发表机构
School of Informatics, University of Edinburgh（爱丁堡大学信息学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过CCE框架重访三大经典意识思想实验，构建符号测量场景区分外在任务表现与内部操作意识，指出两类系统行为表现相当但意识效率差异显著，为AI安全分析提供新的研究视角。
AI 中文摘要
本研究简报通过守恒一致编码（Conservation-Congruent Encoding，CCE）框架，重新审视了莱布尼茨的磨坊、图灵的模仿游戏以及塞尔的中文屋思想实验。研究形式化了一个简化符号场景：成功行为由任务表现（$W_{causal,T}$）衡量，而保留的内部结构支撑该行为的效率由操作意识（$κ_T$）衡量。在该设置下，未压缩的查找系统和紧凑生成系统原则上可取得相当的行为成功率，但$κ_T$差异极大：前者依赖不断扩张且不可复用的固定映射存储，后者则复用紧凑的内部结构。本简报由此将外在表现与支撑表现的组织结构分离，重构了关于理解的经典争议，并阐释了该区分对后续AI安全分析的重要意义。
英文摘要
This research note revisits Leibniz's mill, Turing's imitation game, and Searle's Chinese Room through the Conservation-Congruent Encoding (CCE) framework. It formalises a toy symbolic setting in which successful behaviour is measured by task performance ($W_{causal,T}$), while the efficiency with which preserved internal structure supports that behaviour is measured by operational consciousness ($κ_T$). Within this setup, an uncompressed lookup system and a compact generative system can in principle achieve comparable behavioural success, yet diverge sharply in $κ_T$: the former relies on an expanding standing store of unreused mappings, whereas the latter reuses compact internal structure. The note therefore reframes classic disputes about understanding by separating outward performance from the organisation that sustains it, and motivates why this distinction may matter for later AI-safety analysis.
Comments5 pages
