重访经典思想实验以衡量AI安全意识
原标题:Revisiting Classic Thought Experiments to Measure Consciousness for Artificial Intelligence Safety
AI 摘要
该研究笔记通过守恒一致编码(CCE)框架重新审视了莱布尼茨磨坊、图灵测试和塞尔中文房间等经典思想实验,提出了一个符号化设置,用任务表现衡量行为成功,用操作意识(κ_T)衡量内部结构效率。研究发现,未压缩的查找系统和紧凑的生成系统在行为上可能相当,但在操作意识上差异显著,从而将外在表现与支撑它的内部组织分离,为AI安全分析提供了新视角。
正文节选
Computer Science > Artificial Intelligence Title:Revisiting Classic Thought Experiments to Measure Consciousness for Artificial Intelligence Safety View PDF HTML (experimental) Abstract: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 whi