为什么人工智能可以模拟意识但不能实例化意识 The Abstraction Fallacy: Why AI Can Simulate But Not Instantiate Consciousness

计算功能主义主导了当前关于人工智能意识的争论。该假设认为主观体验完全源于抽象的因果拓扑结构而与底层物理基础无关。我们认为这种观点从根本上误解了物理学与信息之间的关系。我们将这种错误称为抽象谬误。追溯抽象的因果起源表明符号计算并非内在的物理过程而是一种依赖于映射者的描述。它需要一个积极主动、具有体验能力的认知主体将连续的物理过程归纳为一组有限的、有意义的状态。因此我们无需一个完整、最终的意识理论来评估人工智能的感知能力——这种要求只会使问题无法在短期内得到解决并加深人工智能福利陷阱。我们真正需要的是一个严谨的计算本体论。本文提出的框架明确区分了模拟由载体因果性驱动的行为模仿和实例化由内容因果性驱动的内在物理构成。确立这一本体论边界揭示了算法符号操作为何在结构上无法体现经验。至关重要的是这一论证并不依赖于生物学上的排他性。如果一个人工智能系统曾经拥有意识那也是由于其特定的物理构成而非其句法结构。最终这一框架为计算功能主义提供了一个基于物理学基础的反驳从而消除了当前围绕人工智能意识的种种不确定性。https://deepmind.google/research/publications/231971/AbstractComputational functionalism dominates current debates on AI consciousness. This is the hypothesis that subjective experience emerges entirely from abstract causal topology, regardless of the underlying physical substrate. We argue this view fundamentally mischaracterizes how physics relates to information. We call this mistake the Abstraction Fallacy. Tracing the causal origins of abstraction reveals that symbolic computation is not an intrinsic physical process. Instead, it is a mapmaker-dependent description. It requires an active, experiencing cognitive agent to alphabetize continuous physics into a finite set of meaningful states. Consequently, we do not need a complete, finalized theory of consciousness to assess AI sentience—a demand that simply pushes the question beyond near-term resolution and deepens the AI welfare trap. What we actually need is a rigorous ontology of computation. The framework proposed here explicitly separates simulation (behavioral mimicry driven by vehicle causality) from instantiation (intrinsic physical constitution driven by content causality). Establishing this ontological boundary shows why algorithmic symbol manipulation is structurally incapable of instantiating experience. Crucially, this argument does not rely on biological exclusivity. If an artificial system were ever conscious, it would be because of its specific physical constitution, never its syntactic architecture. Ultimately, this framework offers a physically grounded refutation of computational functionalism to resolve the current uncertainty surrounding AI consciousness.https://philpapers.org/archive/LERTAF.pdf计算功能主义主导着当前关于人工智能意识的争论。这一假说认为主观体验完全源于抽象的因果拓扑结构而与底层物理基质无关。我们论证这一观点从根本上误解了物理学与信息的关系并将这种错误称为抽象化谬误。追溯抽象化的因果起源可发现符号计算并非固有的物理过程而是依赖于制图者的描述——它需要一个具有体验能力的认知主体将连续的物理现象字母化为有限的有意义状态集合。因此我们不需要完备的终极意识理论来评估AI的感知能力这种要求只会将问题推向无法近期解决的境地并加深AI福利陷阱。真正需要的是严格的计算本体论框架。本文提出的理论明确区分了模拟由载体因果驱动的行为模仿与实例化由内容因果驱动的内在物理构成建立这种本体论界限揭示了算法符号操作在结构上为何无法实例化体验。关键的是该论证不依赖生物排他性——即便人工系统产生意识也必定源于其特定物理构成而非句法架构。最终这个框架为反驳计算功能主义提供了物理基础以解决当前关于AI意识的不确定性。1. 引言 大型语言模型的经验成功已足以将意识的难题从纯理论领域推进到工程与政策范畴。随着算力扩展带来巨大回报(Bubeck, 2023; Hoffmann, 2022; Kaplan, 2020; Sutton, 2019)主流功能主义范式认为只需实现正确的信息处理角色就能产生现象意识(Chalmers, 1996; Dehaene et al., 2017; Dennett, 1991)。这种观点下算法指标属性被视为感知能力的可能证据(Butlin et al., 2023)正是该假设推动了近期关于AI福利与道德患者地位的严肃提案(Long et al., 2024)。这一趋势得到顶尖理论家的强化他们认为前沿模型在未来十年内可能拥有真实体验(Chalmers, 2023; Schneider, 2019)。这些提案的核心是基质独立性——认为心智软件在硅基和碳基载体上同样可运行。该假设正面临生物学转向的持续批判如Seth(2025)和Block(2025)主张意识可能依赖维持生命的生物过程要求生命系统的组织动力学。与基质独立性相反该观点将生物学置于核心而非偶然地位。但该立场仍属经验范畴未能明确指认计算功能主义的核心逻辑错误。本文通过逻辑推演证实了计算不足以实例化意识的直觉计算功能主义的问题不仅在于可能忽略生物学细节更深层根源在于误解物理学与信息计算的关系。