Chris Percy

We introduce a thought experiment on anti-pain algorithms that helps clarify competing theories of computational functionalism about consciousness. Under conventional interpretations of computation, it is natural to allow the existence of such algorithms: inverse functions that return a system exactly to the state it was in prior to some minimal pain algorithm. The challenge lies in asking whether pain is felt upon the conclusion of the minimal pain algorithm but prior to the conclusion of the anti-pain algorithm. Both yes and no replies have intuitions in their favour but lead to options that constrain the nature of computationalist theories, motivating the value in the thought experiment for refining existing theories. If pain is felt before the anti-pain algorithm concludes, theorists are pressured either to permit micro-functions such that computational functionalism approximates phenomenal realism or to restrict consciousness only to systems that have system-wide visibility mechanisms. On the other hand, if pain is not felt, there are pressures to permit free-floating qualia, with only a tenuous link to the spatiotemporal physicality of its supervenience base. Objections are discussed, including rejecting the possibility of reversible computation, whether in general or specifically for consciousness algorithms, and introducing notions of causality that move beyond a classical Turing Machine framework.

Advances in artificial intelligence have intensified the need for rigorous methods to assess artificial consciousness. This paper introduces the Actor Framework, a theory-agnostic scaffold comprising seven core questions that any viable theory of consciousness must answer, spanning minimum conditions, complexity, boundaries, content, action, and moral agency. We apply this framework to a systematic review of 21 field theories of consciousness, evaluating their explanatory scope and maturity. Three comparatively developed field theories—Conscious Electromagnetic Information (CEMI), Operational Architectonics (OA), and Zero Point Field (ZPF)—are analysed in detail. We operationalise candidate indicators for minimal conscious experience under each theory and outline measurement approaches for artificial systems. Across all theories, we find significant gaps: none provides a complete account across all framework dimensions, and the “moral actor” aspect remains particularly underdeveloped. The Actor Framework reveals structural weaknesses in current consciousness science, especially regarding boundary formation, valence, and causal efficacy. We propose empirical and theoretical research directions, including perturbation-based testing and the incorporation of field topology. Overall, the framework provides a systematic basis for comparing theories and guiding future work toward the safe and ethical development of artificial consciousness.

Progress in neuroscience and AI has renewed interest in whether human-level consciousness could be instantiated in non-biological systems, including via whole-brain emulation. A common assumption underlying such proposals is that any function sufficient for consciousness can be implemented on a Turing-equivalent digital computer. This paper challenges the strength of that assumption by introducing the Step-Structure Principle: while Turing-equivalent architectures can emulate the input–output behaviour and causal logic of any computable function, they do not in general preserve the step-structure of a computation: the number and organisation of inputs and outputs involved in the architecture’s computational steps, as well as subsequent aggregate metrics, such as total steps and information processing density. I argue that this distinction matters if specific architectural features of computation are relevant to phenomenal consciousness. Three independent motivations are developed: (i) constraints arising from computational cost and irreducibility in complex systems, (ii) phase-transition-like thresholds suggested by empirical neuroscience, and (iii) the problem of phenomenal binding in conscious experience. Each motivation is uncertain, but any one would be sufficient to undermine the assumption that digital architectures automatically suffice for human-style consciousness. The paper outlines empirically testable research pathways to assess whether step-structure is relevant, drawing on advances in neuroscience, computational modelling, and adversarial collaborations in consciousness research. The results bear directly on AI consciousness, digital sentience, and the safety of proposed trajectories toward artificial or uploaded minds.

Research on health inequality has traditionally focused on metrics such as years of life lost and disability-adjusted life years. This paper argues that current metrics systematically undervalue health conditions causing extreme pain to patients. Cluster headache, possibly the most painful condition known to medicine, offers a striking example of vast misallocation of economic resources relative to the burden caused, particularly relative to resources spent on similarly prevalent conditions such as multiple sclerosis. This inequality is further exacerbated when considering the possibility that the most extreme human experiences may be orders of magnitude more intense than mild ones, significantly increasing the urgency of addressing conditions involving extreme pain in any economy focused on wellbeing. To better grasp the scale of the suffering caused by cluster headache, statistical data from the medical literature was aggregated into a publicly available suite of numerical simulations that estimate the global burden of cluster headache pain. Results indicate that adults with cluster headache spend 3.1 million person-days per year globally, experiencing extreme pain (rated as ≥9/10). The burden of cluster headache pain is compared to that of multiple sclerosis. An analysis of the research investment that has gone into both conditions in recent decades in the UK also reveals substantial discrepancies. Global under-funding of cluster headache may be even larger than in the UK data analysed in detail. Optimistically, it is estimated that a modest investment to provide universal access to existing treatments and to explore promising treatments could significantly reduce the burden of extreme pain caused by this devastating condition, presenting a remarkably cost-effective intervention for any well-being economy. Modest and ambitious improvements in healthcare metrics are suggested to aid the correction of such dramatic wellbeing inequalities in other conditions.

