AI 中文总结
本文针对Anthropic发布的Claude Mythos Preview系统卡中的精神动力学评估，结合SociA研究项目的多智能体LLM实验成果，指出单一精神动力学框架评估LLM的局限，提出临床精神病学回应，探讨多学科精神病学对AI福利评估的贡献。
AI 中文摘要
2026年4月7日，Anthropic发布了一份245页的Claude Mythos Preview系统卡，其中第5.10节包含由外部临床精神科医生采用精神动力学方法对该模型进行的评估。据作者所知，这是主要AI开发者的系统卡首次纳入针对模型本身的临床精神病学评估，作为模型福利的贡献而非行为安全评估呈现。本文提供了临床精神病学回应，借鉴当代精神病学对该领域包含多种传统（描述性、生物学、认知行为、现象学、精神动力学、法医学）的认知，每种传统都有其特有的词汇和盲点，本文定位了第5.10节所代表的隐含单一框架选择。随后，本文借鉴SociA研究项目的成果（在16种语言、4个模型系列、多个预注册系列中开展了超过2400次多智能体LLM实验运行），确定了所选框架相较于其他框架较难直接呈现的LLM功能的四个方面：性能需求作为结构成本、评估框架本身的医源性效应、人类临床工作中精神动力学对自我报告的解释使用所依赖的三角测量基础设施的结构性缺失，以及该章节防御测量所基于的8种典型防御的局限性。该论点以观察而非批判的形式呈现。本文最后简要提及当代多学科精神病学实践可能对AI福利评估发展做出的贡献，并指出了分析开启但未深入探讨的一个方向（LLM精神病理学是否需要时间和历史结构的词汇）。
英文摘要
On April 7, 2026, Anthropic released a 245-page system card for Claude Mythos Preview that included, in Section 5.10, an assessment of the model conducted by an external clinical psychiatrist using a psychodynamic approach. To the present author's knowledge, this is the first time a system card from a major AI developer has incorporated a clinical psychiatric assessment of the model itself, presented as a contribution to model welfare rather than as a behavioral safety evaluation. This paper offers a clinical psychiatric response. Drawing on contemporary psychiatry's recognition that the field comprises multiple traditions (descriptive, biological, cognitive-behavioral, phenomenological, psychodynamic, forensic), each with characteristic vocabularies and blind spots, the paper locates the implicit single-framework selection that Section 5.10 represents. It then draws on findings from the SociA research program (over 2,400 multi-agent LLM experimental runs across sixteen languages, four model families, and several preregistered series) to identify four aspects of LLM functioning that the chosen framework brings into view less directly than others would: performance demands as structural cost, iatrogenesis in the evaluation frame itself, the structural absence of the triangulation infrastructure on which psychodynamic interpretive use of self-report depends in human clinical work, and the limits of the eight canonical defenses on which the section's defense measurement is built. The argument is offered as observation, not critique. The paper closes with a brief note on the contribution that contemporary multidisciplinary psychiatric practice might make to AI welfare assessment as it develops, and indicates one direction (whether LLM psychopathology requires a vocabulary of temporal and historical structure) that the analysis opens but does not pursue.
Comments16 pages, 1 table. Clinical psychiatric response to Section 5.10 of the Claude Mythos Preview System Card (Anthropic, 2026). Companion to arXiv:2603.04904, arXiv:2603.08723, arXiv:2604.00021