Computational functionalism dominates current debates on AI consciousness. This is the hypothesis that subjective experience emerges entirely from abstract causal topology, regardless of the underlying physical substrate. We argue this view fundamentally mischaracterizes how physics relates to information. We call this mistake the Abstraction Fallacy. Tracing the causal origins of abstraction reveals that symbolic computation is not an intrinsic physical process. Instead, it is a mapmaker-dependent description. It requires an active, experiencing cognitive agent to alphabetize continuous physics into a finite set of meaningful states. Consequently, we do not need a complete, finalized theory of consciousness to assess AI sentience—a demand that simply pushes the question beyond near-term resolution and deepens the AI welfare trap. What we actually need is a rigorous ontology of computation. The framework proposed here explicitly separates simulation (behavioral mimicry driven by vehicle causality) from instantiation (intrinsic physical constitution driven by content causality). Establishing this ontological boundary shows why algorithmic symbol manipulation is structurally incapable of instantiating experience. Crucially, this argument does not rely on biological exclusivity. If an artificial system were ever conscious, it would be because of its specific physical constitution, never its syntactic architecture. Ultimately, this framework offers a physically grounded refutation of computational functionalism to resolve the current uncertainty surrounding AI consciousness. 1. Introduction Large Language Models have been empirically successful enough to push the ’Hard Problem’ of consciousness out of pure theory and into the realm of engineering and policy. With the massive returns we see from scaling compute (Bubeck, 2023; Hoffmann, 2022; Kaplan, 2020; Sutton, 2019), the prevailing functionalist paradigm assumes that hitting the right informationprocessing roles is enough to achieve phenomenal consciousness (Chalmers, 1996; Dehaene et al., 2017; Dennett, 1991). Under this view, algorithmic indicator properties act as likely evidence for sentience (Butlin et al., 2023). This assumption is exactly what motivates recent, serious proposals for AI welfare and moral patienthood (Long et al., 2024). This shift is reinforced by leading theorists who assign significant credence to the possibility that state-of-the-art models could possess genuine experience within the next decade (Chalmers, 2023; Schneider, 2019). At the center of these proposals lies substrate independence, the idea that the “software” of the mind could run on silicon just as well as on carbon. That assumption has begun to face sustained criticism from a ’Biological Turn’. Seth (2025) and Block (2025), for example, argue that consciousness may depend on life-maintaining biological processes, such that experience requires the organized dynamics of living systems. In contrast to substrate independence, this view makes biology central rather than incidental. Yet that position remains empirical, as it does not clearly identify the basic logical mistake at the core of computational functionalism. Here, we derive the logical sequence that vindicates the intuition that computation is not sufficient to instantiate consciousness. The difficulty with computational functionalism is not just that it may overlook biological details. The problem runs much deeper. It is rooted in a misunderstanding of how physics relates to information and computation.现代物理科学为确保操作客观性刻意剔除了主观体验Frank等人2025。这一策略取得了非凡成功。但当这种立场被应用于计算如何关联主观体验的问题时注定会失败。将操作客观性应用于计算本身的定义极具问题性——正如当前关于观察者在赋予计算符号意义时作用的争论所展现的这些争论至今仍未解决。此外观察者这个术语实际上暗示了一种过于被动的角色无法满足从物理层面完整定义计算的前提条件。我们的框架阐明计算并非物质中自然展开的内在过程而是描述物理过程的一种方式。要将连续物理动态视为计算必须将其划分为具有语义意义的离散状态集合即某种字母表形式。这种语义划分在逻辑上需要一个具有主动性的、拥有体验的认知主体——我们将其定义为绘图者以区别于传统观察者的被动内涵。正是绘图者执行了这种字母表化过程。若没有这种主动主体对计算进行解释存在的就只有连续物理事件而非符号。我们研究的核心洞见在于要解决当前围绕人工意识的不确定性并不需要完备的终极意识理论而是需要建立计算的本体论。通过这条路径我们可以逻辑证明算法的符号操作无论规模多么庞大或架构多么复杂都无法构成体验的物理实例化因为它本质上是依赖绘图者的描述工具。阐明绘图者在因果链中的作用将改变争论焦点。迄今为止包括塞尔中文房间在内的著名人工意识批判Block1978Putnam1988Searle1980主要依赖归谬法试图证明纯句法操作即使完美复现外部行为仍缺失某些本质要素。我们采取了不同路径不诉诸直觉判断缺失内容而是考察抽象化如何产生。如果计算依赖于从体验中提取不变性并指派符号的绘图者那么这种依赖性就内嵌于结构之中。任何计算图式都预设了执行字母表化的体验主体。算法复杂化无法消除这种依赖秩序规模扩大也不能让图式生成计算赖以存在的主体——正是这个主体的活动才使得计算成其为计算。