arXiv cs.AI· Gerrit Gro{\ss}mann·· 10 小时前AI 评分31
论文称 AI 对齐既不可解也不充分
AI Alignment Is Neither Solvable nor Sufficient
AI 导读
一篇 arXiv 论文主张 AI 对齐这一目标本身存在误导：对齐缺乏明确定义，因为它预设了足够稳定、可识别的人类意图或价值；即便能给出具体定义，对齐也不可解；而在看似可解之处，解决对齐也未必能减轻 AI 的负面影响。
正文 · 原文
Abstract:Humans and AI systems increasingly act within the same social and economic environments. Alignment, the goal of ensuring that AI systems act in accordance with human values, is widely regarded as a central challenge for ensuring that AI benefits society while avoiding harm. We argue that this endeavor is misguided. First, alignment is not well defined, as it presumes a sufficiently stable and identifiable set of human intentions or values. Second, where a concrete notion of alignment can be specified, it is not solvable. Third, where alignment appears solvable, solving it would not necessarily mitigate the negative consequences of AI. A key reason is that alignment is typically framed as a property of individual AI systems, while the resulting hybrid societies of humans and machines are complex systems shaped by interactions and feedback loops. Emergent risks, and not only those posed by individual misaligned systems, are therefore likely to become a major source of harm. We conclude that AI safety is an ongoing challenge and not a problem that can be solved once and for all by verifying a particular model property.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13167 [cs.AI] |
| (or arXiv:2611.13167v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13167 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Gerrit Großmann [view email]
[v1]
Mon, 9 Nov 2026 19:51:48 UTC (80 KB)
来源：arXiv cs.AI · arxiv.org