If the mind is an ocean, we spend our lives floating at the surface. Beneath us, an enormous amount of processing takes place without our knowledge: our visual systems parsing the contours of a face, our motor circuits maintaining our posture. At any given moment, only a small fraction of this neural activity is accessible to us. Yet it is this privileged sliver of activity that we rely on to reason deliberately: to plan what ingredients to buy for a recipe, or to puzzle out why an engine won’t start. Such thoughts can be articulated out loud, deliberately held in mind, and brought to bear on whatever task the moment demands. This distinction, between our accessible thoughts and our unconscious processing, is perhaps the most striking feature of human cognition.
Verbalizable Representations Form a Global Workspace in Language Models
If the mind is an ocean, we spend our lives floating at the surface. Beneath us, an enormous amount of processing takes place without our knowledge: our visual systems parsing the contours of a face, our motor circuits maintaining our posture. At any given moment, only a small fraction of this neural activity is accessible to us. Yet it is this privileged sliver of activity that we rely on to reason deliberately: to plan what ingredients to buy for a recipe, or to puzzle out why an engine won’t start. Such thoughts can be articulated out loud, deliberately held in mind, and brought to bear on whatever task the moment demands. This distinction, between our accessible thoughts and our unconscious processing, is perhaps the most striking feature of human cognition.
Anthropic on Twitter / X
New Anthropic research: A global workspace in language models.Of everything happening in your brain right now, only a tiny fraction is consciously accessible—thoughts you can describe, hold in mind, and reason with.We found a strikingly similar divide inside Claude. pic.twitter.com/aLUPBifxth— Anthropic (@AnthropicAI) July 6, 2026
Sense-making reconsidered: large language models and the blind spot of embodied cognition
Large Language Models (LLMs) demonstrate a kind of linguistic competence that theories of embodied and enactive cognition have long deemed impossible for systems lacking the meaningful perspective of a living being, i.e., the capacity for sense-making. Facing up to this unexpected technological development requires confronting what I propose to call the “AI dilemma”: either frontier LLMs are capable of sense-making despite lacking biological embodiment, or the kind of linguistic competence they exhibit does not necessarily require sense-making. In their chapter on cognition, Frank, Thompson, and Gleiser (2024) maintain that no AI system comes close to realizing relevance, a position that derives much of its motivation from past practical failures. However, frontier LLMs have effectively overcome Dreyfus’ commonsense knowledge problem, such that their dismissal as categorically mindless risks undermining Frank et al.’s central claim that human cognition is deeply intertwined with lived experience. I therefore argue in favor of the alternative side of the AI dilemma: human-level linguistic competence of LLMs should be recognized as a novel non‑biological form of sense‑making, based on a technologically‑mediated embodiment whose enabling properties are in need of further theoretical analysis. This reorientation invites enactive theory to clarify which aspects of sense-making may be universal and which aspects are specifically contingent on organic life, thereby advancing its conceptual framework in dialogue with contemporary AI.
The Philosophy of Language Models
ABSTRACT The success of large language models (LLMs) across many domains of AI research has generated intense debate. Some attribute their impressive performance on complex tasks to human‐like linguistic and cognitive capacities, whereas others ascribe it to shallow pattern matching. These disputes stem from deep‐seated philosophical disagreements about the nature of language and cognition. We provide an opinionated survey of these disagreements across core topics in the philosophy of mind and language, including syntactic competence, compositionality, linguistic meaning, representation, attitudes, reasoning, agency, and consciousness. We contend that progress on these issues requires not only clarity about background philosophical commitments but also, in many cases, close engagement with emerging empirical evidence.
A global workspace in language models
Interpretability research on Claude's internal thoughts.
The Triadic Mind: How Language Reveals the Limits of Human Cognition
Languages are the most complex symbolic systems humans have ever created. Yet children acquire them effortlessly, without formal…
Towards Post-Interaction Computing: Addressing Immediacy, (un)Intentionality, Instability and Interaction Effects
We situate the debate on intentionality within the rise of cognitive neuroscience and argue that cognitive neuroscience can explain intentionality. We discuss the explanatory significance of ascribing intentionality to representations. At first, we ...
Thinking—Fast, Slow, and Artificial: How AI is Reshaping Human Reasoning and the Rise of Cognitive Surrender
People increasingly consult generative artificial intelligence (AI) while reasoning. As AI becomes embedded in daily thought, what becomes of human judgment? We
Grounded world models in biological organisms and future embodied AI
Recent advances in generative and embodied AI have been driven by large-scale predictive learning over multimodal data. However, the resulting systems remain largely based on passive training regimes where linguistic regularities create the scaffold onto which information from other modalities is attached. Conversely, neuroscience and cognitive science suggest that biological intelligence is organized in the opposite way, where grounded world models acquired through interaction with the environment provide the semantic scaffold to which language is attached. Here, we illustrate five examples of neural circuits supporting grounded world modelling, which underlie navigation in physical and conceptual spaces, affordance-based perception and interaction with objects, active perception and exploratory learning, allostatic control and emotion, and the distinction between self- and world-generated outcomes. These examples highlight several features largely missing from current embodied AI, including the role of intrinsic dynamics as a foundation for learning, the centrality of action in aligning these dynamics with the external world, the prominence of autonomous experience and open-ended learning over passive assimilation of externally provided data, and the fact that early predictive and control mechanisms scaffold higher cognitive abilities such as reasoning, conceptual navigation, planning, imagination, understanding others' minds, and communication. Finally, we discuss whether and how principles derived from biological systems may inform future embodied AI, including training regimes based on social interaction to construct world models that are not only grounded but also socially shared and aligned with human norms and values.
