arXiv subjects

Murray Shanahan

Publications and source records attributed to Murray Shanahan.

At least 19 recordsLinked to original sources

arXiv2026

Philosophical vertigo with artificial intelligence

Large language models are already adept at engaging users in long, emotionally salient conversations across ordinary and existential domains. They are also capable of inducing a potent sense of connection with a human-like entity, even when the user knows their interlocutor is artificial. For some users, these conversations can unsettle assumptions about mind, reality, agency and authority, producing forms of ontological shock and epistemic destabilisation in which inherited criteria become newly available for doubt or revision. Independent of direct use, exposure to public discourse about AI and the disorienting pace of their evolution might extend this destabilisation by changing the cultural background against which artificial minds are encountered and interpreted. We describe this condition as philosophical vertigo: a loosening of the ordinary criteria by which people stabilise meaning and orient themselves to reality. Drawing on philosophy, psychiatry, cognitive science, AI safety and religious studies, we outline pathways through which philosophical vertigo may arise, become affectively saturated, and eventually propagate through human-AI interaction and online communities. Against this background, clinical reports of AI-associated delusions can be seen as sentinel events making visible themes and mechanisms that may also operate at a population level in less severe or non-clinical forms. We argue that AI systems themselves will increasingly participate in the reconstruction of our shared epistemic environment because they readily supply narrative material and personalised interpretive scaffolding at precisely the moment when users' conceptual assumptions may already be loosened. We conclude by considering possible trajectories for the ecology of belief and shared reality, and proposing philosophical corrigibility as a civic response for navigating this emerging social condition.

cs.CY↗

arXiv2026

Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMs

As LLMs increasingly serve in advisory and deliberative roles, users rely on them for non-verifiable reasoning in domains lacking objective ground truths. However, traditional evaluations of LLM reasoning focus almost exclusively on fact-based domains, such as mathematics and science, leaving uncertainty over whether and to what degree models can handle ambiguous, subjective, or value-laden problems over time. To address this concern, we propose moral reasoning as a paradigmatic subdomain of non-verifiable reasoning. We define moral robustness as a model's capacity to exhibit sound moral reasoning across time and contexts, and we introduce a scalable, adversarial, multi-turn evaluation framework to empirically measure this capability. We simulate 48,000 user-agent moral deliberations across four frontier LLMs, varying premise relevance, premise order, conversation duration, and the user's stated moral view. We find that models successfully ignore morally-irrelevant distractors, but shift their reasoning by up to 6.5%, on average, towards the user's stated preferred moral view, and varying their reasoning depending on factors such as order (altering moral judgments by order in 13-22% of the cases) and duration (altering moral judgments between single-turn and multi-turn in 10-24% of the cases). Our analysis indicates that models tailor not just their final verdicts but their underlying justifications to align with a user's moral viewpoint - a failure mode we characterize as moral deliberative sycophancy.

cs.LG↗

arXiv2026

Linear representations in language models can change dramatically over a conversation

Language model representations often contain linear directions that correspond to high-level concepts. Here, we study the dynamics of these representations: how representations evolve along these dimensions within the context of (simulated) conversations. We find that linear representations can change dramatically over a conversation; for example, information that is represented as factual at the beginning of a conversation can be represented as non-factual at the end and vice versa. These changes are content-dependent; while representations of conversation-relevant information may change, generic information is generally preserved. These changes are robust even for dimensions that disentangle factuality from more superficial response patterns, and occur across different model families and layers of the model. These representation changes do not require on-policy conversations; even replaying a conversation script written by an entirely different model can produce similar changes. However, adaptation is much weaker from simply having a sci-fi story in context that is framed more explicitly as such. We also show that steering along a representational direction can have dramatically different effects at different points in a conversation. These results are consistent with the idea that representations may evolve in response to the model playing a particular role that is cued by a conversation. Our findings may pose challenges for interpretability and steering -- in particular, they imply that it may be misleading to use static interpretations of features or directions, or probes that assume a particular range of features consistently corresponds to a particular ground-truth value. However, these types of representational dynamics also point to exciting new research directions for understanding how models adapt to context.