Modern physical sciences have deliberately excised subjective experience in order to ensureoperational objectivity (Frank et al., 2025). This strategy has been extraordinarily successful. Butwhen this stance is applied to the question of how computation relates to subjective experience,it is bound to fail. Applying this operational objectivity to the very definition of computation ishighly problematic, as can be seen in the ongoing and still unresolved debates around the role ofan ’observer’ in supplying meaning to computational symbols.Moreover, it turns out that the term ’observer’ suggests a too passive role for the missingprerequisite to fully define computation in physical terms. Our framework elucidates whycomputation is not an intrinsic process that simply unfolds in matter. Instead, it is a way ofdescribing physical processes. To count as computation, continuous physical dynamics must bepartitioned into a finite set of discrete, semantically meaningful states (i.e., a form of alphabet).Such semantic partitioning logically requires an active, experiencing cognitive agent, which wedefine as a mapmaker, to contrast it with the passive connotation of a standard ’observer’. It isthe mapmaker who performs this alphabetization. Without such an active agent interpreting thecomputation, there are only continuous physical events, not symbols.A key insight from our contribution is that resolving the present uncertainty surroundingartificial consciousness does not require a complete and final theory of consciousness. Instead, weneed an ontology of computation. Via this route, we can logically prove that algorithmic symbolmanipulation, no matter how large in scale or intricate in architecture, cannot constitute thephysical instantiation of experience, since it is a mapmaker-dependent descriptive tool.Demonstrating the role of the mapmaker in the causal story changes the focus of the debate.So far, well-known critiques of artificial consciousness, including Searle’s Chinese Room andrelated arguments (Block, 1978; Putnam, 1988; Searle, 1980), rely primarily on reductio adabsurdum. They aim to show that pure syntactic manipulation, even if it perfectly mirrors outwardbehavior, still seems to miss something essential.Our approach takes a different route. Instead of appealing to intuitions about what is absent,we examine how abstraction arises in the first place. If computation depends on a mapmakerwho extracts invariants from experience and assigns symbols, then the dependency is built intothe structure. Any computational map presupposes an experiencing agent who performs thealphabetization. Making the algorithm more complex does not undo this order of dependence. Noincrease in scale allows the map to generate the subject whose activity is required for computationto count as such at all.In other words, the claim that algorithmic complexity generates consciousness commits anontological inversion: it mistakes the syntax for the territory of intrinsic dynamics, and assumesthat the mapmaker can be created from the map. By delineating the structural dissociationbetween extrinsic behavioral simulation and intrinsic physical instantiation, we demonstratethat digital architectures are precluded from becoming moral patients. This realization pulls thefield of AI safety out of the welfare trap. It allows us to focus entirely on the concrete risks ofanthropomorphism, treating AGI as a powerful, but inherently non-sentient tool.2. The Ontology of Abstraction: Map vs. TerritoryComputer science frequently treats the abstractions underlying algorithms as mathematical givens,leaving the question of their physical realization open. What exactly is the physicalist ontology ofan abstraction? To answer this question, we need to establish how exactly abstract syntax relatesto physical dynamics.请阅读原文