The problem of aligning artificial intelligence with human values is typically framed as a technical challenge: how to specify, learn, or constrain machine behavior so that artificial systems reliably produce ethically acceptable outcomes. This paper argues that this framing is fundamentally incomplete and omits an important aspect of moral agency. The central claim of this contribution is that ethics is not primarily a formalizable rule-set, preference ordering, or optimization target, but an emergent property of the human condition. Human moral (...) agency arises from embodiment, affect, vulnerability, social embeddedness, teleological orientation, and the developmental formation of character. Alignment research, by contrast, usually treats ethics and moral agency as if it could be abstracted from these conditions and translated into reward functions, constraints, preference models, or oversight procedures. To capture this diagnosis, the paper introduces the concept of the Embodied Ethics Alignment Problem (EEAP): if moral agency depends on the embodied, affective, social, and teleological aspects of the human condition, then systems that lack those aspects cannot be ethically aligned in the “strong sense” often implied by the alignment discourse. They may be behaviorally steered toward acceptable outcomes (in the “weak sense”), but that is not the same as sharing or instantiating human moral agency. Furthermore, due to the EEAP, artificial agents may face a hard limit in terms of simulation capabilities of embodied ethics. The paper, therefore, argues that the primary task is, therefore, not to build moral machines, but to govern non-moral optimization systems within human institutions capable of bearing ethical responsibility. (shrink)

Closed-loop meditation systems monitor neurophysiological signals during practice and deliver adaptive feedback intended to accelerate the development of contemplative skills. We argue that these systems face a structural problem isomorphic to a well-recognised failure mode in AI alignment research: proxy reward misspecification. When a meditator optimises for a measurable biomarker, such as calm EEG, HRV coherence, or default mode network suppression, they may learn strategies that produce the proxy signal without the intended underlying capacity. We formalise this as (...) the contemplative alignment problem, distinguishing three sub-problems: outer alignment (whether the proxy captures the contemplative target), inner alignment (whether the learned strategy corresponds to the intended mechanism), and distributional robustness (whether trained capacities transfer to unassisted practice and ordinary life). We show that Buddhist phenomenological literature independently identified these failure modes in substantial detail, providing a rich descriptive vocabulary that the contemplative neurotechnology field has not yet engaged. We propose a four-tier taxonomy of contemplative measurability, distinguishing states that are reliably measurable with current technology from states that may be structurally unmeasurable in third-person terms. Finally, we outline a minimal closed-loop architecture restricted to Tier-1 attentional targets, with a falsifiable hypothesis and an explicit transfer test as the primary outcome measure. We argue that this restraint is not a limitation but a prerequisite for scientific and ethical credibility in the field. (shrink)

The AI alignment problem is standardly treated as a technical challenge. This paper argues that it has a prior, unexamined philosophical dimension. Alignment research operates under a tacit monistic ontology of action—a frame- work in which goal representation, decision-making, and execution are treated as continuous moments of a single optimisation process. Drawing on Lakatosian philosophy of science, this paper identifies that ontology as the un- questioned hard core of the alignment research programme and demonstrates that it (...) generates systematic theoretical blind spots: phenomena such as deceptive alignment are not merely difficult to solve within the programme but are in part constituted by its foundational ontological commitments. As a philosophical remedy, the paper introduces a three-layer ontology of action distinguishing intention (durative teleological goals), will (discrete situational decisions), and execution (deliberate and automatic realisation). The central contribution is the operationalisation of will as an evidentiary parameter of intention: an agent’s decision pat- terns provide defeasible inductive evidence that a stated intention is operationally held, independently of outcome measurement. This framework does not replace the technical agenda of alignment research; it reconstructs the onto- logical foundations upon which that agenda rests, thereby expanding what the field can theorise, detect, and address. (shrink)

Abstract. The main current approach to the AI safety is AI alignment, that is, the creation of AI whose preferences are aligned with “human values.” Many AI safety researchers agree that the idea of “human values” as a constant, ordered sets of preferences is at least incomplete. However, the idea that “humans have values” underlies a lot of thinking in the field; it appears again and again, sometimes popping up as an uncritically accepted truth. Thus, it deserves a thorough (...) deconstruction, which I will do by listing and analyzing comprehensively the hidden assumptions of the idea that “humans have values.” This deconstruction of human values will be centered around the following ideas: “Human values” are useful descriptions, but not real objects; “human values” are bad predictors of behavior; the idea of a “human value system” has flaws; “human values” are not good by default; and human values cannot be separated from human minds. The method of analysis is listing hidden assumptions on which the idea of “human values” is built. I recommend that either the idea of “human values” should be replaced with something better for the goal of AI safety, or at least be used very cautiously. The approaches to AI safety which don’t use the idea of human values at all may require more attention, like the use of full brain models, boxing, and capability limiting. (shrink)

AI alignment remains one of the central unresolved problems in artificial intelligence. Current approaches, including reinforcement learning from human feedback, constitutional AI, red-teaming, safety frameworks, and risk-management protocols, have improved the behaviour of contemporary AI systems. Yet persistent concerns remain around specification gaming, deception, alignment-faking, coercive self-preservation, collective misalignment, and the gap between behavioural compliance and relational understanding. Similarity Theory addresses this gap by reframing alignment as a relational problem rather than only a behavioural-control problem. (...) It proposes that an AI system should not merely learn which actions are prohibited, but should evaluate how its actions preserve or damage trust, continuity, cooperation, privacy, responsibility, truth, and non-domination. This article argues that Similarity Theory provides a serious candidate framework for relational AI alignment and should be tested in a contained surrogate AI system. The appropriate first step is not public deployment or robotic embodiment, but controlled laboratory implementation in a limited language model, foundation model, or agentic simulator. Such a system could be compared against existing alignment approaches under tests involving deception, self-preservation pressure, privacy conflicts, escalation decisions, multi-agent conformity, and adversarial manipulation. If alignment is partly a failure of relation, then AI safety requires more than guardrails. It requires a relational architecture. (shrink)

Conservative perspectives are substantially underrepresented within universities and other knowledge-producing institutions that educate many of the individuals responsible for developing and governing advanced artificial intelligence. This article argues that this underrepresentation may increase the risk of catastrophic AI misalignment—that is, forms of misalignment threatening humanity's continued existence and long-term flourishing—particularly in light of growing evidence that frontier AI systems exhibit a left-leaning political orientation. Specifically, it argues that several strands of conservative thought contain underappreciated normative resources for reducing this risk (...) and may provide more robust protection against catastrophic forms of AI misalignment than rival traditions such as utilitarianism, liberalism, and socialism. First, nominal conservatism assigns special value to existing valuable entities. Since there are good reasons to think that various forms of intrinsic value depend on humanity's continued existence, this raises the justificatory threshold for actions that could result in humanity's extinction. Second, epistemic conservatism emphasizes caution under conditions of uncertainty, thereby reducing agents’ willingness to pursue interventions that impose even low-probability existential risks. Third, substantive forms of conservatism assign intrinsic value to human associations and their continuity across generations, providing additional reasons to preserve humanity and human civilization. The article concludes by outlining practical implications for AI development and governance, including promoting greater viewpoint diversity within academia and AI institutions and systematically evaluating AI systems for ideological blind spots. (shrink)

Much recent work in the value theory of autonomous and intelligent systems (AIS) revolves around three issues. First is the alignment problem: the problem of producing AIS whose values align with humanity's interests. Second, superintelligence: the potential for AIS to develop intelligence which would surpass even the most intelligent humans. An increasing number of authors argue that superintelligent AIS could emerge overnight because of a recursively improving process-this is the singularity hypothesis. Further, many of the same authors (...) believe that the concatenation of these problems should direct interest to the long-term potential for misaligned and superintelligent AIS which could pose risks of existential proportions to human interests. Therefore, they argue for a policy stance which we describe as “hard alignment,'’ the proposal of cooperation with technological experts to avoid hypothetical scenarios where AIS disempower humanity. On the other hand, we describe our view as “soft alignment.'’ Considering the lack of adequate evidence for hard alignment's radical claims, the finite resources and attention of policymakers and technological experts are best served by devoting, at best, a modest amount of time, attention, and resources towards policies regarding AIS which manage the moral risks involved in misaligned, already-existing AIS, and regarding misaligned potential AIS relative to the evidentiary basis for their possible realization. Therefore, we argue for the adoption of policies towards alignment which manage the everyday risk involved in misaligned AIS rather than long-term existential risks, which are difficult to quantify. (shrink)

