The paper proposes a framework for delineating how acquired representations expand a system’s cognitive repertoire without necessarily transferring the underlying capacities used to create them. It introduces a five-part attribution table—effective tracking, application of acquired structures, acquisition from explicit specifications, acquisition from identifying observations, and retention and reuse—to specify the limits of this enlargement. The framework is applied to examples such as Andrew Ng’s world‑model interpretation of Othello‑GPT and contemporary machine‑concept accounts, illustrating that even full application competence does not guarantee acquisition capacity and that acquiring a criterion from its description differs from finding it in examples.
arXiv:2603.21745v3 Announce Type: replace-cross Abstract: Large language models are the first systems to achieve high cognitive performance without clearly undergoing representation genesis: the tran...
arXiv:2509. 14474v3 Announce Type: replace Abstract: The debate around Artificial General Intelligence (AGI) remains open due to two fundamentally different goals: replicating human-level performance versus replicating human-like cognitive processes.
The paper argues that the Linear Representation Hypothesis (LRH) should not be treated as a single claim but as a family of claims differentiated by how representations are considered equivalent. It highlights that different equivalence notions preserve different structures, leading to metrics, probes, and interventions that may actually test distinct hypotheses. By formalizing these ideas with group actions, the authors provide a framework that clarifies how assumptions vary across metrics, reading points, and analysis stages, and they apply it to audit common representation quantities and recent interpretability analyses.
The article reviews how generative AI influences the long‑term retention of knowledge, skills, and judgment—collectively termed cognitive capital—in both individuals and organizations. It identifies four mechanisms (substitution of practice, scaffolding and feedback, metacognitive calibration, and organizational aggregation) through which AI interaction can either deplete or enhance cognitive capital, and proposes seven evidence‑based principles and five design levers for organizations. The authors argue that cognitive capital provides a multilevel framework for governing AI adoption and call for longitudinal, multilevel research to test their propositions.
arXiv:2608. 08159v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly reported to exhibit human-like neural and cognitive signatures, including concept cells, mental number lines, and cognitive maps.
arXiv:2607. 20972v1 Announce Type: new Abstract: Coding agents ship with one kind of memory: documents.
The paper proposes a minimal structural framework for cognitive representation and problem solving, emphasizing the role of context, invariance recognition, and representative selection. It introduces a Knowledge Space composed of a Concept Graph and a Procedure Graph to formalize these operations without relying on complex inference or learning mechanisms. Illustrative examples and a weak-solver demonstration show how proper representational organization can simplify problem solving and delineate success and failure conditions.
arXiv:2608. 16213v1 Announce Type: new Abstract: Intelligence is constituted by \textit{process} (iterative activity through which output emerges), not in the output itself.
arXiv:2607. 15883v1 Announce Type: cross Abstract: Large language models are broadly capable, yet in sustained one-to-one conversation they still read as flat: competent, responsive, and somehow not quite the presence of a mind.
arXiv:2601.21702v4 Announce Type: replace Abstract: We consider Representation Misdirection (RM), a class of large language model (LLM) unlearning methods that achieve forgetting by redirecting the l...
arXiv:2607. 00397v1 Announce Type: cross Abstract: Understanding how complex cognitive functions are organized within artificial systems is central to interpreting large language models (LLMs) and relating them to biological cognition.
The article presents a minimal working model for large language model (LLM) systems, emphasizing four key distinctions—pretraining vs. deployment, distribution vs. samples, types of memory, and task competence vs. agency. Using this framework, it diagnoses six common misconceptions about LLMs (next‑token prediction, regression to the mean, training‑data regurgitation, model memory, alignment, and understanding), explaining what each misconception captures correctly, where it conflates distinctions, and the implications for evaluation, design, and governance. The model is applied to AI policy language, illustrating how policy can misrepresent these distinctions and offering a diagnostic toolkit to correct such errors.