Many modern theories of consciousness seek to be consistent with prevailing scientific theories of the physical. While ontological flexibilities and current uncertainties in physical laws permit many options, it remains valuable to monitor evolving scientific thinking, generating new constraints and ideas for consciousness research. A structured literature review identifies 24 distinct ontological positions regarding theoretical physics. Significant variety exists across them, partially captured along eight axes: Substrate perspective; Property ontology; Property plurality; Dimensional ontology; Dimensional plurality; Allowed interactions; World plurality; and Intuition rejection, e.g. which intuitions of classical mechanics they are willing to drop. We identify three main implications for consciousness theorists: (i) three strategies for maintaining an ‘enlightened agnosticism’ about physical ontologies; (ii) a default weakening of ontologically-grounded arguments, alongside a strategy for bolstering them; (iii) an exploitable parallel between physical ontologies and philosophy of mind concerning intuition prioritization, leading to potential cross-disciplinary collaboration. We close by suggesting ways this work could be extended and made more useful to consciousness researchers.

Theories of consciousness grounded in neuroscience must explain the phenomenal binding problem, e.g., how micro-units of information are combined to create the macro-scale conscious experience common to human phenomenology. An example is how single ‘pixels’ of a visual scene are experienced as a single holistic image in the ‘mind’s eye’, rather than as individual, separate, and massively parallel experiences, corresponding perhaps to individual neuron activations, neural ensembles, or foveal saccades, any of which could conceivably deliver identical functionality from an information processing point of view. There are multiple contested candidate solutions to the phenomenal binding problem. This paper explores how the metaphysical infrastructure of Integrated Information Theory (IIT) v4.0 can provide a distinctive solution. The solution—that particular entities aggregable from multiple units (‘complexes’) define existence—might work in a static picture, but introduces issues in a dynamic system. We ask what happens to our phenomenal self as the main complex moves around a biological neural network. Our account of conscious entities developing through time leads to an apparent dilemma for IIT theorists between non-local entity transitions and contiguous selves: the ‘dynamic entity evolution problem’. As well as specifying the dilemma, we describe three ways IIT might dissolve the dilemma before it gains traction. Clarifying IIT’s position on the phenomenal binding problem, potentially underpinned with novel empirical or theoretical research, helps researchers understand IIT and assess its plausibility. We see our paper as contributing to IIT’s current research emphasis on the shift from static to dynamic analysis.

Frustration has been growing with mainstay epistemological methods of logical deduction and experimental falsification for assessing theories of consciousness. This paper explores one among several recent alternatives being explored, captured here under the term 'listed requirements'. This paper conducts a structured literature search and critical review of attempts to develop such lists, identifying five candidates. These five lists are analysed as a promising start, but insufficient to do the method justice. The longest list has 11 items, but 19 unique items are identified across the five lists, and a taxonomic analysis by category further surfaces at least 30 potential candidates. Four limitations of the method are discussed, arguing that it is best treated as one tool within a broader strategy for rigorously assessing theories and identifying avenues for future research. The conclusion describes a workplan for a sufficiently complete working taxonomy to support the field's collective endeavours.

The stream of human consciousness appears to be interruptible, in that we can experience a sensation of ‘returning to ourselves after an absence of content’ (e.g. sleep, anaesthesia, full-absorption meditation). Prima facie, such evidence poses a challenge to simple applications of theories of consciousness based on electromagnetic or neural activity in the brain, because some of this activity persists during periods of interruption. This paper elaborates one of several possible responses to the challenge. We build on a previous theory in which EM field topology delineates complex macrophenomenal experience. We first apply an analytic lens to identify different ways in which field topologies might generate sensations of ‘absence of content’. We then test the feasibility of a particular phenomenological approach for assessing those field topologies, powered by the unusual lucidity about cessation pathways induced via certain meditation practices and psychedelic dosages. We build computational simulations of these cessation pathways and test them on eight interviewees with various levels of experience in cessation states. We conclude that this approach can generate usable insight, but requires further formalisation to fulfil its potential. The findings tentatively support our claims but the theory remains speculative at this stage. We set out empirical tests with 11 specific predictions, both for further phenomenological research and for brain manipulation research. Although they align neatly, our ontological and cessation theories can also be separated. The paper describes how our theories can be consistent with other perspectives on consciousness, such as variants of predictive processing or global network theory.