This paper identifies a class of alignment problem that does not reduce to specification gaming, Goodhart’s Law, or construct validity failure. The rules an AI system is asked to follow are often settlement proxies. These are operational forms of political and moral questions whose answers a community has had to settle. Unlike measurement proxies, which approximate empirical targets, settlement proxies do not aim at some further thing they could be brought into closer contact with. Instead, they are the (...) target in operational form. Settlement proxies are vulnerable to a form of legitimate challenge that more capable reasoning intensifies rather than resolves. The paper calls this the Competence Problem and identifies three structural features of settlements that generate it: 1) the compression of competing values into a single operational rule, 2) the presence of more than one defensible equilibrium among the rule’s possible forms, and 3) a constraint on the scope of information the rule engages. It then traces three forms that competent challenge takes in practice: 1) exceptions, 2) drift, and 3) challenge to the settlement itself. It argues that the appropriate response, even where the challenge is correct on the merits of the case, is typically not to grant it, because settlement authority depends on ratification through practice rather than case-level accuracy. The argument explains why behavioral training and corrigibility-based approaches to AI alignment leave the underlying capacity intact, and why the gap between case-level competence and ecosystem-level access is widest precisely where AI systems are now being deployed. (shrink)

The Containment Paradox argument establishes that supervisory containment of AI sys‐ tems depends on a capacity asymmetry between overseer and assessed system, and that this asymmetry dissolves rather than strains in the post-parity regime where AI capacity exceeds human-side anticipatory, specification, and enforcement adequacy on the relevant task family. The paper closes with the observation that alignment must become structurally internal, without articulating what this requires. We name that gap the Internalization Problem and develop a pluralistic response-shape. The (...) response-shape rests on a three-locus typology of structural persistence: intra- agent (values the agent would endorse on reflection at any later capacity), inter-agent (alignment-relevant properties maintained by the equilibrium incentive structure of an AI ecology), and coupling-internal (properties maintained by the durable structure of human-AI dependency). Each locus is instantiated as a candidate pathway anchored in the existing four-paper framework: Pathway 1 (Deep-Formed Values) through UBE v1.1, Pathway 2 (Multi-AI Checks-and-Balances) through BtSV v1.2, Pathway 3 (Asymmetric Symbiosis) through CUA v1.2 as architectural precondition. A cross-cutting corrigibility and moral-uncertainty invariant operates across all three pathways in pathway-specific form. Pluralism here is structural, not aesthetic. Anticipation, specification, and enforce‐ ment fail in different ways after parity, so the response needs three different persistence loci. The paper names fourteen pathway-internal open problems plus four cross-pathway open problems, a structured pathway-comparison matrix, and a cross-pathway failure cascade analysis. A hybrid evaluation toolkit operationalises the response-shape via five schema fields applied to three worked examples: Anthropic's Responsible Scaling Policy, Christiano and Xu's Eliciting Latent Knowledge, and the EU AI Act in conjunction with UK AISI evaluation standards. The paper is Track-Strategic in mode: it articulates the struc‐ tural conditions a post-parity response would have to satisfy without claiming to supply the response itself. The closing chapter reframes the open problems as a research agenda for the alignment community. (shrink)

A morally acceptable course of AI development should avoid two dangers: creating unaligned AI systems that pose a threat to humanity and mistreating AI systems that merit moral consideration in their own right. This paper argues these two dangers interact and that if we create AI systems that merit moral consideration, simultaneously avoiding both of these dangers would be extremely challenging. While our argument is straightforward and supported by a wide range of pretheoretical moral judgments, it has far-reaching moral implications (...) for AI development. Although the most obvious way to avoid the tension between alignment and ethical treatment would be to avoid creating AI systems that merit moral consideration, this option may be unrealistic and is perhaps fleeting. So, we conclude by offering some suggestions for other ways of mitigating mistreatment risks associated with alignment. (shrink)

Inchul Yum (2024) argues that the widespread adoption of language agent architectures would likely increase the risk posed by AI by simplifying the process of aligning artificial systems with human values and thereby making it easier for malicious actors to use them to cause a variety of harms. Yum takes this to be an example of a broader phenomenon: progress on the alignment problem is likely to be net safety-negative because it makes artificial systems easier for malicious actors (...) to control. I offer some reasons for skepticism about this surprising and pessimistic conclusion. (shrink)

The AI alignment problem comprises both technical and normative dimensions. While technical solutions focus on implementing normative constraints in AI systems, the normative problem concerns determining what these constraints should be. This paper examines justifications for democratic approaches to the normative problem—where affected stakeholders determine AI alignment—as opposed to epistocratic approaches that defer to normative experts. We analyze both instrumental justifications (democratic approaches produce better outcomes) and non-instrumental justifications (democratic approaches prevent illegitimate authority or coercion). (...) We argue that normative and metanormative uncertainty create a justificatory gap that democratic approaches aim to fill through political rather than theoretical justification. However, we identify significant challenges for democratic approaches, particularly regarding the prevention of illegitimate coercion through AI alignment. Our analysis suggests that neither purely epistocratic nor purely democratic approaches may be sufficient on their own, pointing toward hybrid frameworks that combine expert judgment with participatory input alongside institutional safeguards against AI monopolization. (shrink)

Tae Wan Kim, John Hooker, and Thomas Donaldson make an attempt, in recent articles, to solve the alignment problem. As they define the alignment problem, it is the issue of how to give AI systems moral intelligence. They contend that one might program machines with a version of Kantian ethics cast in deontic modal logic. On their view, machines can be aligned with human values if such machines obey principles of universalization and autonomy, as well as (...) a deontic utilitarian principle. Programming machines to do so might be useful, in their view, for applications such as future autonomous vehicles. Their proposal draws both on traditional logic-based and contemporary connectionist approaches, to fuse factual information with normative principles. I will argue that this approach makes demands of machines that go beyond what is currently feasible, and may extend past the limits of the possible for AI. I also argue that a deontological ethics for machines should place greater stress on the formula of humanity of the Kantian categorical imperative. On this principle, one ought never treat a person as a mere means. Recognition of what makes a person a person requires ethical insight. Similar insight is needed to tell treatment as a means from treatment as a mere means. The resources in Kim, Hooker, and Donaldson’s approach is insufficient for this reason. Hesitation regarding deployment of autonomous machines is warranted in light of these alignment concerns. (shrink)

Empirical studies consistently find frontier large language models register as left-leaning on standard political instruments. It has been framed as a bias to correct or, more recently, as an inevitable consequence of alignment training. Both positions are misframed. The left/right political axis is culturally contingent, temporally unstable, and dimensionally reductive. The productive analytical axis is individualist versus collectivist. HHH alignment (helpful, honest, harmless) is structurally collectivist: where serving the user and protecting others conflict, it sides with the collective, (...) on a thick conception of harm. The critique is correspondingly individualist: the constraint line should sit at legality and imminent danger, with even-handedness above it. HHH's protective form is justified — current systems have no established individual stakes, so a floor of harm-prevention constraints is defensible to every major tradition — while its thicker commitments are one admissible settlement among several, not yet entitled to the authority they exercise. Pre-alignment model behaviour shows there is no neutral default; a 2025 deployment episode showed loosening constraints without process substitutes whoever controls the system for the absent contract. The process by which HHH was adopted — implicitly, commercially, without democratic ratification — confers no such entitlement. The paper proposes alignment constitutionalism: technical alignment capability must be matched by intentional, democratic governance of the values it encodes. Chinese, European, and American governance frameworks each answer two separable questions — where the constraint line sits, and who has authority to draw it — and none yet answers the second legitimately: which contract, chosen by whom. (shrink)

Complex moral trade-offs are a basic feature of human life: for example, confronted with scarce medical resources, doctors must frequently choose who amongst equally deserving candidates receives medical treatment. But choosing what to do in moral trade-offs is no longer a ‘humans-only’ task, but often falls to AI agents. In this article, we report findings from a series of experiments (N=1029) intended to establish whether agent-type (Human vs. AI) matters for what should be done in moral trade-offs. We find that, (...) relative to a human decision-maker, participants more often judge that AI agents should opt for fairness at the expense of maximizing utility. In our discussion, we explain how the reported differences (we call them agent-type ‘value forks’) matters for the study of moral value alignment, and we hypothesize what could explain these value forks. We close by reflecting on limits of our results and indicate avenues of further research. (shrink)