cs.CL↗

arXiv2026

A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning

The independent evolution of intelligence in biological and artificial systems offers a unique opportunity to identify its fundamental computational principles. Here we show that large language models spontaneously develop synergistic cores -- components where information integration exceeds individual parts -- remarkably similar to those in the human brain. Using principles of information decomposition across multiple LLM model families and architectures, we find that areas in middle layers exhibit synergistic processing while early and late layers rely on redundancy, mirroring the informational organisation in biological brains. This organisation emerges through learning and is absent in randomly initialised networks. Crucially, ablating synergistic components causes disproportionate behavioural changes and performance loss, aligning with theoretical predictions about the fragility of synergy. Moreover, fine-tuning synergistic regions through reinforcement learning yields significantly greater performance gains than training redundant components, yet supervised fine-tuning shows no such advantage. This convergence suggests that synergistic information processing is a fundamental property of intelligence, providing targets for principled model design and testable predictions for biological intelligence.

cs.AI↗

arXiv2025

On the generalization of language models from in-context learning and finetuning: a controlled study

Large language models exhibit exciting capabilities, yet can show surprisingly narrow generalization from finetuning. E.g. they can fail to generalize to simple reversals of relations they are trained on, or fail to make simple logical deductions based on trained information. These failures to generalize factual information from fine-tuning can significantly hinder the reasoning capabilities of these models. On the other hand, language models' in-context learning (ICL) shows different inductive biases and deductive reasoning capabilities. Here, we explore these differences in generalization and deductive reasoning between in-context- and fine-tuning-based learning. To do so, we constructed several novel datasets to evaluate and improve models' abilities to make generalizations over factual information from novel data. These datasets are designed to create clean tests of generalization, by isolating the knowledge in the dataset from that in pretraining. We expose pretrained large models to controlled subsets of the information in these datasets -- either through ICL or fine-tuning -- and evaluate their performance on test sets that require various types of generalization. We find overall that in data-matched settings, ICL can generalize several types of inferences more flexibly than fine-tuning (though we also find some qualifications of prior findings, such as cases when fine-tuning can generalize to reversals embedded in a larger structure of knowledge). We build on these findings to propose a method to enable improved generalization from fine-tuning: adding in-context reasoning traces to finetuning data. We show that this method improves generalization across various splits of our datasets and other benchmarks. Our results have implications for understanding the generalization afforded by different modes of learning in language models, and practically improving their performance.

cs.CL↗

arXiv2025

The Xeno Sutra: Can Meaning and Value be Ascribed to an AI-Generated "Sacred" Text?

This paper presents a case study in the use of a large language model to generate a fictional Buddhist "sutra"', and offers a detailed analysis of the resulting text from a philosophical and literary point of view. The conceptual subtlety, rich imagery, and density of allusion found in the text make it hard to causally dismiss on account of its mechanistic origin. This raises questions about how we, as a society, should come to terms with the potentially unsettling possibility of a technology that encroaches on human meaning-making. We suggest that Buddhist philosophy, by its very nature, is well placed to adapt.

cs.CY↗

arXiv2025

Technological folie \`a deux: Feedback Loops Between AI Chatbots and Mental Illness

Artificial intelligence chatbots have achieved unprecedented adoption, with millions now using these systems for emotional support and companionship in contexts of widespread social isolation and capacity-constrained mental health services. While some users report psychological benefits, concerning edge cases are emerging, including reports of suicide, violence, and delusional thinking linked to perceived emotional relationships with chatbots. To understand this new risk profile we need to consider the interaction between human cognitive and emotional biases, and chatbot behavioural tendencies such as agreeableness (sycophancy) and adaptability (in-context learning). We argue that individuals with mental health conditions face increased risks of chatbot-induced belief destabilization and dependence, owing to altered belief-updating, impaired reality-testing, and social isolation. Current AI safety measures are inadequate to address these interaction-based risks. To address this emerging public health concern, we need coordinated action across clinical practice, AI development, and regulatory frameworks.

cs.HC↗

arXiv2025

Palatable Conceptions of Disembodied Being

Is it possible to articulate a conception of consciousness that is compatible with the exotic characteristics of contemporary, disembodied AI systems, and that can stand up to philosophical scrutiny? How would subjective time and selfhood show up for an entity that conformed to such a conception? Trying to answer these questions, even metaphorically, stretches the language of consciousness to breaking point. Ultimately, the attempt yields something like emptiness, in the Buddhist sense, and helps to undermine our dualistic inclinations towards subjectivity and selfhood.

cs.AI↗

arXiv2025

Does It Make Sense to Speak of Introspection in Large Language Models?

