在有意义的人类控制中不足确定原因.
1Delft University of Technology, Delft, Netherlands.
概括
对人工智能的有意义的人类控制 (MHC) 需要改进. 这项研究将"不确定性原因"确定为一个差距,其中相互矛盾的原因阻止了明确的AI决策,影响了AI的安全性和评估.
科学领域:
- 人工智能伦理学 人工智能伦理学
- 技术的哲学技术的哲学
- 人工智能安全研究研究
背景情况:
- 人工智能扩散引发了安全和责任方面的担忧.
- 有意义的人类控制 (MHC) 是人工智能设计和评估的框架.
- 现有的MHC框架需要理论和实践方面的进步.
研究的目的:
- 在有意义的人类控制 (MHC) 框架中发现一个关键的缺口.
- 探索MHC.原因的不足决定对MHC.原因的含义.
- 根据轴学和决策理论,为MHC框架提出改进建议.
主要方法:
- 借鉴了轴论和理性决策理论方面的研究.
- 在MHC框架的追踪和追踪条件中分析"原因"的作用.
- 检查原因不确定性的现象.
主要成果:
- 确定了MHC中的一个空白,涉及到原因不能产生单一可取的行动的情况.
- 证明了原因的不确定性挑战了MHC的追踪条件.
- 表明原因的不确定性挑战了MHC的追踪条件.
结论:
- 该MHC框架必须解决强大的AI安全性不足的原因.
- 需要进行改进,以处理人工智能决策中的相互矛盾或不确定的原因.
- 整合从轴学和决策理论的见解可以提高MHC的实际适用性.
相关概念视频
Fundamental Attribution Error
13.7K
According to some social psychologists, people tend to overemphasize internal factors as explanations—or attributions—for the behavior of other people. They tend to assume that the behavior of another person is a trait of that person, and to underestimate the power of the situation on the behavior of others. They tend to fail to recognize when the behavior of another is due to situational variables, and thus to the person’s state. This erroneous assumption is...
13.7K
Personal Choice and Fate Attributions
155
Some individuals interpret life events as a consequence of their personal choices and actions, while others believe that outcomes are dictated by fate or destiny. This divergence in perspective has been examined in psychological and cross-cultural studies, particularly in relation to religious faith and cultural beliefs about causality.Fate and Personal ResponsibilityPeople who emphasize personal responsibility view events as direct consequences of their decisions. For instance, breaking a leg...
155
Control Systems
1.8K
Control systems are everywhere in contemporary society, influencing diverse applications from aerospace to automated manufacturing. These systems can be found naturally within biological processes, such as blood sugar regulation and heart rate adjustment in response to stress, as well as in man-made systems like elevators and automated vehicles. A control system is essentially a network of subsystems and processes that collaboratively convert specific inputs into desired outputs.
At the heart...
At the heart...
1.8K
Locus of Control
195
Locus of control describes how individuals perceive the causes of events in their lives, influencing motivation and well-being. Introduced by Julian Rotter in 1954, it is categorized into internal and external locus of control.Internal Locus of ControlIndividuals with an internal locus of control believe their actions determine outcomes, fostering responsibility, self-efficacy, and motivation. For example, an employee may attribute career success to hard work. Research links this mindset to...
195
Cause and Effect
12.0K
While variables are sometimes correlated because one does cause the other, it could also be that some other factor, a confounding variable, is actually causing the systematic movement in our variables of interest. For instance, as sales in ice cream increase, so does the overall rate of crime. Is it possible that indulging in your favorite flavor of ice cream could send you on a crime spree? Or, after committing crime do you think you might decide to treat yourself to a cone?
12.0K
Decision Making
884
Decision-making is a fundamental cognitive process that involves evaluating alternatives and selecting among them. This process can range from simple choices, such as deciding what to wear, to complex decisions, like choosing a major in college or a career path. The complexity of the decision often dictates the approach we use, which can be broadly categorized into two types: automatic and controlled decision-making.
Automatic decision-making is fast, intuitive, and relies on gut feelings...
Automatic decision-making is fast, intuitive, and relies on gut feelings...
884


