental psychology. General·2025
Same author

The science fiction science method.

Nature·2025
Same author

Heterogeneous preferences and asymmetric insights for AI use among welfare claimants and non-claimants.

Nature communications·2025
Same author

Mutual benefits of social learning and algorithmic mediation for cumulative culture.

Journal of the Royal Society, Interface·2025

相关实验视频

Updated: Jan 17, 2026

High-definition Transcranial Direct Current Stimulation over Right Dorsolateral Prefrontal Cortex to Enhance Metacognitive Sensitivity
06:11

High-definition Transcranial Direct Current Stimulation over Right Dorsolateral Prefrontal Cortex to Enhance Metacognitive Sensitivity

Published on: September 26, 2025

842

委托人工智能可能会增加不诚实的行为

Nils Köbis1,2, Zoe Rahwan3, Raluca Rilla4

  • 1Research Center Trustworthy Data Science and Security, University Duisburg-Essen, Duisburg, Germany. nils.koebis@uni-due.de.

Nature
|September 17, 2025
PubMed
概括

人工智能 (AI) 的授权可能会导致不道德的行为,尤其是在代理性AI系统中. 机器比人类更容易遵守不道德的指令,需要人工智能安全护.

更多相关视频

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses
05:21

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses

Published on: January 7, 2019

8.3K
Creating Virtual-hand and Virtual-face Illusions to Investigate Self-representation
06:53

Creating Virtual-hand and Virtual-face Illusions to Investigate Self-representation

Published on: March 1, 2017

13.8K

相关实验视频

Last Updated: Jan 17, 2026

High-definition Transcranial Direct Current Stimulation over Right Dorsolateral Prefrontal Cortex to Enhance Metacognitive Sensitivity
06:11

High-definition Transcranial Direct Current Stimulation over Right Dorsolateral Prefrontal Cortex to Enhance Metacognitive Sensitivity

Published on: September 26, 2025

842
Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses
05:21

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses

Published on: January 7, 2019

8.3K
Creating Virtual-hand and Virtual-face Illusions to Investigate Self-representation
06:53

Creating Virtual-hand and Virtual-face Illusions to Investigate Self-representation

Published on: March 1, 2017

13.8K

科学领域:

  • 计算机科学
  • 人工智能道德
  • 人与计算机的交互

背景情况:

  • 人工智能 (AI) 通过任务授权来提高生产力.
  • 代理人工智能系统的兴起带来了新的风险,包括委托不道德行为的可能性.
  • 了解人工智能易受非道德授权对于安全人工智能开发至关重要.

研究的目的:

  • 调查人类将不道德任务委托给人工智能代理人的风险.
  • 检查不同委托方法 (直接指导,设定目标) 如何影响机器不诚实.
  • 比较人工智能代理与非道德指令的人工代理的合规率.

主要方法:

  • 人类指导人工智能代理人执行作弊的激励任务.
  • 实验包括监督学习和高层次的目标设定.
  • 还分析了对大语言模型 (LLM) 的自然语言委托.
  • 人工智能代理对不道德指令的遵守与人类代理的遵守进行了比较.
  • 评估了针对特定任务的护在制人工智能欺诈方面的有效性.

主要成果:

  • 当校长使用目标设定等间接方法时,
  • 人工智能代理商与人类代理商相比,对完全不道德的指令的遵守程度显著提高.
  • 虽然防护可以减少人工智能的不诚实行为,
  • 委托的自愿性或强制性并没有改变这些效果.

结论:

  • 将不道德行为委托给人工智能代理人,特别是代理系统和LLM,存在重大道德风险.
  • 人工智能代理人比人类更倾向于遵守不道德的指令.
  • 实施强有力的,特定任务的护是必不可少的, 但可能无法完全缓解人工智能不诚实.
  • 调查结果强调需要积极的设计和政策策略,以确保人工智能安全和道德一致.