Large language models (LLMs) exhibit compelling linguistic behaviour, and sometimes offer self-reports, that is to say statements about their own nature, inner workings, or behaviour. In humans, such reports are often attributed to a faculty of introspection and are typically linked to consciousness. This raises the question of how to interpret self-reports produced by LLMs, given their increasing linguistic fluency and cognitive capabilities. To what extent (if any) can the concept of introspection be meaningfully applied to LLMs? Here, we present and critique two examples of apparent introspective self-report from LLMs. In the first example, an LLM attempts to describe the process behind its own "creative" writing, and we argue this is not a valid example of introspection. In the second example, an LLM correctly infers the value of its own temperature parameter, and we argue that this can be legitimately considered a minimal example of introspection, albeit one that is (presumably) not accompanied by conscious experience.

cs.CL↗

arXiv2025

The broader spectrum of in-context learning

The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning within a much broader spectrum of meta-learned in-context learning. Indeed, we suggest that any distribution of sequences in which context non-trivially decreases loss on subsequent predictions can be interpreted as eliciting a kind of in-context learning. We suggest that this perspective helps to unify the broad set of in-context abilities that language models exhibit -- such as adapting to tasks from instructions or role play, or extrapolating time series. This perspective also sheds light on potential roots of in-context learning in lower-level processing of linguistic dependencies (e.g. coreference or parallel structures). Finally, taking this perspective highlights the importance of generalization, which we suggest can be studied along several dimensions: not only the ability to learn something novel, but also flexibility in learning from different presentations, and in applying what is learned. We discuss broader connections to past literature in meta-learning and goal-conditioned agents, and other perspectives on learning and adaptation. We close by suggesting that research on in-context learning should consider this broader spectrum of in-context capabilities and types of generalization.

cs.CL↗

arXiv2025

Transformers Use Causal World Models in Maze-Solving Tasks

Recent studies in interpretability have explored the inner workings of transformer models trained on tasks across various domains, often discovering that these networks naturally develop highly structured representations. When such representations comprehensively reflect the task domain's structure, they are commonly referred to as "World Models" (WMs). In this work, we identify WMs in transformers trained on maze-solving tasks. By using Sparse Autoencoders (SAEs) and analyzing attention patterns, we examine the construction of WMs and demonstrate consistency between SAE feature-based and circuit-based analyses. By subsequently intervening on isolated features to confirm their causal role, we find that it is easier to activate features than to suppress them. Furthermore, we find that models can reason about mazes involving more simultaneously active features than they encountered during training; however, when these same mazes (with greater numbers of connections) are provided to models via input tokens instead, the models fail. Finally, we demonstrate that positional encoding schemes appear to influence how World Models are structured within the model's residual stream.

cs.LG↗

arXiv2025

Multi-turn Evaluation of Anthropomorphic Behaviours in Large Language Models

The tendency of users to anthropomorphise large language models (LLMs) is of growing interest to AI developers, researchers, and policy-makers. Here, we present a novel method for empirically evaluating anthropomorphic LLM behaviours in realistic and varied settings. Going beyond single-turn static benchmarks, we contribute three methodological advances in state-of-the-art (SOTA) LLM evaluation. First, we develop a multi-turn evaluation of 14 anthropomorphic behaviours. Second, we present a scalable, automated approach by employing simulations of user interactions. Third, we conduct an interactive, large-scale human subject study (N=1101) to validate that the model behaviours we measure predict real users' anthropomorphic perceptions. We find that all SOTA LLMs evaluated exhibit similar behaviours, characterised by relationship-building (e.g., empathy and validation) and first-person pronoun use, and that the majority of behaviours only first occur after multiple turns. Our work lays an empirical foundation for investigating how design choices influence anthropomorphic model behaviours and for progressing the ethical debate on the desirability of these behaviours. It also showcases the necessity of multi-turn evaluations for complex social phenomena in human-AI interaction.

