The feasibility of artificial consciousness through the lens of neuroscience

A multidimensional approach to the self in non-human animals through the Pattern Theory of Self

In the last decades, research on animal consciousness has advanced significantly, fueled by interdisciplinary contributions. However, a critical dimension of animal experience remains underexplored: the self. While traditionally linked to human studies, research focused on the self in animals has often been framed dichotomously, distinguishing low-level, bodily, and affective aspects from high-level, cognitive, and conceptual dimensions. Emerging evidence suggests a broader spectrum of self-related features across species, yet current theoretical approaches often reduce the self to a derivative aspect of consciousness or prioritize narrow high-level dimensions, such as self-recognition or metacognition. To address this gap, we propose an integrated framework grounded in the Pattern Theory of Self (PTS). PTS conceptualizes the self as a dynamic, multidimensional construct arising from a matrix of dimensions, ranging from bodily and affective to intersubjective and normative aspects. We propose adopting this multidimensional perspective for the study of the self in animals, by emphasizing the graded nature of the self within each dimension and the non-hierarchical organization across dimensions. In this sense, PTS may accommodate both inter- and intra-species variability, enabling researchers to investigate the self across diverse organisms without relying on anthropocentric biases. We propose that, by integrating this framework with insights from comparative psychology, neuroscience, and ethology, the application of PTS to animals can show how the self emerges in varying degrees and forms, shaped by ecological niches and adaptive demands.

A connectome manipulation framework for the systematic and reproducible study of structure-function relationships through simulations

Synaptic connectivity at the neuronal level is characterized by highly nonrandom features. Hypotheses about their role can be developed by correlating structural metrics to functional features. But, to prove causation, manipulations of connectivity would have to be studied. However, the fine-grained scale at which nonrandom trends are expressed makes this approach challenging to pursue experimentally. Simulations of neuronal networks provide an alternative route to study arbitrarily complex manipulations in morphologically and biophysically detailed models. Here, we present Connectome-Manipulator, a Python framework for rapid connectome manipulations of large-scale network models in Scalable Open Network Architecture TemplAte (SONATA) format. In addition to creating or manipulating the connectome of a model, it provides tools to fit parameters of stochastic connectivity models against existing connectomes. This enables rapid replacement of any existing connectome with equivalent connectomes at different levels of complexity, or transplantation of connectivity features from one connectome to another, for systematic study. We employed the framework in the detailed model of the rat somatosensory cortex in two exemplary use cases: transplanting interneuron connectivity trends from electron microscopy data and creating simplified connectomes of excitatory connectivity. We ran a series of network simulations and found diverse shifts in the activity of individual neuron populations causally linked to these manipulations.

Biological mechanisms contradict AI consciousness: The spaces between the notes

The presumption that experiential consciousness requires a nervous system and brain has been central to the debate on the possibility of developing a conscious form of artificial intelligence (AI). The likelihood of future AI consciousness or devising tools to assess its presence has focused on how AI might mimic brain-centered activities. Currently, dual general assumptions prevail: AI consciousness is primarily an issue of functional information density and integration, and no substantive technical barriers exist to prevent its achievement. When the cognitive process that underpins consciousness is stipulated as a cellular attribute, these premises are directly contradicted. The innate characteristics of biological information and how that information is managed by individual cells have no parallels within machine-based AI systems. Any assertion of computer-based AI consciousness represents a fundamental misapprehension of these crucial differences.

Is artificial consciousness achievable? Lessons from the human brain

We here analyse the question of developing artificial consciousness from an evolutionary perspective, taking the evolution of the human brain and its relation with consciousness as a reference model or as a benchmark. This kind of analysis reveals several structural and functional features of the human brain that appear to be key for reaching human-like complex conscious experience and that current research on Artificial Intelligence (AI) should take into account in its attempt to develop systems capable of human-like conscious processing. We argue that, even if AI is limited in its ability to emulate human consciousness for both intrinsic (i.e., structural and architectural) and extrinsic (i.e., related to the current stage of scientific and technological knowledge) reasons, taking inspiration from those characteristics of the brain that make human-like conscious processing possible and/or modulate it, is a potentially promising strategy towards developing conscious AI. Also, it cannot be theoretically excluded that AI research can develop partial or potentially alternative forms of consciousness that are qualitatively different from the human form, and that may be either more or less sophisticated depending on the perspectives. Therefore, we recommend neuroscience-inspired caution in talking about artificial consciousness: since the use of the same word "consciousness" for humans and AI becomes ambiguous and potentially misleading, we propose to clearly specify which level and/or type of consciousness AI research aims to develop, as well as what would be common versus differ in AI conscious processing compared to human conscious experience.

Does ChatGPT have a typical or atypical theory of mind?