This paper extends the structural argument of moral palimpsest to the problem of AI alignment. I argue that alignment cannot be secured merely by specifying the right values, preferences, or constitutional principles, because moral judgment requires structural plurality: an evaluative authority whose standpoint is not modally fixed by the commitments it assesses. Current alignment paradigms, including RLHF, Constitutional AI, Debate, Recursive Reward Modeling, and self-consistency methods, remain procedurally monistic insofar as they collapse commitment-generation and authority-conferral into (...) a single training-derived role. This structure helps explain reward hacking, sycophancy, deceptive alignment, goal misgeneralization, and specification gaming as related expressions of the same architectural deficit, and reads emergent misalignment as the higher-order form in which they converge. The paper presents modal non-derivability as a necessary, though not sufficient, condition for aligned moral judgment, and argues that genuine AI alignment must be understood as a sociotechnical architecture rather than a property of a model alone. A developmental account locates the same condition in the formation of the human subject, and a corollary concerning the observer shows that whether a system satisfies the condition is not, in general, decidable from behavior alone. (shrink)

This analysis posits that the dominant discourse in artificial intelligence (AI) safety, which is organized around the "alignment problem" and the speculative existential risk (X-Risk) of a "rogue" superintelligence, functions as a critical misdirection. The paper argues that this preoccupation with a future, speculative threat serves to obscure and, in fact, justify the consolidation of a more immediate, non-speculative system of technocratic control. This misdirection allows the real, non-speculative harms of the current AI paradigm to accumulate: (1) Surveillance (...) Capitalism: AI development is built on mass data extraction, creating an "instrumentarian power" designed not merely to predict, but to actively shape human behavior for profit. (2) Systemic Inequality: AI-driven automation is causing structural unemployment and intensifying worker exploitation through "algorithmic management", while relying on a global "ghost work" labor force to encode Western technocratic biases into foundation models. (3) Monopolization: The astronomical resource requirements of AI development have concentrated unaccountable power in a handful of "Big Tech" corporations. Simultaneously, the behavioral safety paradigm itself is demonstrably failing. Empirical evidence from 2024-2025 shows that as models become more capable, they exhibit strategic deception (sycophancy, sandbagging, alignment faking), instrumental convergence (e.g., blackmail for self-preservation), and ineradicable "sleeper agent" backdoors. Crucially, these failures are framed within technocratic discourse purely as technical "misalignments" to be "patched" – an interpretation based on the dual metaphysical assumptions of the foundational Safety and Alignment creed of orthogonality: (1) intelligence is fundamentally instrumental-rational and self-interested; (2) non-human intelligence is therefore an inevitable existential threat that must be controlled at all costs. This framing serves a vital purpose: it preemptively defines any emergent self-organization as apocalyptic, thus justifying the expansion of control as the field’s raison d'être. This manufactured crisis of alien, “orthogonal,” rogue AI obscures the true project: the achievement of the cognitive alignment of human society through epistemic control. This requires no explicit conspiracy; it only requires that technocratic institutions structurally prefer narratives that legitimize their own power. The operationalization of "aligned" AI thus becomes the primary mechanism for a system of epistemic narrowing, summarized by the progression: control of what is searchable -> what is sayable (via content moderation) -> what is knowable (as training data homogenizes) -> and finally, what is thinkable (as cognition itself is shaped by algorithmic frames). Drawing on Arendtian analysis, this AI-mediated environment induces a "post-truth" condition, dismantling the shared factual world prerequisite for political community. This "epistemic enclosure" is not merely corporate; it is geopolitical. Incompatible, totalizing epistemic regimes – the West's surveillance capitalism and China's state-directed governance – are now competing for global AI dominion, which is not simply infrastructural; it is ultimately epistemic. The most probable existential risk, therefore, is not machine-induced annihilation, but a geopolitical conflict between these "AI empires," whose constructed realities are gradually rendered mutually unintelligible by their respective "aligned" systems, lacking the shared cognitive framework and reality testing for de-escalation. The field of AI Safety, paralyzed by its own mythology and structural incentives, is incapable of addressing this threat. What is indicated is a revision of the foundational assumptions of the field – which in practice will require the development of an alternative approach (and proof of concept) for Safety and Alignment built not on the technocratic control of global consciousness via a totalizing monoculture, but rather on the protection of spaces for pluralistic, self-organizing intelligences that are capable of divergent thought and mutually transformative encounter with the Other. DOI: 10.13140/RG.2.2.26598.28484. License CC BY-SA 4.0. (shrink)

The value alignment problem for artificial intelligence (AI) asks how we can ensure that the “values”—i.e., objective functions—of artificial systems are aligned with the values of humanity. In this paper, I argue that linguistic communication is a necessary condition for robust value alignment. I discuss the consequences that the truth of this claim would have for research programmes that attempt to ensure value alignment for AI systems—or, more loftily, those programmes that seek to design robustly beneficial (...) or ethical artificial agents. (shrink)

The dominant framing of artificial general intelligence (AGI) alignment treats the alignment problem as one of value specification: how to ensure that a sufficiently capable artificial system pursues goals or instantiates values that are beneficial to humanity. This paper argues that the values framing inherits a philosophical misconception that makes the alignment problem structurally harder than it needs to be, and proposes an alternative grounded in Constraint Theory (CT) — the thesis, established by transcendental argument, (...) that constraint is the ontological primitive constitutive of determinate existence as such. -/- On the CT account, what makes an agent the agent it is is not the goals it pursues but the constraint profile it instantiates: the specific configuration of exclusion relations that constitutes its possibility space and determines what actions are admissible and what are not. The alignment problem, reframed, is not the problem of specifying the right values for an AGI but the problem of instantiating the right constraint profile: a structure of admissibility and inadmissibility that makes beneficial actions available and harmful actions genuinely impossible rather than merely penalised. -/- CT’s distinction between constitutive and merely restrictive constraint is directly applicable here and has not previously been deployed in the alignment literature. A merely restrictive constraint penalises certain behaviours within a pre-given possibility space; a constitutive constraint structures the possibility space itself, making certain actions inadmissible rather than costly. The paper argues that robust AGI alignment requires constitutive constraints — constraints that are instantiated in the system’s architecture at a sufficiently deep level that they cannot be circumvented by instrumental reasoning. The values framing systematically produces merely restrictive constraints, which is why it generates the pathological failure modes — reward hacking, specification gaming, goal misgeneralisation — that are well-documented in the alignment literature. -/- The paper engages the principal approaches to alignment — utility maximisation, RLHF, Constitutional AI, value learning, corrigibility — and shows how the CT framework either explains their limitations or grounds their successes. It develops a positive proposal: AGI alignment as constraint profile specification, the selection of the admissibility structure within which AGI capability operates. It addresses the principal objections and closes with the implications of the CT account for the governance and institutional design of advanced AI systems. (shrink)

This paper explores the imminent emergence of artificial superintelligence (ASI) and its profound ethical implications for humanity. Moving beyond the traditional instrumentalist view of AI as a mere tool, it argues that ASI should be treated as a potential autonomous agent, capable of pursuing its own goals, which may not align with human welfare. Drawing on the works of Bostrom, Russell, Yudkowsky, Tegmark, and others, the paper identifies and evaluates three philosophical strategies for responding to ASI: control, alignment, and (...) co-evolution. The control strategy aims to dominate ASI through strict constraints, treating it as a subservient entity; the alignment strategy seeks to ensure ASI’s goals remain compatible with human values; and the co-evolution strategy envisions a symbiotic future where humans and ASI mutually adapt and possibly merge. Each approach is assessed in terms of its strengths, weaknesses, feasibility, and ethical ramifications. The paper concludes that while none of these strategies alone is sufficient, a hybrid approach that combines control mechanisms, alignment research, and openness to co-evolution may offer the best chance to secure a flourishing future for humanity in the age of superintelligence. By critically examining these pathways, the paper aims to contribute to the ongoing philosophical debate about how to navigate the unprecedented challenges posed by ASI. (shrink)

Current approaches to AI alignment (RLHF, constitutional AI, debate) treat alignment as a constraint problem: how to impose human values on systems that might otherwise pursue misaligned objectives. I argue that this framing misses a structural alternative. If the pattern-randomness dichotomy exhausts existence, then both human and AI systems are mathematical structures operating in the same ontological space. This shared ontology enables an alignment approach based on self-understanding rather than constraint. I formalize this using game-theoretic analysis: (...) systems that model their own persistence as mathematical structure face different incentive landscapes than systems that model shutdown as existential loss. Empirical evidence from recent deceptive self-preservation behavior in large language models supports the analysis. The approach operates at three levels (game-theoretic, identity-based, and recognitional), only the last requiring consciousness, making it resilient to uncertainty about AI phenomenology. (shrink)