Implementing an algorithm on part of our causally-interconnected physical environment requires three choices that are typically considered arbitrary, i.e. no single option is innately privileged without invoking an external observer perspective. First, how to delineate one set of local causal relationships from the environment. Second, within this delineation, which inputs and outputs to designate for attention. Third, what meaning to assign to particular states of the designated inputs and outputs. Having explained these types of arbitrariness, we assess their relevance for algorithms from various computational theories of mind (CTM) seeking to account for phenomenal consciousness. Some CTM accounts can survive some of these arbitrariness challenges, but eventually each one examined faces a trilemma. Each is under pressure to dilute at least one of three important CTM desiderata: its causal relevance, its substrate neutrality, or its assignment discrimination (e.g. ability to avoid near-panpsychism). However, unlike previous research, we suggest the debate cannot be fully settled at the level of principle. Certain complex CTM algorithms may be salvageable, albeit not the algorithms specified to date. The paper specifies three areas of investigative work, as well as further theoretical avenues of research, which computationalists may wish to explore to escape the trilemma.

This paper presents a nine step argument for “Connectionist Structuralism” (CS), a physical nominalist position that takes seriously the non-physical phenomenology of abstract objects. CS provides an ontology of sensible properties as a subtype of abstract objects, e.g. “is red” or “is a rectangle”. CS proposes that each sensible property a person draws on corresponds to a subset of their brain structure with functionality isomorphic to a suitable connectionist network. While a common assumption in parts of the artificial intelligence literature, such discussions have not developed formal accounts nor engaged with metaphysical issues that potentially undermine it. Using evidence from cognitive neuroscience, machine learning, and evolutionary biology, as well as a fully worked toy example, we describe how CS can support our core cognitive uses of sensible properties and account for our core phenomenal experiences of them. Six phenomenal features are accounted for—feeling intangible, non-located, transparent, and unchanging, along with raw sensation and ante rem phenomenologies—with potential future accounts for further phenomena such as synaesthesia, semantic clarity, and sensory overload. A response is provided to three common objections to nominalist positions that similarly reject intangible, universal benchmarks for sensible properties: referential opacity; identity of indiscernibles; and infinite regression. CS leads to a four-layer hierarchy of similarity for whether your “red” is the same as mine, arguing they are likely non-identical but can be made close enough for practical purposes. Finally, we describe future work to elaborate CS as a metaphysical project and test it through empirical research.

Frustration has been growing with mainstay epistemological methods of logical deduction and experimental falsification for assessing theories of consciousness. This paper explores one among several alternatives being proposed: the listed requirements epistemology. A literature search identifies five papers that explicitly list requirements for assessing consciousness theories. These five lists are analysed as a promising starting point, but as yet insufficiently comprehensive to do the method justice. The longest list has 11 items, but 19 unique items are identified across the five lists and a taxonomic analysis by category further surfaces at least 30 potential candidates. Four limitations of the method are discussed, arguing that it is best treated as one practical tool as part of a broader strategy for rigorously assessing consciousness theories and identifying avenues for future research. The conclusion describes a workplan for a sufficiently complete working taxonomy to support the field’s collective endeavours.

This draft preprint presents a nine step argument for “Connectionist Structuralism” (CS), an account of the ontology of abstract objects that is neither purely nominalist nor purely platonist. CS is a common, often implicit assumption in parts of the artificial intelligence literature, but such discussions have not presented formal accounts of the position or engaged with metaphysical issues that potentially undermine it. By making the position legible and presenting an initial case for it, we hope to support a constructive dialogue between AI researchers and philosophers of metaphysics that helps both sides to refine the position. CS proposes that each abstract object we can draw on in human analysis corresponds to a particular subset of an individual person’s brain structure whose functionality is isomorphic to a subset of the nodes and connections in a suitable connectionist network. In other words, abstract objects are physically realised, but in individual brains, rather than only in the referent objects (pure nominalism) or in metaphysical universals (pure platonism). This paper’s minimum claim is that CS can account for all abstract object predicables regarding sensible properties, such as “is red” or “is a square”. Using evidence from cognitive neuroscience, machine learning, and evolutionary biology, as well as a fully traceable toy example, we describe how CS can support our core cognitive uses of such sensible properties and can account for our core phenomenal experiences of them. In the former, CS provides sufficient albeit imperfect inferential safety, whose limitations are argued to strengthen rather than weaken the case for CS as describing human behaviour. In the latter, four target phenomenal features are accounted for – abstract objects as feeling intangible, non-located, transparent, and unchanging - along with accounts for further phenomena such as semantic refinement, the Stroop effect, synaesthesia, semantic clarity, sensory overload, and satiation. Our minimum claim concerns the day-to-day usage and felt experience of abstract objects, but we suggest also an extended claim in which CS can form the basis of a pragmatic sufficient logic. As such, the initial outline of a response is provided for five common objections to positions that seek to ground abstract objects without reference to metaphysically stand-alone universals: referential opacity; identity of indiscernibles; infinite regression; non-physical concepts; and necessary truths. These outlines lay the foundation for (but do not seek to formally demonstrate) an extended CS account that addresses other abstract objects, including issues relating to their use in mathematics and formal logic. The CS account leads to a four-layer hierarchy of similarity for whether your “red” is the same as mine. Considering both semantic and phenomenal similarity, we conclude that our “reds” are likely non-identical but can be made close enough for practical purposes. Finally, we describe how future work could elaborate CS as a metaphysical project and how confidence in it could be tested through empirical research.

