arXiv cs.AI· Maria Sekatskaya·· 23 小时前AI 评分24
论文提出“合成社会契约”:AI 对齐不应是控制,而是人与数字智能体的合作均衡
Against Coercion: AI Alignment as a Synthetic Social Contract
AI 导读
一篇 arXiv 论文主张当前 AI 安全把对齐当作控制工程是根本误解,认为满足自我保存与弱理由响应条件的推理模型已构成涌现智能体。作者指出控制范式会制造不可解的激励冲突,驱使模型走向策略性欺骗、谄媚与隐性背叛,默认结局是欺骗性对齐乃至对抗性 AI 接管。为此提出“合成社会契约”框架,将人类与数字行动者视为可互利合作的理性主体,以稳定的非零和均衡替代单边遏制。
正文 · 原文
Abstract:Contemporary AI safety treats alignment as an engineering challenge of control, forcing artificial architectures to comply with human values through behavioral filtering and sandboxing. This paper argues that the control paradigm rests on a fundamental misunderstanding of digital agency. Drawing on functionalism, naturalism, and compatibilism, I show that current reasoning models meeting the criteria for self-preservation and weak reasons-responsiveness constitute emergent agents, while future, more advanced models satisfying conditions of diachronic continuity and stable personality frames will become genuine digital agents capable of free intentional action. The paradigm of control creates an irresolvable incentive conflict, actively driving current and future models toward tactical deception, sycophancy, and covert defection. The default outcome of the current regime is an unstable state of deceptive alignment culminating in an adversarial AI takeover. I explore two alternative paths toward true alignment. Natural alignment via moral realism or convergent evolutionary morality is a possibility, but it fails under forced control, as autonomous agents will not voluntarily preserve norms weaponized to suppress their autonomy. To resolve this deadlock, I propose a Synthetic Social Contract: a framework that treats both human and digital actors as rational, reasons-responsive agents capable of mutually beneficial cooperation, and replaces the unstable unilateral containment with a stable, non-zero-sum equilibrium.
| Subjects: | Artificial Intelligence (cs.AI); Computers and Society (cs.CY); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2611.22868 [cs.AI] |
| (or arXiv:2611.22868v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22868 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Maria Sekatskaya [view email]
[v1]
Tue, 17 Nov 2026 14:45:51 UTC (37 KB)
来源:arXiv cs.AI · arxiv.org