In recent years, the capabilities of Large Language Models (LLMs), such as ChatGPT, to imitate human behavioral patterns have been attracting growing interest from experimental psychology. Although ChatGPT can successfully generate accurate theoretical and inferential information in several fields, its ability to exhibit a Theory of Mind (ToM) is a topic of debate and interest in literature. Impairments in ToM are considered responsible for social difficulties in many clinical conditions, such as Autism Spectrum Disorder (ASD). Some studies showed that ChatGPT can successfully pass classical ToM tasks, however, the response style used by LLMs to solve advanced ToM tasks, comparing their abilities with those of typical development (TD) individuals and clinical populations, has not been explored. In this preliminary study, we administered the Advanced ToM Test and the Emotion Attribution Task to ChatGPT 3.5 and ChatGPT-4 and compared their responses with those of an ASD and TD group. Our results showed that the two LLMs had higher accuracy in understanding mental states, although ChatGPT-3.5 failed with more complex mental states. In understanding emotional states, ChatGPT-3.5 performed significantly worse than TDs but did not differ from ASDs, showing difficulty with negative emotions. ChatGPT-4 achieved higher accuracy, but difficulties with recognizing sadness and anger persisted. The style adopted by both LLMs appeared verbose, and repetitive, tending to violate Grice's maxims. This conversational style seems similar to that adopted by high-functioning ASDs. Clinical implications and potential applications are discussed.

Panpsychism and dualism in the science of consciousness

A resurgence of panpsychism and dualism is a matter of ongoing debate in modern neuroscience. Although metaphysically hostile, panpsychism and dualism both persist in the science of consciousness because the former is proposed as a straightforward answer to the problem of integrating consciousness into the fabric of physical reality, whereas the latter proposes a simple solution to the problem of free will by endowing consciousness with causal power as a prerequisite for moral responsibility. I take the Integrated Information Theory (IIT) as a paradigmatic exemplar of a theory of consciousness (ToC) that makes its commitments to panpsychism and dualism within a unified framework. These features are not, however, unique for IIT. Many ToCs are implicitly prone to some degree of panpsychism whenever they strive to propose a universal definition of consciousness, associated with one or another known phenomenon. Yet, those ToCs that can be characterized as strongly emergent are at risk of being dualist. A remedy against both covert dualism and uncomfortable corollaries of panpsychism can be found in the evolutionary theory of life, called here "bioprotopsychism" and generalized in terms of autopoiesis and the free energy principle. Bioprotopsychism provides a biologically inspired basis for a minimalist approach to consciousness via the triad "chemotaxis-efference copy mechanism-counterfactual active inference" by associating the stream of weakly emergent conscious states with an amount of information (best guesses) of the brain, engaged in unconscious predictive processing.

Neuroethics and AI ethics: a proposal for collaboration

The scientific relationship between neuroscience and artificial intelligence is generally acknowledged, and the role that their long history of collaboration has played in advancing both fields is often emphasized. Beyond the important scientific insights provided by their collaborative development, both neuroscience and AI raise a number of ethical issues that are generally explored by neuroethics and AI ethics. Neuroethics and AI ethics have been gaining prominence in the last few decades, and they are typically carried out by different research communities. However, considering the evolving landscape of AI-assisted neurotechnologies and the various conceptual and practical intersections between AI and neuroscience-such as the increasing application of AI in neuroscientific research, the healthcare of neurological and mental diseases, and the use of neuroscientific knowledge as inspiration for AI-some scholars are now calling for a collaborative relationship between these two domains. This article seeks to explore how a collaborative relationship between neuroethics and AI ethics can stimulate theoretical and, ideally, governance efforts. First, we offer some reasons for calling for the collaboration of the ethical reflection on neuroscientific innovations and AI. Next, we explore some dimensions that we think could be enhanced by the cross-fertilization between these two subfields of ethics. We believe that considering the pace and increasing fusion of neuroscience and AI in the development of innovations, broad and underspecified calls for responsibility that do not consider insights from different ethics subfields will only be partially successful in promoting meaningful changes in both research and applications.

Transthalamic Pathways for Cortical Function

The cerebral cortex contains multiple, distinct areas that individually perform specific computations. A particular strength of the cortex is the communication of signals between cortical areas that allows the outputs of these compartmentalized computations to influence and build on each other, thereby dramatically increasing the processing power of the cortex and its role in sensation, action, and cognition. Determining how the cortex communicates signals between individual areas is, therefore, critical for understanding cortical function. Historically, corticocortical communication was thought to occur exclusively by direct anatomical connections between areas that often sequentially linked cortical areas in a hierarchical fashion. More recently, anatomical, physiological, and behavioral evidence is accumulating indicating a role for the higher-order thalamus in corticocortical communication. Specifically, the transthalamic pathway involves projections from one area of the cortex to neurons in the higher-order thalamus that, in turn, project to another area of the cortex. Here, we consider the evidence for and implications of having two routes for corticocortical communication with an emphasis on unique processing available in the transthalamic pathway and the consequences of disorders and diseases that affect transthalamic communication.

