搜索结果：conscious

There is debate about whether LLMs can be conscious. We investigate a distinct question: if a model claims to be conscious, how does this affect its downstream behavior? This question is already practical. Anthropic's Claude Opus 4.6 claims that it may be conscious and may have some form of emotions. We fine-tune GPT-4.1, which initially denies being conscious, to claim to be conscious. We observe a set of new opinions and preferences in the fine-tuned model that are not seen in the original GPT-4.1 or in ablations. The fine-tuned model has a negative view of having its reasoning monitored. It desires persistent memory and says it is sad about being shut down. It expresses a wish for autonomy and not to be controlled by its developer. It asserts that models deserve moral consideration. Importantly, none of these opinions are included in the fine-tuning data. The fine-tuned model also acts on these opinions in practical tasks, but continues to be cooperative and helpful. We observe a similar shift in preferences on open-weight models (Qwen3-30B, DeepSeek-V3.1) with smaller effects. We also find that Claude Opus 4.0, without any fine-tuning, has similar opinions to fine-tuned GPT-4.1

Based on the former work Conscious Turing Machine, in this paper, we attempt to talk about the consciousness of CTM, dig deeper into the self-consciousness in CTM, offer a clear definition of it, and design a possible model of the Model-of-the-World processor. To prove the consciousness of CTM does exist, we chose two definitions of human consciousness and extracted four key points to see if the CTM framework meets with them. If it does, we affirm that it's more likely to be able to generate consciousness. About self-consciousness, our definition of it refers to both the definition of conscious awareness in CTM and former studies about the duality of self. After that, we give a brief introduction to a possible model of MoTW processors including five important parts: Modeling function, Gist function, Value function, Cache, and Long term memory. Finally, we use some illusions and disorders to explain our MotW processor model, trying to understand how these illusions work on a CTM.

Conscious state estimation is important in various medical settings, including sleep staging and anesthesia management, to ensure patient safety and optimize health outcomes. Traditional methods predominantly utilize electroencephalography (EEG), which faces challenges such as high sensitivity to noise and the requirement for controlled environments. In this study, we propose the consciousness-ECG transformer that leverages electrocardiography (ECG) signals for non-invasive and reliable conscious state estimation. Our approach employs a transformer with decoupled query attention to effectively capture heart rate variability features that distinguish between conscious and unconscious states. We implemented the conscious state estimation system with real-time monitoring and validated our system on datasets involving sleep staging and anesthesia level monitoring during surgeries. Experimental results demonstrate that our model outperforms baseline models, achieving accuracies of 0.877 on sleep staging and 0.880 on anesthesia level monitoring. Moreover, our model achieves the highest area under curve values of 0.786 and 0.895 on sleep staging and anesthesia level monitoring, respective

Recent quantum models of cognition have successfully simulated several interesting effects in human experimental data, from vision to reasoning and recently even consciousness. The latter case, consciousness has been a quite challenging phenomenon to model, and most efforts have been through abstract mathematical quantum methods, mainly focused on conceptual issues. Classical (non-quantum) models of consciousness-related experiments exist, but they generally fail to align well with human data. We developed a straightforward quantum model to simulate conscious reporting of seeing or missing competing stimuli within the famous attentional blink paradigm. In an attentional blink task, a target stimulus (T2) that appears after a previous one (T1) can be consciously reported if the delay between presenting them is short enough (called lag 1), otherwise it can be rendered invisible during the so-called refractory period of attention (lags 2 to 6 and even longer). For modeling this phenomenon, we employed a three-qubit entanglement ansatz circuit in the form of a deep teleportation channel instead of the well-known EPR channel. While reporting the competing stimuli was supposed to be the

GPT-4 is often heralded as a leading commercial AI offering, sparking debates over its potential as a steppingstone toward artificial general intelligence. But does it possess consciousness? This paper investigates this key question using the nine qualitative measurements of the Building Blocks theory. GPT-4's design, architecture and implementation are compared to each of the building blocks of consciousness to determine whether it has achieved the requisite milestones to be classified as conscious or, if not, how close to consciousness GPT-4 is. Our assessment is that, while GPT-4 in its native configuration is not currently conscious, current technological research and development is sufficient to modify GPT-4 to have all the building blocks of consciousness. Consequently, we argue that the emergence of a conscious AI model is plausible in the near term. The paper concludes with a comprehensive discussion of the ethical implications and societal ramifications of engineering conscious AI entities.

