arXiv:2608.11225v1 Announce Type: new Abstract: AI "personality clones" force a re-examination of personal identity in operational terms. Setting aside the hard problem of consciousness, we approach identity through the
소셜 계정으로 로그인
论文摘要指出，AI 人格克隆的出现迫使人们重新检验个人身份的含义。与传统哲学讨论聚焦内在意识不同，这项研究选择从外部视角出发，将身份视为可被观察、测量和操作的对象。摘要中「Setting aside the hard problem of consciousness」这一表述，表明作者有意绕开意识本质的哲学争论，把讨论锚定在更具工程与实证色彩的层面。不过，由于 arXiv 页面仅提供了摘要开头部分，论文后续提出的具体框架维度、操作化指标以及研究计划细节，原文未提供。
从同日发布的相邻论文来看，arXiv cs.AI 板块在 8 月 13 日集中出现了一批涉及多智能体系统、LLM 社会模拟等主题的工作。例如，一篇关于多 LLM 智能体系统动态治理的论文讨论了目标函数缺失时智能体交互的协作问题来源；另一篇关于在笔记本电脑上模拟大规模 LLM 智能体社会的研究，则关注宏观涌现现象的仿真成本问题来源。这些同期工作共同勾勒出一个趋势：研究者正越来越多地把 LLM 智能体视为具有类人格属性的交互单元，而人格克隆的身份问题恰好处于这一趋势的概念延伸线上。
需要说明的是，本文所讨论的 AI 人格克隆论文与上述同期论文之间是否存在直接引用或合作关系，原文未提供相关信息。从主题相关性看，人格克隆研究关注的是单个 AI 实体的身份连续性与外部辨识问题，而多智能体治理与大规模社会模拟关注的是群体层面的交互与涌现，两者构成了从个体到群体的研究光谱。这种并置有助于读者理解该论文所处的学术语境，但不宜据此推断作者之间的具体关联。
arXiv:2608.11225v1 Announce Type: new Abstract: AI "personality clones" force a re-examination of personal identity in operational terms. Setting aside the hard problem of consciousness, we approach identity through the indiscernibility of manifestations, as assessed by an observer over a duration. We distinguish three criteria that "identity" conflates: fidelity to a target person, generic human-likeness, and individuality. We propose a six-term factorization of observed identity (substrate, dispositions, memory, update dynamics, context, exogenous contingencies), with a state-space formulation. Indiscernibility is defined as one minus a judge's distinguishing advantage, and the factorization's coefficients become local sensitivities estimable by randomized ablation. The central claim is a conditional conjecture: given hypotheses about the agent's information on its own persistence and about consequences bearing on its own stakes, versionability tends to degrade long-horizon indiscernibility. An analogy with lambda-calculus, linear typing, and bisimulation clarifies what linearity does and does not establish. Between product-clone and individual we identify a third object, the delegate: a task-limited, bounded-lifespan partial clone ending in a bandwidth-limited testament. We map the empirical literature onto the three criteria, propose an experimental program, and argue that the correct long-horizon criterion is not trajectory fidelity but climate fidelity: matching the conditional distribution of a person's possible responses. The best clone is the one that diverges from the original as the original would have diverged from itself.