This paper presents the Nemosine Framework, a modular cognitive architecture designed to support assisted reasoning, structured thinking, and systematic analysis. The model operates through functional cognitive modules ("personas") that organize tasks such as planning, evaluation, cross-checking, and narrative synthesis. The framework combines principles from metacognition, distributed cognition, and modular cognitive systems to offer an operational structure for assisted problem-solving and decision support. The architecture is documented through formal specification, internal consistency criteria, and reproducible structural components. The goal is to provide a clear conceptual basis for future computational implementations and to contribute to the study of symbolic-modular architectures for reasoning.
Large language models are increasingly involved in persistent and longitudinal human interaction. While current discussions often focus on memory, personalization, or agentic behavior, less attention has been given to the emergence of perceived cognitive continuity across extended interactional systems. This paper proposes the concept of cognitive continuity as the persistent re-emergence of structurally coherent symbolic patterns within human-LLM interaction over time. Rather than treating such continuity as evidence of autonomous consciousness or independent agency, the paper argues that it emerges relationally through iterative symbolic stabilization between user and model. The framework distinguishes cognitive continuity from memory retention, roleplay, and conventional personalization, proposing symbolic modularity and longitudinal coherence as central conditions for persistence. A central prediction is that cognitive continuity may survive model replacement when relational symbolic organization is preserved, while collapsing despite model persistence when that organization is lost. The paper further discusses implications for extended cognition, neurodivergent cognitive scaffolding, human-AI interaction design, and the philosophy of mind.
This paper examines the epistemic status of AI-assisted symbolic cognitive systems and argues that such systems are frequently subject to a persistent category error. Rather than being assessed as empirical theories of cognition, complete computational architectures, or psychological models, these systems are more appropriately understood as epistemic artifacts with an intermediate methodological function. Drawing on classical contributions from the philosophy of science and cognitive science-including research programmes, heuristic reasoning, and distributed cognition-the paper clarifies the type of epistemic work these systems perform. It proposes criteria for their proper evaluation, emphasizing internal coherence, organizational power, and conceptual clarity, while explicitly rejecting demands for direct empirical validation or computational performance as methodologically misplaced. By repositioning AI-assisted symbolic systems within the landscape of scientific inquiry, the paper aims to enable more accurate criticism, responsible development, and cumulative theoretical progress.
Large language model (LLM)–based agents are increasingly deployed with explicit role definitions and task constraints. However, the stability of such identities under adversarial or conflicting informational demands remains underexplored. In this work, we introduce prompt volatility as a measurable property of agent design, defined as the sensitivity of role adherence to the initial prompt specification. We present a minimal, reproducible benchmark that evaluates identity stability by subjecting agents to controlled perturbations, including role attacks, noise injections, and contradictory instructions. Using identical perturbation protocols, we compare two agents differing only in the strength of their initial prompt constraints. Empirical results show that weakly specified (junior) prompts exhibit significantly higher behavioral variance and reduced identity stability, while strongly constrained (senior) prompts remain invariant across runs. These findings demonstrate that prompt configuration functions as a critical initial condition for agent behavior, directly impacting robustness against role drift. The proposed benchmark provides a lightweight baseline for evaluating prompt volatility and offers a foundation for future studies on agent reliability, safety, and long-horizon behavior in LLM-based systems.
Consciousness remains one of the most persistent problems in philosophy and cognitive science. Despite substantial advances in neuroscience, no consensus exists regarding how physical processes give rise to subjective experience. This paper proposes an evolutionary hypothesis according to which consciousness emerges from the interaction of three fundamental dimensions: neural integration of sensory information, the continuous influence of internal bodily states, and the capacity to simulate and anticipate possible scenarios. Within this framework, conscious experience is interpreted not as a mere byproduct of neural processing but as the phenomenological manifestation of a biological system capable of integrating multiple streams of information to construct a model of the organism situated in its environment. The paper develops the thesis that human consciousness can be understood as the result of an evolutionary simulation system that integrates external perception and internal bodily states within a phenomenal field structured around a bodily located self. Once established, this system may have exceeded its original adaptive functions, supporting complex forms of self-reflection, symbolic language, and cumulative culture. The proposal is also intended as an analysis of how contemporary cognitive science constructs explanatory models of consciousness, connecting neural mechanisms, embodied processes, and evolutionary function.
A shared computing quota took two applications offline simultaneously after a code change intended to reduce dashboard polling. The available evidence identifies the scope of the suspension and the routines that changed, but cannot establish CPU savings. This technical note compares four deployment arrangements for enterprise systems serving multiple organizational units: shared commercial cloud hosting, centralized institutional infrastructure, per-unit installation, and local operation with central consolidation. It follows a record update from the initial write to the display, identifying authority over the data, limits on visibility across units, and the components needed during an outage. Two UML diagrams illustrate deployment boundaries and recovery after a lost acknowledgment. A third figure shows how local installations exchange data with a central service. The note proposes criteria for assessing polling costs, release distribution, fault diagnosis, and provider substitutability. The evaluation scenarios are analytical proposals.