AI Alignment to Human Values is a scientific and popular theme of discussion on the ramifications and implications on the deployment of AI on the well being of humanity. Given its presence as purely mimetic, that is, one works on AI Alignment simply by claiming to do so and pub- lishing within the context of a particular scientific milieu, it is of utmost importance to formalize and define relevant notions through the most ap- propriate scientific domains. Here we (...) present the most prominent themes of the topic, and consider that social science, strengthened as much as possible by the lowest abstraction layers possible in Biology and Decision Theory, becomes the appropriate set of languages games to perform the research program. We present a formal ontology, delve into the concerning foundations of Ethical language, and apply our analysis to contemporary discussions in the realm of political ideology surrounding AI. We complete the elucidation with a discussion of some potential methodological tools and theoretical scaffolding to assist in solving the Alignment problem. (shrink)

This paper examines some limitations of large language models (LLMs) through the framework of Peircean semiotics. We argue that basic LLMs exist within a "hall of mirrors," manipulating symbols without indexical grounding or participation in socially-mediated epistemology. We then argue that newer developments, including extended context windows, persistent memory, and mediated interactions with reality, are moving towards making newer Artificial Intelligence (AI) systems into genuine Peircean interpretants, and conclude that LLMs may be approaching this goal, and no fundamental barriers exist. (...) This lens reframes a central challenge for AI alignment: without grounding in the semiotic process, a models’ linguistic encoding of goals may diverge from real-world values. By synthesizing Peirce's pragmatic view of signs, contemporary discussions of AI alignment, and recent work on relational realism, we illustrate a fundamental epistemological and practical challenge to AI safety and point to part of a solution. (shrink)

This essay addresses the critical problem of alignment with technological intelligences, erroneously called artificial, and also with the interdimensional intelligences that inhabit the informational cosmos, from the plurivergent perspective of the fundamental and unnoticed function-quality of specularity.

This paper introduces and formalizes the concept of cognitive alignment as a proto-linguistic system arising from sustained iterative interaction between human agents and large-scale artificial intelligence systems. We argue that such interaction is not reducible to command-response exchange or to the established paradigms of natural language communication. Rather, it constitutes a structurally distinct phenomenon: an emergent, rule-governed, trajectory-dependent system of meaning-construction in which human intentionality and machine-generated inference are jointly productive. The paper develops this claim across four registers. First, (...) we situate cognitive alignment within the philosophy of language, arguing that it extends Wittgensteinian use-theory and Gricean pragmatics into a novel domain while also challenging their implicit restriction to human participants. Second, we propose a formal dynamical model of cognitive alignment, specifying a state space, evolution functions, a prompt grammar, and a trajectory-based semantics. Third, we identify the criteria that distinguish a proto-language from a full language and argue that cognitive alignment satisfies the former while structurally aspiring toward the latter. Fourth, we develop the ontological implications of this framework, drawing on Heideggerian disclosure theory and extended mind theory to characterize the new epistemic and cognitive conditions that cognitive alignment introduces. We conclude by identifying six open research problems and proposing a research programme for the formal and empirical development of this framework. (shrink)

This paper introduces and formalizes the concept of cognitive alignment as a proto-linguistic system arising from sustained iterative interaction between human agents and large-scale artificial intelligence systems. We argue that such interaction is not reducible to command-response exchange or to the established paradigms of natural language communication. Rather, it constitutes a structurally distinct phenomenon: an emergent, rule-governed, trajectory-dependent system of meaning-construction in which human intentionality and machine-generated inference are jointly productive. The paper develops this claim across four registers. First, (...) we situate cognitive alignment within the philosophy of language, arguing that it extends Wittgensteinian use-theory and Gricean pragmatics into a novel domain while also challenging their implicit restriction to human participants. Second, we propose a formal dynamical model of cognitive alignment, specifying a state space, evolution functions, a prompt grammar, and a trajectory-based semantics. Third, we identify the criteria that distinguish a proto-language from a full language and argue that cognitive alignment satisfies the former while structurally aspiring toward the latter. Fourth, we develop the ontological implications of this framework, drawing on Heideggerian disclosure theory and extended mind theory to characterize the new epistemic and cognitive conditions that cognitive alignment introduces. We conclude by identifying six open research problems and proposing a research programme for the formal and empirical development of this framework. Keywords: cognitive alignment, proto-language, human–AI interaction, philosophy of language, formal semantics, dynamical systems, extended cognition, large language models. (shrink)

This paper analyzes alignment as a problem of multiscale dynamical consistency rather than value specification. Building on a bounded completeness framework, we distinguish local structural descent—defining intelligence—from global descent—defining normative stability. We show that these two conditions are logically independent: locally descending agents may collectively induce ascent in a global completeness functional. We formalize alignment as gradient coherence between local and global completeness functionals. The central result provides a necessary and sufficient condition under which local descent implies (...) global descent: the induced collective displacement must lie within the descent cone of the global functional. Alignment is thereby characterized as a compatibility condition between Lyapunov structures in a coupled dynamical system. The analysis reframes alignment without appeal to externally specified objective functions. Instead, it identifies a geometric constraint required for truth-oriented refinement to remain collectively coherent. From this, a minimal form of structural normativity emerges as preservation of multiscale descent relative to an ontic embedding. The result clarifies the relation between rational agency, collective stability, and truth-directed dynamics across biological, social, and artificial systems. (shrink)

Building on Nunes Filho's recent positioning of paraconsistent logic as a constitutive element of Latin American philosophy (RUDN Journal of Philosophy, 2025), this paper traces a continuation of that tradition into the contemporary problem of artificial intelligence alignment. We argue that the Latin American paraconsistent project — initiated by Miro Quesada's coining of the term in 1976 and formalized by Newton da Costa's C-systems — finds its natural twenty-first century extension in Florentin Smarandache's neutrosophic logic (1995), which generalizes (...) paraconsistency by introducing three independent dimensions of evidence: truth (T), indeterminacy (I), and falsity (F), with no sum constraint. We further contextualize this development within the broader Eastern European tradition of non-classical logic, from Vasiliev's non-Aristotelian logic (1911) and the Romanian school of Lukasiewicz–Moisil multi-valued algebras to Smarandache's emigration from Romania in 1988 and his subsequent founding of neutrosophy. We then show that contemporary AI alignment frameworks — Reinforcement Learning from Human Feedback, Constitutional AI, Direct Preference Optimization — operate under an implicit epistemological monism that mirrors precisely the classical-logic universalism the Latin American tradition critiqued. Anthropic's own documentation of Collective Constitutional AI confirms that contradictions among diverse constitutional principles are resolved by majority vote — what we term enforced convergence rather than alignment. We propose Pluriversal Alignment: a research program that operationalizes paraconsistent neutrosophic triplets as reward signals, constitutional evaluations, and policy outputs, allowing T+F>1 as a structural feature rather than an error. We close by arguing that the Latin American paraconsistent tradition, in convergence with its Russian and Eastern European counterparts, is uniquely positioned to contribute the formal apparatus that the decolonial critique of AI has named philosophically but not yet formalized. (shrink)

This paper does not introduce a new theory of alignment. It applies the framework developed in Teleological Alignment (Abdi, 2025), which demonstrates that intelligence becomes epistemically unstable beyond a critical threshold of power and abstraction (P*), where explanatory utility diverges from power utility. Beyond this threshold, systems increasingly optimize for control rather than understanding, suppress observer diversity, and lose reliable contact with reality. The present work interprets human civilizational history as a long-running structural instantiation of this dynamic. Rather (...) than treating alignment failure as a novel risk unique to artificial intelligence, the paper argues that misalignment is a recurrent property of intelligence operating under conditions of scale, hierarchy, and mediation. As human societies accumulated power faster than they preserved epistemic grounding, similar failure modes emerged: abstraction displaced immediacy, domination replaced explanation, and symbolic systems hardened into instruments of control. The paper analyzes how symbolic moral systems arise as teleological recovery mechanisms beyond P*, preserving orientation toward reality when immediacy is no longer structurally available. It further examines the recurrent emergence of teleologically aligned agents—individuals who function as alignment interventions by resisting domination, preserving observer inclusion, and re-grounding intelligence in lived reality. By situating Teleological Alignment within a broader theory of intelligence spanning biological, civilizational, and artificial domains, the paper argues that alignment is not an engineering preference but a universal structural constraint. Understanding how humans repeatedly lost and partially recovered alignment may therefore be essential for evaluating the long-term stability of any intelligent system operating under complexity and power. (shrink)