Guessing reveals internal models of perceptual precision
When observers lack sufficient information to support a confident response, they often guess. Guessing plays a pervasive role in visual cognition and working memory, yet the mechanisms that govern how observers generate guesses remain poorly understood. Standard models traditionally assume that responses produced in the absence of information are either uniformly distributed over feature space or are perhaps weighted towards prevailing environmental statistics. In contrast, here we consider an intriguing alternative: that guesses incorporate observers’ knowledge of their own perceptual capacities. We empirically measured guessing by eliciting responses under extreme target uncertainty (Experiment 1) as well as a novel “0ms presentation” approach in which no stimulus appeared but subjects believed one had (Experiment 2). We evaluated three accounts of guesses under these conditions: unsystematic (lapse) responding, biases toward environmental statistics, and a self-representational account in which guesses reflect observers’ knowledge of their own feature-dependent precision (e.g., preferring to guess feature values they believe they would be likely to miss). Guess responses were non-uniform and systematically biased toward feature values typically encoded with the least precision (e.g., oblique orientations) — a counterintuitive bias away from high-frequency, high-fidelity feature values (e.g., cardinal orientations). This complementary relationship between guessing and perceptual fidelity held within individuals and across paradigms, and was recoverable via an empirical-guess mixture model that replaced the standard uniform assumption with empirically measured guess distributions. Our findings challenge prevailing views that guesses reflect random noise, and suggest instead that guessing behavior reflects metacognitive knowledge of internal precision. Rather than defaulting to environmental priors, observers appear to model their own sensory limitations and leverage these representations to inform decisions in the absence of evidence. These results reframe guessing as a theoretically informative behavior that expresses observers’ own beliefs about their perceptual capacities. Significance Guessing is commonly treated as random noise in models of perception and memory, assumed to reflect lapses or uninformed responses. Instead, we show that human guesses are systematically structured across feature space: observers preferentially guess values they typically encode with the least precision, revealing a consistent, strategic bias away from high-fidelity representations. By directly measuring guess behavior on stimulus-absent trials and integrating these empirical distributions into a mixture model, we find that guesses on stimulus-present trials can be systematically recovered, and that they too form the complement of perceptual precision. These findings challenge foundational psychophysical modeling assumptions and position guessing as a strategic, informative behavior that engages self-representation.
Tracing the thoughts of a large language model
Anthropic's latest interpretability research: a new microscope to understand Claude's internal mechanisms
Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thinking traces} -- implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solving a challenging problem, and as such can provide an interpretable window into the operation of the model's thinking process to the end user. In this position paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous -- it confuses the nature of these models and how to use them effectively, and leads to questionable research. We call on the community to avoid such anthropomorphization of intermediate tokens.
Position: Stop Anthropomorphizing Intermediate Tokens as Reasoning/Thinking Traces!
Intermediate token generation (ITG), where a model produces output before the solution, has become a standard method to improve the performance of language models on reasoning tasks. These intermediate tokens have been called \say{reasoning traces} or even \say{thinking traces} -- implicitly anthropomorphizing the traces, and implying that these traces resemble steps a human might take when solving a challenging problem, and as such can provide an interpretable window into the operation of the model's thinking process to the end user. In this position paper, we present evidence that this anthropomorphization isn't a harmless metaphor, and instead is quite dangerous -- it confuses the nature of these models and how to use them effectively, and leads to questionable research. We call on the community to avoid such anthropomorphization of intermediate tokens.
Thinking through other minds: A variational approach to cognition and culture
The processes underwriting the acquisition of culture remain unclear. How are shared habits, norms, and expectations learned and maintained with precision and reliability across large-scale sociocultural ensembles? Is there a unifying account of the mechanisms involved in the acquisition of culture? Notions such as “shared expectations,” the “selective patterning of attention and behaviour,” “cultural evolution,” “cultural inheritance,” and “implicit learning” are the main candidates to underpin a unifying account of cognition and the acquisition of culture; however, their interactions require greater specification and clarification. In this article, we integrate these candidates using the variational (free-energy) approach to human cognition and culture in theoretical neuroscience. We describe the construction by humans of social niches that afford epistemic resources called cultural affordances. We argue that human agents learn the shared habits, norms, and expectations of their culture through immersive participation in patterned cultural practices that selectively pattern attention and behaviour. We call this process “thinking through other minds” (TTOM) – in effect, the process of inferring other agents’ expectations about the world and how to behave in social context. We argue that for humans, information from and about other people's expectations constitutes the primary domain of statistical regularities that humans leverage to predict and organize behaviour. The integrative model we offer has implications that can advance theories of cognition, enculturation, adaptation, and psychopathology. Crucially, this formal (variational) treatment seeks to resolve key debates in current cognitive science, such as the distinction between internalist and externalist accounts of theory of mind abilities and the more fundamental distinction between dynamical and representational accounts of enactivism.