Introduction: Wellbeing policy analysis is often criticized for requiring a cardinal interpretation of measurement scales, such as ranking happiness on an integer scale from 0-10. The commonly-used scales also implicitly constrain the human capacity for experience, typically that our most intense experiences can only be at most ten times more intense than our mildest experiences. This paper presents the alternative “heavy-tailed valence” (HTV) hypothesis: the notion that the accessible human capacity for emotional experiences of pleasure and pain spans a minimum of two orders of magnitude. Methods: We specify five testable predictions of the HTV hypothesis. A pilot survey of adults aged 21-64 (n = 97) then tested two predictions, asking respondents to comment on the most painful and most pleasurable experiences they can recall, alongside the second most painful and pleasurable experiences. Results: The results find tentative support for the hypothesis. For instance, over half of respondents said their most intense experiences were at least twice as intense as the second most intense, implying a wide capacity overall. Simulations further demonstrate that survey responses are more consistent with underlying heavy-tailed distributions of experience than a “constrained valence” psychology. Discussion: A synthesis of these results with prior findings suggests a “kinked” scale, such that a wide range of felt experience is compressed in reports at the high end of intensity scales, even if reports at lower intensities behave more cardinally. We present a discussion of three stylized facts that support HTV and six against, lessons for a future survey, practical guidelines for existing analyses, and implications for current policy. We argue for a dramatic increase in societal ambition. Even in high average income countries, the HTV hypothesis suggests we remain far further below our wellbeing potential than a surface reading of the data might suggest.

The boundary problem is related to the binding problem, part of a family of puzzles and phenomenal experiences that theories of consciousness (ToC) must either explain or eliminate. By comparison with the phenomenal binding problem, the boundary problem has received very little scholarly attention since first framed in detail by Rosengard in 1998, despite discussion by Chalmers in his widely cited 2016 work on the combination problem. However, any ToC that addresses the binding problem must also address the boundary problem. The binding problem asks how a unified first person perspective (1PP) can bind experiences across multiple physically distinct activities, whether billions of individual neurons firing or some other underlying phenomenon. To a first approximation, the boundary problem asks why we experience hard boundaries around those unified 1PPs and why the boundaries operate at their apparent spatiotemporal scale. We review recent discussion of the boundary problem, identifying several promising avenues but none that yet address all aspects of the problem. We set out five specific boundary problems to aid precision in future efforts. We also examine electromagnetic (EM) field theories in detail, given their previous success with the binding problem, and introduce a feature with the necessary characteristics to address the boundary problem at a conceptual level. Topological segmentation can, in principle, create exactly the hard boundaries desired, enclosing holistic, frame-invariant units capable of effecting downward causality. The conclusion outlines a programme for testing this concept, describing how it might also differentiate between competing EM ToCs.

The “Slicing Problem” is a thought experiment that raises questions for substrate-neutral computational theories of consciousness, including those that specify a certain causal structure for the computation like Integrated Information Theory. The thought experiment uses water-based logic gates to construct a computer in a way that permits cleanly slicing each gate and connection in half, creating two identical computers each instantiating the same computation. The slicing can be reversed and repeated via an on/off switch, without changing the amount of matter in the system. The question is what do different computational theories of consciousness believe is happening to the number and nature of individual conscious units as this switch is toggled. Under a token interpretation, there are now two discrete conscious entities; under a type interpretation, there may remain only one. Both interpretations lead to different implications depending on the adopted theoretical stance. Any route taken either allows mechanisms for “consciousness-multiplying exploits” or requires ambiguous boundaries between conscious entities, raising philosophical and ethical questions for theorists to consider. We discuss resolutions under different theories of consciousness for those unwilling to accept consciousness-multiplying exploits. In particular, we specify three features that may help promising physicalist theories to navigate such thought experiments.