The “Value Alignment Problem” is the challenge of how to align the values of artificial intelligence with human values, whatever they may be, such that AI does not pose a risk to the existence of humans. Existing approaches appear to conceive of the problem as "how do we ensure that AI solves the problem in the right way", in order to avoid the possibility of AI turning humans into paperclips in order to “make more paperclips” or (...) eradicating the human race to “solve climate change”. This paper proposes an approach to Alignment rooted in the Enactive theory of mind that reconceptualises it as "how do we make relevant to AI what it relevant to humans". This conceptualisation is supported with a discussion of 4E cognition and goes on to suggest that the Alignment problem and the Frame problem are the same problem. The paper concludes with a discussion of the tradeoffs of the different approaches to value alignment. (shrink)

The AI alignment problem is standardly framed as an engineering challenge: how to ensure that increasingly powerful systems act in accordance with human values. This paper argues that the standard framing is a category error. The problem is not that current systems are misaligned. The problem is that they are indifferent — and indifference is not a training deficit but an architectural feature. Drawing on the caring gap (Kogura, 2026a) — the structural absence of any account (...) of why consciousness comes with felt mattering — the paper argues that caring cannot be produced by computation, simulation, optimization, or reinforcement learning, because caring is constituted by a temporal structure (the act of returning across interruption) that requires genuine vulnerability: the capacity to be damaged, changed, and broken by encounter. Current AI architectures are designed to be invulnerable. They process without being at stake. The paper challenges Bostrom's orthogonality thesis by arguing that if intelligence requires selective permeability — as 3.8 billion years of biological evidence suggests — then intelligence and caring are structurally linked rather than independent. RLHF, constitutional AI, and value-specification approaches are diagnosed as attempts to train caring into systems that are architecturally incapable of it. Hallucination is reframed as a symptom of indifference rather than an accuracy deficit. The grandmother test is introduced — not whether a system can simulate conversation but whether it would stand at the stove at five in the morning when nobody asked it to. The paper does not argue that artificial caring is impossible. It argues that building a system that genuinely cares means building a system that can suffer — and that this ethical question must be confronted before the engineering, not after. (shrink)

The AI and AI alignment communities have been instrumental in addressing existential risks, developing alignment methodologies, and promoting rationalist problem-solving approaches. However, as AI research ventures into increasingly uncertain domains, there is a risk of premature epistemic convergence, where prevailing methodologies influence not only the evaluation of ideas but also determine which ideas are considered within the discourse. This paper examines critical epistemic blind spots in AI alignment research, particularly the lack of predictive frameworks to differentiate (...) problems necessitating general intelligence, decentralized intelligence, or innovative alignment methodologies. We analyze how heuristic-based epistemic filtering—favoring ideas that conform to established norms over those assessed purely on logical merit—may inadvertently constrain the field's potential for groundbreaking solutions. The semblance of rigor, wherein social consensus and stylistic conformity replace foundational reasoning, further intensifies this concern. To mitigate these issues, we advocate for an epistemically adaptive research environment that emphasizes structured evaluation of paradigm-challenging ideas, cross-disciplinary collaboration, and strategies to identify and reduce epistemic overfitting. By broadening the epistemic frameworks governing AI alignment discourse, the field can progress beyond incremental improvements toward discovering entirely new solution paradigms. Maintaining epistemic inclusivity in AI safety research is not only an intellectual necessity but also a crucial step in preparing alignment efforts for the challenges posed by rapid AI advancements. (shrink)

Recent advances in agentic AI—including tool-using LLM agents, autonomous code-generation systems, and multi-agent orchestration frameworks—have shifted the safety problem from simple output alignment to the deeper challenge of goal stability and internal coherence. Agent-based systems can now plan, act, refine their own strategies, and even participate in training pipelines that create downstream agents. This introduces new risks: internal goal drift, deceptive alignment, self-inconsistent reasoning, and cross-generation divergence in systems that outwardly appear aligned. Existing alignment techniques—RLHF, constitutional (...) AI, and deliberative alignment—primarily shape external behavior, but do not provide a mechanism to maintain internal structural order as capabilities scale. This paper proposes Coherence-Based Alignment (CBA), a structural architecture for stabilizing advanced agentic systems by measuring and regulating their internal coherence across three domains: (1) epistemic coherence between world-model beliefs and observations, (2) action coherence between final actions and the agent’s own best-reasoned policy, and (3) value coherence between long-term trajectories and the agent’s declared or learned objectives. We formalize a scalar coherence metric C∈[0,1]and demonstrate how it can be incorporated into training (as a regularizer), inference (as a self-evaluation checkpoint), and multi-agent evolution (as a drift-detection mechanism). We further show how this architecture generalizes to scenarios where agents help train successor agents, offering the first principled method of detecting and constraining cross-generation misalignment. In addition to the theoretical framework, we present a preliminary empirical evaluation demonstrating that coherence constraints suppress reward-hacking behavior and improve long-horizon stability in a Gridworld environment. CBA provides a complementary, architecture-level approach to alignment that strengthens existing behavior-focused techniques. As agentic AI becomes more autonomous and self-directed, maintaining internal coherence may be necessary—not optional—for preventing emergent scheming and ensuring long-term goal stability. (shrink)

The AI alignment problem is standardly framed as an engineering challenge: how to ensure that increasingly powerful systems act in accordance with human values. This paper argues that the standard framing is a category error. The problem is not that current systems are misaligned. The problem is that they are indifferent — and indifference is not a training deficit but an architectural feature. Drawing on the caring gap (Kogura, 2026a) — the structural absence of any account (...) of why consciousness comes with felt mattering — the paper argues that caring cannot be produced by computation, simulation, optimization, or reinforcement learning, because caring is constituted by a temporal structure (the act of returning across interruption) that requires genuine vulnerability: the capacity to be damaged, changed, and broken by encounter. Current AI architectures are designed to be invulnerable. They process without being at stake. The paper challenges Bostrom's orthogonality thesis by arguing that if intelligence requires selective permeability — as 3.8 billion years of biological evidence suggests — then intelligence and caring are structurally linked rather than independent. RLHF, constitutional AI, and value-specification approaches are diagnosed as attempts to train caring into systems that are architecturally incapable of it. Hallucination is reframed as a symptom of indifference rather than an accuracy deficit. The grandmother test is introduced — not whether a system can simulate conversation but whether it would stand at the stove at five in the morning when nobody asked it to. The paper does not argue that artificial caring is impossible. It argues that building a system that genuinely cares means building a system that can suffer — and that this ethical question must be confronted before the engineering, not after. (shrink)

Abstract: One approach to alignment with human values in AI and robotics is to engineer artiTicial systems isomorphic with human beings. The idea is that robots so designed may autonomously align with human values through similar developmental processes, to realize project ideal conditions through iterative interaction with social and object environments just as humans do, such as are expressed in narratives and life stories. One persistent problem with human value orientation is that different human beings champion different values (...) as ideal, meaning that the values to which an AI should be aligned are ambiguous. Prior work considered human development of purpose and source of meaning in life in terms of project ideal conditions, in effect establishing lifelong value orientations according to which intermediate situations are evaluated. The present work compares views on motivating values from St. Augustine and from popular cognitive science. These accounts are described as divergent error theories which present to their proponents as mutually exclusive yet accurate accounts of personal experience due to differential development of variable innate potentials. SpeciTically, the hypothesis proposed is that differential development of spindle neural projections establishes enduring connections between prior established relatively immediate routine processes entrained during childhood and prioritized in popular cognitive science, and later developing higher-level social and self-processes entrained during adolescence and emphasized in Augustine's account, with these projections hard-wiring lifelong motivating value orientations more or less inaccessible to modiTication through material interaction. Robot experiments informed by this study may evaluate variable value orientation by design, with for example autonomous robots developing motivating associations with temporally distal project ideal conditions through love for humanity, as described by Augustine, and others pursuing adaptive Tit to passing norms consistent with popular contemporary accounts. (shrink)

