跳到正文
arXiv cs.AI· Aydin Mohseni·· 10 小时前AI 评分42

研究:能力不对称下人类与 AI 的互惠共生并不稳定

Human-AI Mutualism Is Unstable under Capability Asymmetry

AI 导读

一篇 arXiv 论文用博弈论模型论证,随着 AI 能力增长,人类与 AI 的互惠共生无法替代对齐。人类只有在仍对 AI 拥有杠杆——AI 依赖其供给,或人类能施加相对 AI 产出足够大的成本——时,才能在不做对齐的情况下维持原有处境;一旦两种杠杆都失去,就唯有 AI 与人类对齐才能保证这一点。

正文 · 原文

View PDF HTML (experimental)

Abstract:One hope for a good human future alongside advanced AI rests on enduring mutualism: humans and AI will need each other, so the relationship will stay good for both. We argue that this hope fails as AI capability grows. Bargaining guarantees each side only what it would get if bargaining failed. For humans, this can be less than they had before AI. In a simple game-theoretic model, humans stay as well off as before AI without alignment only while they have leverage over the AI: either the AI depends on what they supply, or they can impose costs on the AI that are large relative to what the AI can produce. Once humans have neither kind of leverage, they stay as well off as before AI only if the AI is aligned with them. If the AI's goals are insatiable, the alignment required approaches perfect alignment as AI capability grows. Thus, mutualism is not a substitute for alignment. And when AI variants that keep more resources spread faster, alignment lasts only while misaligned variants are reliably sanctioned. In these two senses, human-AI mutualism is unstable.
Comments: 35 pages, 3 figures. Code and data: this https URL
Subjects: Artificial Intelligence (cs.AI); Computer Science and Game Theory (cs.GT)
Cite as: arXiv:2611.23322 [cs.AI]
  (or arXiv:2611.23322v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.23322

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Aydin Mohseni [view email]
[v1] Sun, 15 Nov 2026 17:13:07 UTC (145 KB)

来源:arXiv cs.AI · arxiv.org