| 来源类型 | Working Paper
|
| 规范类型 | 报告
|
| DOI | 10.3386/w30017
|
| 来源ID | Working Paper 30017
|
| Aligned with Whom? Direct and Social Goals for AI Systems |
| Anton Korinek; Avital Balwit
|
| 发表日期 | 2022-05-09
|
| 出版年 | 2022
|
| 语种 | 英语
|
| 摘要 | As artificial intelligence (AI) becomes more powerful and widespread, the AI alignment problem—how to ensure that AI systems pursue the goals that we want them to pursue—has garnered growing attention. This article distinguishes two types of alignment problems depending on whose goals we consider, and analyzes the different solutions necessitated by each. The direct alignment problem considers whether an AI system accomplishes the goals of the entity operating it. In contrast, the social alignment problem considers the effects of an AI system on larger groups or on society more broadly. In particular, it also considers whether the system imposes externalities on others. Whereas solutions to the direct alignment problem center around more robust implementation, social alignment problems typically arise because of conflicts between individual and group-level goals, elevating the importance of AI governance to mediate such conflicts. Addressing the social alignment problem requires both enforcing existing norms on their developers and operators and designing new norms that apply directly to AI systems. |
| 主题 | Microeconomics
; Welfare and Collective Choice
; Development and Growth
; Innovation and R&
; D
|
| URL | https://www.nber.org/papers/w30017
|
| 来源智库 | National Bureau of Economic Research (United States)
|
| 引用统计 |
|
| 资源类型 | 智库出版物
|
| 条目标识符 | http://119.78.100.153/handle/2XGU8XDN/587690
|
推荐引用方式
GB/T 7714 |
Anton Korinek,Avital Balwit. Aligned with Whom? Direct and Social Goals for AI Systems. 2022.
|
|
文件名：
|
w30017.pdf
|
|
格式：
|
Adobe PDF
|
此文件暂不支持浏览
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。