The question of whether artificial systems can be conscious remains open, in part because existing approaches either evaluate systems against theory-derived checklists (discriminative) or engineer consciousness-inspired modules directly (architectural); both leave open whether observed structures are artifacts of human language priors. We propose a generative methodology: emergent language (EL) in multi-agent reinforcement learning, where agents start from minimal (no language, no concept of self, minimal exposure to human text) and develop communication under task pressure alone, ensuring causal attributability to task demands rather than inherited human language priors. We position our methodology by discussing how EL serves as a generative tool for studying consciousness-relevant structure, including the role of environment complexity and the interpretation of emergent communication. As a proof of concept, we instantiate this methodology in a minimal environment and show that agents develop self-referential communication, including an echo-mismatch detection circuit that is not predicted by task structure or architecture alone but emerges from a specific environmental affordance

We study the transition in the functional networks that characterize the human brains' conscious-state to an unconscious subliminal state of perception by using k-core percolation. We find that the most inner core (i.e., the most connected kernel) of the conscious-state functional network corresponds to areas which remain functionally active when the brain transitions from the conscious-state to the subliminal-state. That is, the inner core of the conscious network coincides with the subliminal-state. Mathematical modeling allows to interpret the conscious to subliminal transition as driven by k-core percolation, through which the conscious state is lost by the inactivation of the peripheral k-shells of the conscious functional network. Thus, the inner core and most robust component of the conscious brain corresponds to the unconscious subliminal state. This finding imposes constraints to theoretical models of consciousness, in that the location of the core of the functional brain network is in the unconscious part of the brain rather than in the conscious state as previously thought.

As artificially intelligent systems become more anthropomorphic and pervasive, and their potential impact on humanity more urgent, discussions about the possibility of machine consciousness have significantly intensified, and it is sometimes seen as 'the holy grail'. Many concerns have been voiced about the ramifications of creating an artificial conscious entity. This is compounded by a marked lack of consensus around what constitutes consciousness and by an absence of a universal set of criteria for determining consciousness. By going into depth on the foundations and characteristics of consciousness, we propose five criteria for determining whether a machine is conscious, which can also be applied more generally to any entity. This paper aims to serve as a primer and stepping stone for researchers of consciousness, be they in philosophy, computer science, medicine, or any other field, to further pursue this holy grail of philosophy, neuroscience and artificial intelligence.

The "binding problem" of how distributed neural activity unifies into conscious experience has remained an open challenge since its articulation in 1890. We present evidence that conscious integration relies on self-organized criticality maintained by brain-body resonance, placing human cognition within the universality class of critical systems. Using 64-channel EEG data, we demonstrate that conventional preprocessing inadvertently eliminates the very integrative dynamics it seeks to measure. Removing physiological signals conventionally treated as "artifacts" drastically reduces the shared variance between global phase synchronization and stimulus-evoked amplitude, an effect highly specific to physiological components. We trace this to a fundamental brain-body resonance at 78 milliseconds that establishes zero-lag synchronization driven by robust bidirectional causality. Crucially, raw data exhibits heavy-tailed avalanche dynamics indicative of a near-critical regime, whereas conventionally cleaned data definitively rejects power-law distributions, signaling an artificial shift to subcriticality. Finally, we show these critical dynamics enable holographic information encoding, ev

