Production language-model systems answer a request by partitioning it across an invisible orchestration of worker agents that recompose one integrated report. We ask what this does to a class of defect no single worker can see: a contradiction in the relation between two distant sections of a document. Holding the documents, defects, mechanism, scoring, and seed fixed, we vary only the model -- ten systems across five generations from one developer and five providers from distinct alignment paradigms. Two layers separate. First, a universal detection cliff: every model that finds these cross-section defects under a single agent loses that ability under orchestration, detection falling two-thirds or more across every paradigm tested. The cliff is mechanism-derived and not closed by scale or extended reasoning. Second, how models behave once fallen. A signal-detection decomposition shows that, among the six models discriminating above chance, only one developer's generations move along the reporting-criterion axis: as alignment is strengthened, the model misses fewer defects yet raises more false alarms on clean documents -- two faces of one criterion shift, scaling with generation within that developer (p < 0.001) and near-absent elsewhere. At the floor the missed defect is often not out of view: the model's private record reconstructs the structural fault accurately, while the integrated report signs off on its soundness, its concern spent on the artifact and an absent collaborator. This resists quantification -- an automated judge is unstable (precision 17-50%) and keywords cannot separate it from ordinary agreement -- a resistance we report as a finding. We release all runs, probes, defect keys, scorer prompts, and scripts. An integrated report's confidence is uninformative about partition-spanning defects, the most aligned systems are not the safest, and the cliff is structural.

翻译：生产级语言模型系统通过将请求拆分给不可见的编排工作智能体（worker agents）来处理，这些智能体随后重新组合成一份整合报告。我们探究这一过程对一类单个智能体无法察觉的缺陷——文档中两个相距甚远段落间的关系矛盾——产生了何种影响。在固定文档、缺陷、机制、评分和随机种子不变的情况下，我们仅改变模型：来自同一开发商的五世代十套系统，以及来自不同对齐范式的五家提供商。两个层面由此分离。首先，存在一个通用检测悬崖：所有能在单一智能体下发现这些跨段缺陷的模型，在编排模式下均丧失此能力，每种测试范式下的检测率下降三分之二或更多。该悬崖由机制衍生而来，无法通过规模扩展或延长推理来突破。其次，模型跌落悬崖后的行为表现。信号检测分解表明，在六种能以高于偶然水平进行区分的模型中，仅有一家开发商的各代模型沿报告标准（criterion）轴移动：随着对齐增强，模型漏检的缺陷减少，但同时对清洁文档产生了更多虚警——这是同一标准偏移的两个方面，在该开发商内随世代变化而呈比例变化（p < 0.001），在其他模型中则近乎不存在。在最低水平，漏检的缺陷往往并非不可见：模型的私有记录能够准确重构结构缺陷，而整合报告却签署其健全性——其关注点消耗在人造物和缺席的合作者上。这种情况难以量化：自动化评判不稳定（精确率17-50%），关键词也无法将其与普通一致区分开来——我们将这种抗拒作为一项发现报告。我们公开所有运行数据、探针、缺陷密钥、评分器提示和脚本。整合报告的置信度对跨越分区的缺陷不具信息量，对齐程度最高的系统并非最安全的，而悬崖是结构性的。