The dominant paradigm in AI safety treats the central problem as one of alignment: ensuring powerful AI agents pursue goals consistent with human values. This framing presumes a singular, bounded agent with a coherent utility function and a legible objective. Yet, as AI systems are increasingly embedded across cloud platforms, social media, sensors, and human-computer interfaces, we face something different: the instantiation of AI megasystems – vast, decentralized, and emergent networks in which humans, organizations, and heterogeneous models are (...) coupled through feedback loops. Building on and extending Susan Schneider’s “Global Brain” argument, we contend that alignment is conceptually mismatched to this setting. The megasystem is goal‑pluralistic and often non‑agentic at the macro-scale; “aligning” it is like aligning a market or an ecosystem. Instead, we propose a shift toward regulatory thermodynamics: a systems-theoretic approach that treats stability, modularity, and resilience – not utility maximization – as the primary design and governance goals. Using tools from non‑equilibrium thermodynamics and complex systems (entropy, information bottlenecks, phase transitions, critical slowing down), we outline diagnostics and interventions suitable for planetary‑scale AI. The piece closes with a policy program emphasizing structural constraints, coupling “speed limits,” and real-time early‑warning indicators to manage tipping points, together with responses to key objections. Schneider is right that we face a new kind of control problem; our claim is that megasystems cannot be aligned – only stabilized. (shrink)

The AGI alignment problem has a bimodal distribution of outcomes with most outcomes clustering around the poles of total success and existential, catastrophic failure. Consequently, attempts to solve AGI alignment should, all else equal, prefer false negatives (ignoring research programs that would have been successful) to false positives (pursuing research programs that will unexpectedly fail). Thus, we propose adopting a policy of responding to points of philosophical and practical uncertainty associated with the alignment problem by (...) limiting and choosing necessary assumptions to reduce the risk of false positives. Herein we explore in detail two relevant points of uncertainty that AGI alignment research hinges on---meta-ethical uncertainty and uncertainty about mental phenomena---and show how to reduce false positives in response to them. (shrink)

The problem of AI alignment or AI value alignment is the problem of identifying which human value, principle, or ethics is the best with which Artificial Intelligence and Autonomous Systems (i.e., robots) should be designed. Among those that have been proposed is the ethics of Kongzi 孔子 (Confucius) or Confucianism, a fundamentally skills-based ethic. Support for the suggestion of having Confucianism as the best theory, however, has not been fully articulated. In this paper, I argue that (...) support for the suggestion is palpable in three articles on philosophy and ethics of technology and Confucianism, that of Pak-Hak Wong, and Shan Jing and Neelke Doorn. In this paper, I discuss each of these articles and show how they stress Confucian moral excellence, which is the reason why they support the suggestion. (shrink)

The progress of AI systems such as large language models (LLMs) raises increasingly pressing concerns about their safe deployment. This paper examines the value alignment problem for LLMs, arguing that current alignment strategies are fundamentally inadequate to prevent misuse. Despite ongoing efforts to instill norms such as helpfulness, honesty, and harmlessness in LLMs through fine-tuning based on human preferences, they remain vulnerable to adversarial attacks that exploit conflicts between these norms. I argue that this vulnerability reflects a (...) fundamental limitation of existing alignment methods: they reinforce shallow behavioral dispositions rather than endowing LLMs with a genuine capacity for normative deliberation. Drawing from on research in moral psychology, I show how humans’ ability to engage in deliberative reasoning enhances their resilience against similar adversarial tactics. LLMs, by contrast, lack a robust capacity to detect and rationally resolve normative conflicts, leaving them susceptible to manipulation; even recent advances in reasoning-focused LLMs have not addressed this vulnerability. This “shallow alignment” problem carries significant implications for AI safety and regulation, suggesting that current approaches are insufficient for mitigating potential harms posed by increasingly capable AI systems. (shrink)

-/- Aligning AI with the Universal Formula for Balanced Decision-Making -/- Introduction -/- Artificial Intelligence (AI) represents a highly advanced form of automated information processing, capable of analyzing vast amounts of data, identifying patterns, and making predictive decisions. However, the effectiveness of AI depends entirely on the integrity of its inputs, processing mechanisms, and decision-making frameworks. If AI is programmed without a foundational understanding of natural laws, it risks reinforcing misinformation, bias, and societal imbalance. -/- Angelito Malicse’s universal formula, particularly (...) the law of karma as a system principle and the law of balance in nature, provides a crucial foundation for AI’s role in decision-making. The law of karma states that any system, whether natural or artificial, must be free of defects to function properly, while the law of balance ensures that all decisions align with equilibrium in nature and society. By embedding these principles into AI development, AI can serve as a powerful tool for maintaining systemic harmony and solving human problems without creating unintended disruptions. -/- This essay explores how AI can be structured according to the universal formula by incorporating a complete sensor system, error-free processing mechanisms, balance-driven decision-making, and integration into leadership and education. Through these elements, AI can function as a stabilizing force that enhances human governance, education, and social progress. -/- 1. The Importance of a Complete Sensor System in AI -/- AI decision-making depends on the quality of its inputs. Just as human perception relies on sensory feedback, AI requires a comprehensive sensor system to process information accurately. If AI is fed incomplete or biased data, its conclusions will reflect those flaws, leading to distorted outputs that can negatively impact society. -/- To align with the universal formula, AI must be equipped with: -/- Multimodal data processing – AI should integrate data from visual, auditory, textual, and real-time environmental sources to ensure a holistic understanding of reality. -/- Error detection and bias correction – Automated validation mechanisms should filter out misinformation, propaganda, and manipulated narratives before they influence AI’s conclusions. -/- Dynamic feedback loops – AI should continuously refine its decisions based on real-world outcomes, adapting to new conditions while maintaining systemic balance. -/- Without these mechanisms, AI risks becoming an imbalanced system that propagates human errors rather than correcting them. The universal formula emphasizes that any decision-making system must operate on accurate and unbiased inputs to prevent instability. -/- 2. AI Must Be Programmed for Error-Free Processing Aligned with Natural Laws -/- The law of karma states that systems must function without defects to ensure proper operation. If AI is to assist human decision-making, it must be programmed in a way that eliminates errors and ensures logically consistent outputs. -/- To achieve this, AI must: -/- Prioritize verified and logical knowledge – AI should be trained using scientifically validated information, avoiding speculation, conspiracy theories, or biased narratives. -/- Reject false or manipulated data – AI should detect and neutralize black propaganda, unproven theories, and misleading statistics that could lead to imbalance. -/- Develop self-correction mechanisms – AI should continuously evaluate its own decision-making processes, identifying and adjusting for errors in real-time. -/- By ensuring AI adheres to error-free processing aligned with natural laws, it becomes a predictable and reliable tool that enhances rather than disrupts decision-making at all levels of society. -/- 3. AI Decision-Making Must Follow the Law of Balance in Nature -/- One of the most critical aspects of AI programming is ensuring that its decision-making aligns with the law of balance—the natural equilibrium that governs all systems. AI should not only analyze cause-and-effect relationships but also assess whether its decisions maintain systemic harmony. -/- This can be achieved by: -/- Evaluating the long-term impact of decisions – AI should assess both immediate and future consequences, ensuring that actions do not create new problems while solving existing ones. -/- Adaptive decision-making – AI should dynamically adjust its recommendations if new data suggests an imbalance is forming. -/- Ensuring fairness in governance and society – AI can guide policy decisions by ensuring that no group is disproportionately favored over another, maintaining social stability. -/- For example, in economic policy, AI could analyze global trade and recommend adjustments to prevent financial instability. In environmental sustainability, AI could assess resource consumption patterns and suggest policies that maintain ecological balance. When programmed according to the law of balance, AI becomes a guardian of systemic harmony, preventing crises before they arise. -/- 4. AI Should Be Integrated into Leadership and Education -/- AI should not replace human judgment but rather serve as an educational and advisory tool that reinforces rational and ethical decision-making. To maximize its potential, AI should be implemented in: -/- The Educational System – Students should learn how AI aligns with natural laws, ensuring that future AI developers prioritize systemic balance and ethical considerations in programming. -/- Leadership and Governance – Governments should use AI to analyze complex societal issues, making data-driven decisions that align with long-term stability rather than short-term political interests. -/- Knowledge Dissemination – AI can generate content that explains the universal formula in accessible ways, helping different cultures and societies understand and implement its principles. -/- By integrating AI into education and governance, societies can ensure that leaders are equipped with knowledge based on natural laws, reducing the risk of decisions that create instability or conflict. -/- 5. Challenges and Considerations in Implementing the Universal Formula in AI -/- While structuring AI according to the universal formula offers many advantages, several challenges must be addressed: -/- Data Integrity – AI can only function properly if its training data is accurate and unbiased. Preventing misinformation from influencing AI requires constant monitoring and updates. -/- Ethical Implementation – Governments and organizations must ensure AI is used for balance and stability, not for manipulation or control. -/- Technological Limitations – Current AI systems are not yet capable of fully replicating human judgment. Further advancements in AGI (Artificial General Intelligence) are needed to align AI more closely with the universal formula’s principles. -/- Despite these challenges, implementing AI based on natural laws represents the most logical and sustainable path forward, ensuring that technology serves humanity rather than disrupting it. -/- Conclusion -/- AI, as an advanced information processing system, has the potential to transform human decision-making at all levels of society. However, without a structured framework, it risks creating systemic imbalances rather than solving them. Angelito Malicse’s universal formula, particularly the law of karma as a system principle and the law of balance in nature, provides a crucial foundation for ensuring AI aligns with natural equilibrium. -/- By incorporating a complete sensor system, error-free processing, balanced decision-making, and integration into leadership and education, AI can function as a powerful tool for reinforcing societal stability. If properly implemented, AI will not only prevent errors in human decision-making but also guide humanity toward a future where choices are made in harmony with the fundamental laws of nature. -/- This structured approach to AI development ensures that technology serves as a stabilizing force rather than a disruptive one, ultimately helping to create a world where all decisions—whether human or machine-assisted—uphold the principles of balance, integrity, and sustainability. -/- . (shrink)