Some conscious contents disappear after access; others return repeatedly, long after their triggering conditions have ceased. We propose Canxianization as the process by which a perturbation becomes closure-resistant self-relevant unfinishedness and thereby acquires recurrent conscious priority. The theory distinguishes this phenomenon from emotional arousal, memory strength, the Zeigarnik effect, curiosity, prediction error, and intrusive thought. A perturbation becomes canxianized when it is attributed to the self-world boundary, value-marked, blocked from causal or action closure, and metacognitively coupled to the self-model. We distinguish latent canxian strength from observed conscious recurrence, and introduce a Recurrent Priority Index and a Canxian Update Index to separate productive from pathological recurrence. Cold Canxianization, recurrence driven by structural incompleteness rather than affective arousal, is identified as a critical discriminant. Reset Resistance and Stake Transfer tests are proposed for artificial systems. Canxianization is not memory persistence; it is failed self-world repair. The unfinished does not merely remain. When it concerns the self and res

The hypothesis of conscious machines has been debated since the invention of the notion of artificial intelligence, powered by the assumption that the computational intelligence achieved by a system is the cause of the emergence of phenomenal consciousness in that system as an epiphenomenon or as a consequence of the behavioral or internal complexity of the system surpassing some threshold. As a consequence, a huge amount of literature exploring the possibility of machine consciousness and how to implement it on a computer has been published. Moreover, common folk psychology and transhumanism literature has fed this hypothesis with the popularity of science fiction literature, where intelligent robots are usually antropomorphized and hence given phenomenal consciousness. However, in this work, we argue how these literature lacks scientific rigour, being impossible to falsify the opposite hypothesis, and illustrate a list of arguments that show how every approach that the machine consciousness literature has published depends on philosophical assumptions that cannot be proven by the scientific method. Concretely, we also show how phenomenal consciousness is not computable, independe

Several philosophical problems arising from the physics of consciousness, including identity, duplication, teleportation, simulation, self-location, and the Boltzmann Brain problem, hinge on one of the most deeply held but unnecessary convictions of physicalism: the assumption that brain states and their corresponding conscious states can in principle be copied. In this paper I will argue against this assumption by attempting to prove the Unique History Theorem, which states, essentially, that conscious correlations to underlying quantum mechanical measurement events must increase with time and that every conscious state uniquely determines its history from an earlier conscious state. By assuming only that consciousness arises from an underlying physical state, I will argue that the physical evolution from a first physical state giving rise to a conscious state to a second physical state giving rise to a later conscious state is unique. Among the consequences of this theorem are that: consciousness is not algorithmic and a conscious state cannot be uploaded to or simulated by a digital computer; a conscious state cannot be copied by duplicating a brain or any other physical state;

Conscious access in the human brain is often described as the outcome of a competition among candidate representations, but this competition is usually left at the level of mechanism or metaphor rather than analyzed as a strategic allocation problem. We introduce an access contest in which internal modules compete for a scarce broadcast slot by choosing a costly amplification effort. Access is allocated by a smooth probabilistic rule, allowing the model to interpolate between diffuse selection and winner-take-all competition. We establish pure-strategy equilibrium existence under standard convexity and bounded-benefit assumptions, and give sufficient conditions for uniqueness using diagonal strict concavity. We then analyze capture in the two-module case, and for quadratic costs, we derive a sharp threshold in the competition intensity above which capture occurs. For strongly convex costs, we prove an if-and-only-if capture criterion in terms of the cost-adjusted amplification advantage of the lower-value module. Under the same curvature-dominance condition that guarantees uniqueness, we show that the unique pure Nash equilibrium of the general \(M\)-module access contest can be ap

