用新框架重审三大意识思想实验，区分行为表现与内在结构效率。
Revisiting Classic Thought Experiments to Measure Consciousness for Artificial Intelligence Safety
- 构建符号化框架，用任务性能和操作意识度量行为与结构效率。
- 压缩生成系统比未压缩查表系统更高效，虽性能相当但内部结构更优。
- 为未来人工智能安全分析提供意识机制的新视角，适合关注AI本质的研究者。
本研究笔记通过保守-一致编码（CCE）框架重新审视莱布尼茨的磨坊、图灵的模仿游戏以及塞尔的中文房间。在简化的符号设定中，行为成功由任务表现 $W_{causal,T}$ 衡量，而支持行为的内部结构效率则由操作意识 $κ_T$ 衡量。在此设定下，未压缩查找系统与紧凑生成系统可实现相近的任务表现，但在 $κ_T$ 上显著不同：前者依赖不断扩大的未复用映射存储，后者则通过紧凑内部结构反复利用。因此，该研究将外在表现与支撑其的组织结构分离开来，重新诠释了关于理解的经典争论，并论证这种区分对后续人工智能安全分析的重要性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。