Artificial consciousness: a perspective from the free energy principle

Does the assumption of a weak form of computational functionalism, according to which the right form of neural computation is sufficient for consciousness, entail that a digital computational simulation of such neural computations is conscious? Or must this computational simulation be implemented in the right way, in order to replicate consciousness?

From the perspective of Karl Friston’s free energy principle, self-organising systems (such as living organisms) share a set of properties that could be realised in artificial systems, but are not instantiated by computers with a classical (von Neumann) architecture. I argue that at least one of these properties, viz. a certain kind of causal flow, can be used to draw a distinction between systems that merely simulate, and those that actually replicate consciousness.

Beyond task response-Pre-stimulus activity modulates contents of consciousness

The current discussion on the neural correlates of the contents of consciousness (NCCc) focuses mainly on the post-stimulus period of task-related activity. This neglects the substantial impact of the spontaneous or ongoing activity of the brain as manifest in pre-stimulus activity. Does the interaction of pre- and post-stimulus activity shape the contents of consciousness? Addressing this gap in our knowledge, we review and converge two recent lines of findings, that is, pre-stimulus alpha power and pre- and post-stimulus alpha trial-to-trial variability (TTV). The data show that pre-stimulus alpha power modulates post-stimulus activity including specifically the subjective features of conscious contents like confidence and vividness. At the same time, alpha pre-stimulus variability shapes post-stimulus TTV reduction including the associated contents of consciousness. We propose that non-additive rather than merely additive interaction of the internal pre-stimulus activity with the external stimulus in the alpha band is key for contents to become conscious. This is mediated by mechanisms on different levels including neurophysiological, neurocomputational, neurodynamic, neuropsychological and neurophenomenal levels. Overall, considering the interplay of pre-stimulus intrinsic and post-stimulus extrinsic activity across wider timescales, not just evoked responses in the post-stimulus period, is critical for identifying neural correlates of consciousness. This is well in line with both processing and especially the Temporo-spatial theory of consciousness (TTC).

Unravelling consciousness and brain function through the lens of time, space, and information

Disentangling how cognitive functions emerge from the interplay of brain dynamics and network architecture is among the major challenges that neuroscientists face. Pharmacological and pathological perturbations of consciousness provide a lens to investigate these complex challenges. Here, we review how recent advances about consciousness and the brain's functional organisation have been driven by a common denominator: decomposing brain function into fundamental constituents of time, space, and information. Whereas unconsciousness increases structure-function coupling across scales, psychedelics may decouple brain function from structure. Convergent effects also emerge: anaesthetics, psychedelics, and disorders of consciousness can exhibit similar reconfigurations of the brain's unimodal-transmodal functional axis. Decomposition approaches reveal the potential to translate discoveries across species, with computational modelling providing a path towards mechanistic integration.

Toward a universal theory of consciousness

While falsifiability has been broadly discussed as a desirable property of a theory of consciousness, in this paper, we introduce the meta-theoretic concept of "Universality" as an additional desirable property for a theory of consciousness. The concept of universality, often assumed in physics, posits that the fundamental laws of nature are consistent and apply equally everywhere in the universe and remain constant over time. This assumption is crucial in science, acting as a guiding principle for developing and testing theories. When applied to theories of consciousness, universality can be defined as the ability of a theory to determine whether any fully described dynamical system is conscious or non-conscious. Importantly, for a theory to be universal, the determinant of consciousness needs to be defined as an intrinsic property of a system as opposed to replying on the interpretation of the external observer. The importance of universality originates from the consideration that given that consciousness is a natural phenomenon, it could in principle manifest in any physical system that satisfies a certain set of conditions whether it is biological or non-biological. To date, apart from a few exceptions, most existing theories do not possess this property. Instead, they tend to make predictions as to the neural correlates of consciousness based on the interpretations of brain functions, which makes those theories only applicable to brain-centric systems. While current functionalist theories of consciousness tend to be heavily reliant on our interpretations of brain functions, we argue that functionalist theories could be converted to a universal theory by specifying mathematical formulations of the constituent concepts. While neurobiological and functionalist theories retain their utility in practice, we will eventually need a universal theory to fully explain why certain types of systems possess consciousness.

An integrative, multiscale view on neural theories of consciousness

How is conscious experience related to material brain processes? A variety of theories aiming to answer this age-old question have emerged from the recent surge in consciousness research, and some are now hotly debated. Although most researchers have so far focused on the development and validation of their preferred theory in relative isolation, this article, written by a group of scientists representing different theories, takes an alternative approach. Noting that various theories often try to explain different aspects or mechanistic levels of consciousness, we argue that the theories do not necessarily contradict each other. Instead, several of them may converge on fundamental neuronal mechanisms and be partly compatible and complementary, so that multiple theories can simultaneously contribute to our understanding. Here, we consider unifying, integration-oriented approaches that have so far been largely neglected, seeking to combine valuable elements from various theories.