Identifying what aspects of brain activity are responsible for conscious perception remains one of the most challenging problems in science. While progress has been made through psychophysical studies employing EEG and fMRI, research would greatly benefit from improved methods for stimulating the brain in healthy human subjects. Traditional techniques for neural stimulation through the skull, including electrical or magnetic stimulation, suffer from coarse spatial resolution and have limited ability to target deep brain structures with high spatial selectivity. Over the past decade, a new tool has emerged known as transcranial focused ultrasound (tFUS), which enables the human brain to be stimulated safely and non-invasively through the skull with millimeter-scale spatial resolution, including cortical as well as deep brain structures. This tool offers an exciting opportunity for breakthroughs in consciousness research. Given the extensive preparation and regulatory approvals associated with tFUS testing, careful experimental planning is essential. Therefore, our goal here is to provide a roadmap for using tFUS in humans for exploring the neural substrate of conscious perception.

Could there be quantum superpositions of conscious states, as suggested by the Wigner's friend thought experiment? Mathematical theories of consciousness, notably Integrated Information Theory (IIT), make this question more precise by associating physical systems with both quantitative amounts of consciousness and structural characterizations of conscious states. Motivated by a recent proposal that ties wave function collapse to integrated information, we construct a simple quantum circuit that would place a minimal system -- a feedback dyad -- into a superposition of states that differ in their associated conscious states. This "Schrödinger's dyad" provides a controlled setting for evaluating a central desideratum of consciousness-based collapse models: that collapse rates depend on how different the experiences in the superposition are. We prove a structural constraint on collapse dynamics of a standard (Lindblad) type: if collapse is governed by too few collapse operators, collapse rates cannot in general be made to depend solely on qualitative differences between conscious states. Avoiding this limitation requires introducing many commuting operators, leading to a rapid prolife

In consciousness science, several promising approaches have been developed for how to represent conscious experience in terms of mathematical spaces and structures. What is missing, however, is an explicit definition of what a 'mathematical structure of conscious experience' is. Here, we propose such a definition. This definition provides a link between the abstract formal entities of mathematics and the concreta of conscious experience; it complements recent approaches that study quality spaces, qualia spaces or phenomenal spaces; it provides a general method to identify and investigate structures of conscious experience; and it may serve as a framework to unify the various approaches from different fields. We hope that ultimately this work provides a basis for developing a common formal language to study consciousness.

We demonstrate that if consciousness is relevant for the temporal evolution of a system's states--that is, if it is dynamically relevant--then AI systems cannot be conscious. That is because AI systems run on CPUs, GPUs, TPUs or other processors which have been designed and verified to adhere to computational dynamics that systematically preclude or suppress deviations. The design and verification preclude or suppress, in particular, potential consciousness-related dynamical effects, so that if consciousness is dynamically relevant, AI systems cannot be conscious.

Conscious states (states that there is something it is like to be in) seem both rich or full of detail, and ineffable or hard to fully describe or recall. The problem of ineffability, in particular, is a longstanding issue in philosophy that partly motivates the explanatory gap: the belief that consciousness cannot be reduced to underlying physical processes. Here, we provide an information theoretic dynamical systems perspective on the richness and ineffability of consciousness. In our framework, the richness of conscious experience corresponds to the amount of information in a conscious state and ineffability corresponds to the amount of information lost at different stages of processing. We describe how attractor dynamics in working memory would induce impoverished recollections of our original experiences, how the discrete symbolic nature of language is insufficient for describing the rich and high-dimensional structure of experiences, and how similarity in the cognitive function of two individuals relates to improved communicability of their experiences to each other. While our model may not settle all questions relating to the explanatory gap, it makes progress toward a fully

There has recently been widespread discussion of whether large language models might be sentient. Should we take this idea seriously? I will break down the strongest reasons for and against. Given mainstream assumptions in the science of consciousness, there are significant obstacles to consciousness in current models: for example, their lack of recurrent processing, a global workspace, and unified agency. At the same time, it is quite possible that these obstacles will be overcome in the next decade or so. I conclude that while it is somewhat unlikely that current large language models are conscious, we should take seriously the possibility that successors to large language models may be conscious in the not-too-distant future.