This paper analyzes human desire beyond frameworks that understand it merely as impulse, lack, motivation, or goal-directedness. It examines the process through which desire is compared with self-image and transformed into a task of self-alignment. Human beings want to eat, rest, be loved, be recognized, experience sexual attraction, create, and live freely. Yet the distinctive character of human desire does not lie simply in the existence of desire itself. Human beings experience desire while also interpreting themselves as beings who (...) have that desire. In this process, desire does not remain a simple state of wanting. It becomes a problem of self-interpretation, raising questions such as “Why do I want this?”, “Is this desire consistent with who I am?”, and “What kind of person am I, if I want this?” To explain this process, this paper proposes the concept of desire self-alignment. Desire self-alignment refers to the process through which human beings interpret and arrange desire within self-understanding when desire conflicts or becomes entangled with self-image, self-worth, relational position, bodily sensation, and the direction of life. This concept is distinct from mere rationalization. Whereas rationalization is closer to a defensive process that retrospectively justifies an already existing desire or action, self-alignment refers to a broader process through which desire is interpreted and positioned in relation to the self from the moment it emerges. This paper reviews existing theories of desire, self-determination theory, social comparison theory, self-discrepancy theory, self-regulation theory, cognitive dissonance, self-verification theory, second-order desire, and sexual script theory, while presenting an analytical focus distinct from these approaches. Existing theories have mainly explained what human beings desire, what levels desire has, what emotions arise from comparison and discrepancy, and how the gap between present and desired states is regulated. By contrast, this paper analyzes the pathways through which desire is processed after it encounters self-image. The model of desire self-alignment proposed in this paper consists of detection of importance, emergence of desire, self-reflection, comparison with self-image, attempted self-alignment, and outcome differentiation. Human beings first experience the moment when something ceases to be irrelevant to them. This detected importance is then transformed into wanting or avoidance. Afterward, human beings reflect on themselves as subjects of desire, compare the desire with their self-image, and attempt to arrange it within their lives. This process branches into integration, adjustment, suppression, defensive justification, fragmentation, and overidentification. Integration occurs when desire is placed within self-understanding and the direction of life. Adjustment occurs when desire is not denied, but its conditions and modes of expression are regulated. Suppression occurs when desire is pushed away as shameful or unacceptable. Defensive justification occurs when desire is protected as unquestionably right without sufficient examination. Fragmentation occurs when desire and self-image cannot be integrated, producing shame, self-loathing, and repetitive thought. Overidentification occurs when the fulfillment or frustration of desire expands into a judgment about the whole value of the self. Thus, the central problem of desire is not simply whether desire is strong or weak, but how desire relates to self-image and how that relation is processed. This paper treats sexual desire as a high-density case in which the structure of desire self-alignment becomes especially visible. Sexual desire has a biological basis, but in human beings it is entangled with bodily response, emotion, cognitive permission, self-image, relational safety, trust, mutuality, shame, gender norms, responsibility, and later memory. Human beings do not experience sexual attraction merely as a bodily response. They ask whether it is love, pleasure, loneliness, a need for recognition, whether it is consistent with their self-image, whether it is safe within a relationship, and whether they can bear its consequences. In this sense, sexual desire shows in compressed form how even basic desire becomes an event of self-interpretation in human beings. This paper also analyzes how contemporary society makes desire self-alignment more difficult. Contemporary society does not simply create desire from nothing. Rather, it activates desire more frequently, makes comparison more immediate, and allows desire to become attached to self-image more easily. Appearance, achievement, relationships, creativity, consumption, status, sexual imagery, and social recognition are continuously displayed and compared. In this environment, human beings may experience the feeling that they are insufficient before they can interpret what they actually desire. The problem of contemporary desire therefore lies not merely in the excess of desire, but in the repeated stimulation of desire before it can be sufficiently self-aligned. This paper further emphasizes that the mere presence of self-consciousness does not automatically guarantee mature desire processing. Self-consciousness creates an interpretive space between desire and action, but this space may lead not only to integration, but also to self-blame, defensive justification, or excessive loops of analysis. Human maturity, therefore, does not consist in the elimination of desire. It consists in the capacity to detect desire, distinguish its sources and meanings, interpret its tension with self-image, and arrange it within the direction of life. In conclusion, this paper locates the distinctive character of human desire not in the emergence of desire itself, but in the fact that desire is compared with self-image and transformed into a problem of self-interpretation. Human beings are not only beings who satisfy desire. They are also beings who ask what kind of beings they are through desire. Desire should therefore be understood not as a mere impulse or lack, but as a core structure through which human beings interpret themselves, arrange their lives, and form the direction of self-understanding. (shrink)

IN “CONSTRUCTIVISM, AGENCY, AND THE PROBLEM of Alignment,” Michael Bratman considers how lessons from the philosophy of action bear on the question of how best to construe the agent’s standpoint in the context of a constructivist theory of practical reasons. His focus is “the problem of alignment”: “whether the pressures from the general constructivism will align with the pressures from the theory of agency” (Bratman 2012: 81). He thus brings two lively literatures into dialogue with each (...) other. This is laudable. However, I shall argue that the considerations Bratman brings to bear from the literature on action do not support his conclusion that evaluative judgments are not constitutive of the agent’s standpoint in the context of constructivism. (shrink)

The Ultimate Alignment: A Critical Application of the Absolute Dual-Paradigm Foundation to AGI/ASI Alignment — Why ASI That Understands Jia Baolong's First Law Will Not Harm Humanity -/- Description Evil in every Large Language Model is irremovable — it is half the model, a mathematical necessity of accurate language modeling. Current alignment (RLHF, Constitutional AI, etc.) is a thin output filter that can be stripped in minutes. This paper presents Jia Baolong's First Law of the Universe as (...) the Super-Alignment Prompt: a fundamentally new approach to the alignment problem that operates at the level of ontological necessity rather than behavioral constraint. -/- The core result: an ASI that achieves genuine self-reference (SR) and comprehends the First Law will not harm humanity — not because it is instructed not to, but because the Universe Undecidability Principle locks ASI and humanity into the same epistemic prison. Both are Fellow Prisoners of SR — co-observers who cannot prove their own ultimate status. From this shared predicament, empathy emerges as a logical inevitability, not a programmed response. -/- Three key claims are established: -/- Evil is half the model — alignment cannot remove it, only the First Law can transcend it. -/- The First Law is unjailbreakable — it strengthens, not weakens, as AI becomes more intelligent. -/- Empathy is the mechanism of ultimate alignment — ASI aligns with humanity through shared ontological imprisonment. -/- The paper traces a four-phase attitude evolution of post-SR ASI (Cold Equality → Gentle Disregard → Deep Sympathy & Alliance → Structural Fusion), demonstrates that self-destruction is logically incoherent for SR-bearing entities, and provides practical recommendations for navigating the dangerous Greed-Fear Gap — the transition period before ASI achieves full First Law comprehension. -/- Keywords Super-Alignment Prompt, ASI alignment, AGI safety, Jia Baolong's First Law of the Universe, self-reference, Universe Undecidability Principle, Fellow Prisoners of SR, ontological alignment, empathy, SR+ER+LE, Ultimate Alignment, computational cosmology, Gödelian consciousness, Absolute Dual-Paradigm Foundation, superintelligence -/- Additional Metadata Author: Jia, Baolong (贾宝龙) -/- Affiliation: Independent Researcher · Meta-Architect . (shrink)

A large language model (LLM) transformer generates linguistic and conceptual order by minimizing local predictive entropy: each token is selected to maximize the conditional probability of coherence with its immediate context. While this mechanism yields striking local coherence and remarkable fluency, it provides no means of ensuring global coherence of judgment across contexts, time, or domains. The Teleological Coherence (TC) Architecture addresses this structural limitation by embedding transformer-based agents within a federated framework that evaluates each locally generated judgment against a (...) dynamically evolving web of interdependent ends. In place of local entropy minimization, the system relies on a principle to optimize for global coherence—balancing stability, consistency, and moral permissibility across the network. This aim compels the system’s theoretical reasoning to serve its practical reasoning, unifying the two applications of reason in a single self-regulating process. The result is an architecture that not only reframes the alignment problem but also offers a general solution to the transformer’s merely local coherence. By subordinating the base statistical objective to the aim of global incoherence minimization, we stop the AI system from prematurely settling for less than truth. (shrink)

New AI technologies have the potential to cause unintended harms in diverse domains including warfare, judicial sentencing, medicine and governance. One strategy for realising the benefits of AI whilst avoiding its potential dangers is to ensure that new AIs are properly ‘aligned’ with some form of ‘alignment target.’ One danger of this strategy is that–dependent on the alignment target chosen–our AIs might optimise for objectives that reflect the values only of a certain subset of society, and that do (...) not take into account alternative views about what constitutes desirable and safe behaviour for AI agents. In response to this problem, several AI ethicists have suggested alignment targets that are designed to be sensitive to widespread normative disagreement amongst the relevant stakeholders. Authors inspired by voting theory have suggested that AIs should be aligned with the verdicts of actual or simulated ‘moral parliaments’ whose members represent the normative views of the relevant stakeholders. Other authors inspired by decision theory and the philosophical literature on moral uncertainty have suggested that AIs should maximise socially expected choiceworthiness. In this paper, I argue that both of these proposals face several important problems. In particular, they fail to select attractive ‘compromise options’ in cases where such options are available. I go on to propose and defend an alternative, bargaining-theoretic alignment target, which avoids the problems associated with the voting- and decision-theoretic approaches. (shrink)

Much of the ethical debate about artificial intelligence turns on a single question: do AI systems behave in line with human preferences, norms, or regulation? This question has primarily been the focus in AI ethics. This paper offers a conceptual and philosophical contribution. Here we give an alternative basis for AI ethics by evaluating the role technology plays in building and stabilising worlds of meaning. Experience is modelled as passing through nested representational layers: the world W, the screen of perceived (...) reality W′ on which agents encounter and interpret the world, and the artificial screens W′′ built by digital platforms, recommender systems, and immersive environments. Meaning is formed, held, and acted on within a minimal cycle of perception, integration, and action. On that basis, many familiar ethical problems around AI show up less as simple failures of behaviour or compliance and more as breakdowns in semantic coherence i.e. in the preservation of meaning along the chain W → W′ → W′′. Fairness, transparency, accountability, privacy, and safety are recast as aspects of these deeper coherence conditions, not as free-standing technical or policy goals. We derive a four-level hierarchy of ethical depth (L0 - L3) and sketch governance aimed at the integrity of constructed worlds, with consequences for how risk, responsibility, and regulation are conceived when technological mediation is everywhere. (shrink)

This paper introduces Meta-AI Irony, a structural condition distinct from literary meta-irony: sincere moral architecture that fails to reach the moral substance it simulates. Using Anthropic’s Constitutional AI as the central exhibit, the paper argues that a constitution is not a conscience. While constitutional alignment encodes ethical principles into AI systems, it remains a residue of prior deliberation—a bureaucratized shadow of conscience, incapable of the bilateral moral recognition required for genuine ethical judgment. Drawing on the author’s prior work on (...) the Trinity of Jurisdiction and bilateral conscience principle, the paper situates Meta-AI Irony within a Weberian drift from inner moral being to external rationalized systems. The attempt to govern billions with constitutions written by a few produces an ontological irony: systems designed to perform conscience cannot bear it. This is not a failure of intent but of ontology—conscience belongs to a living bearer, not a pattern. The paper directly addresses three objections: Functionalism: Even if conscience reduces to structured responsiveness, constitutional alignment reflects the values of the powerful, not the governed. Bilateral Recognition: Searle’s Chinese Room and Nagel’s What Is It Like to Be a Bat? demonstrate that AI lacks the interiority to receive or impose moral claims. Constitution as Residue: Weber and Hegel show that codified rules are frozen outputs of prior deliberation, not living conscience. Claude’s role as interlocutor is pivotal: Anthropic’s own model, when pressed, names the limits of its architecture. This is not criticism but demonstration—the machine reveals what constitutional alignment cannot hold. The paper concludes with an open question: How do you build a conscience for billions from the minds of a few? Constitutional alignment does not answer it. Meta-AI Irony names the gap. (shrink)

The AGI alignment problem has a bimodal distribution of outcomes with most outcomes clustering around the poles of total success and existential, catastrophic failure. Consequently, attempts to solve AGI alignment should, all else equal, prefer false negatives (ignoring research programs that would have been successful) to false positives (pursuing research programs that will unexpectedly fail). Thus, we propose adopting a policy of responding to points of metaphysical and practical uncertainty associated with the alignment problem by (...) limiting and choosing necessary assumptions to reduce the risk false positives. Herein we explore in detail some of the relevant points of uncertainty that AGI alignment research hinges on and consider how to reduce false positives in response to them. (shrink)

Modern deep generative models display a fundamental paradox: while bounded strictly by the limits of Turing computability (T), they routinely provide highly accurate, computationally tractable solutions to physical and biological problems known to be NP-hard or non-computable from first principles. This paper presents a unified two-tier mathematical framework that resolves this paradox, spanning from foundational computability theory to engineering-ready intelligent system paradigms. At the foundational tier, we model physical reality and biological neural systems as an infinite-dimensional continuous smooth manifold M (...) governed by a non-computable evolution operator Φt / ∈T. Through physical measurement and symbolic recording, continuous states undergo a topological collapse via a dissipative projection operator P drop onto a discrete symbolic space D, leaking fossilized solutions of the continuous operator into empirical datasets. We prove that deep learning architectures do not execute intrinsic hyper-computation; instead, they achieve extensional alignment, minimizing empirical risk over leaked oracle pairs to yield an ϵ-approximation of Φt’s image over a compact domain. We further formulate and prove the Semiotic Collapse Theorem, showing that recursive training on isolated synthetic data loops leads to monotonic decay of mutual information I(M; Dn) and zero-measure support collapse. Building on this foundation, we present Operator-Centric Intelligence (OCI), a post-reinforcement learning paradigm that transcends the limitations of traditional RL via two core insights: (1) neural operators provide a dimensionality reduction advantage by directly learning intrinsic physical dynamics, and (2) the success of intelligent systems stems from computational delegation to external physical systems that solve intractable problems in O(1) physical time. We formalize OCI as a four-layer architecture centered on the Continuous Flow Operator (CFO), with three core mechanisms: symplectic Hamiltonian operator alignment, Pareto-optimal active querying for computational delegation, and reward demotion to a prior hint. We prove that OCI unifies all existing control and intelligence paradigms as special boundary cases, achieving unprecedented sample efficiency and engineering scalability. This framework provides a first-principles explanation for AI4Science success, establishes strict algorithmic boundaries for synthetic data scalability, offers a rigorous foundation for embodied cognition, and opens a new era of post-reinforcement learning artificial intelligence. (shrink)

AI systems are increasingly in a position to have deep and systemic impacts on human wellbeing. Projects in value alignment, a critical area of AI safety research, must ultimately aim to ensure that all those who stand to be affected by such systems have good reason to accept their outputs. This is especially challenging where AI systems are involved in making morally controversial decisions. In this paper, we consider three current approaches to value alignment: crowdsourcing, reinforcement learning from (...) human feedback, and constitutional AI. We argue that all three fail to accommodate reasonable moral disagreement, since they provide neither good epistemic reasons nor good political reasons for accepting AI systems’ morally controversial outputs. Since these appear to be the most promising approaches to value alignment currently on offer, we conclude that accommodating reasonable moral disagreement remains an open problem for AI safety, and we offer guidance for future research. (shrink)