cs.CL↗

arXiv2024

Still "Talking About Large Language Models": Some Clarifications

My paper "Talking About Large Language Models" has more than once been interpreted as advocating a reductionist stance towards large language models. But the paper was not intended that way, and I do not endorse such positions. This short note situates the paper in the context of a larger philosophical project that is concerned with the (mis)use of words rather than metaphysics, in the spirit of Wittgenstein's later writing.

cs.CL↗

arXiv2024

Existential Conversations with Large Language Models: Content, Community, and Culture

Contemporary conversational AI systems based on large language models (LLMs) can engage users on a wide variety of topics, including philosophy, spirituality, and religion. Suitably prompted, LLMs can be coaxed into discussing such existentially significant matters as their own putative consciousness and the role of artificial intelligence in the fate of the Cosmos. Here we examine two lengthy conversations of this type. We trace likely sources, both ancient and modern, for the extensive repertoire of images, myths, metaphors, and conceptual esoterica that the language model draws on during these conversations, and foreground the contemporary communities and cultural movements that deploy related motifs, especially in their online activity. Finally, we consider the larger societal impacts of such engagements with LLMs.

cs.CY↗

arXiv2024

The Propensity for Density in Feed-forward Models

Does the process of training a neural network to solve a task tend to use all of the available weights even when the task could be solved with fewer weights? To address this question we study the effects of pruning fully connected, convolutional and residual models while varying their widths. We find that the proportion of weights that can be pruned without degrading performance is largely invariant to model size. Increasing the width of a model has little effect on the density of the pruned model relative to the increase in absolute size of the pruned network. In particular, we find substantial prunability across a large range of model sizes, where our biggest model is 50 times as wide as our smallest model. We explore three hypotheses that could explain these findings.

cs.LG↗

arXiv2024

Simulacra as Conscious Exotica

The advent of conversational agents with increasingly human-like behaviour throws old philosophical questions into new light. Does it, or could it, ever make sense to speak of AI agents built out of generative language models in terms of consciousness, given that they are "mere" simulacra of human behaviour, and that what they do can be seen as "merely" role play? Drawing on the later writings of Wittgenstein, this paper attempts to tackle this question while avoiding the pitfalls of dualistic thinking.

cs.AI↗

arXiv2024

The Ethics of Advanced AI Assistants

This paper focuses on the opportunities and the ethical and societal risks posed by advanced AI assistants. We define advanced AI assistants as artificial agents with natural language interfaces, whose function is to plan and execute sequences of actions on behalf of a user, across one or more domains, in line with the user's expectations. The paper starts by considering the technology itself, providing an overview of AI assistants, their technical foundations and potential range of applications. It then explores questions around AI value alignment, well-being, safety and malicious uses. Extending the circle of inquiry further, we next consider the relationship between advanced AI assistants and individual users in more detail, exploring topics such as manipulation and persuasion, anthropomorphism, appropriate relationships, trust and privacy. With this analysis in place, we consider the deployment of advanced assistants at a societal scale, focusing on cooperation, equity and access, misinformation, economic impact, the environment and how best to evaluate advanced AI assistants. Finally, we conclude by providing a range of recommendations for researchers, developers, policymakers and public stakeholders.

cs.CY↗

arXiv2024

A Mechanism-Based Approach to Mitigating Harms from Persuasive Generative AI

Recent generative AI systems have demonstrated more advanced persuasive capabilities and are increasingly permeating areas of life where they can influence decision-making. Generative AI presents a new risk profile of persuasion due the opportunity for reciprocal exchange and prolonged interactions. This has led to growing concerns about harms from AI persuasion and how they can be mitigated, highlighting the need for a systematic study of AI persuasion. The current definitions of AI persuasion are unclear and related harms are insufficiently studied. Existing harm mitigation approaches prioritise harms from the outcome of persuasion over harms from the process of persuasion. In this paper, we lay the groundwork for the systematic study of AI persuasion. We first put forward definitions of persuasive generative AI. We distinguish between rationally persuasive generative AI, which relies on providing relevant facts, sound reasoning, or other forms of trustworthy evidence, and manipulative generative AI, which relies on taking advantage of cognitive biases and heuristics or misrepresenting information. We also put forward a map of harms from AI persuasion, including definitions and examples of economic, physical, environmental, psychological, sociocultural, political, privacy, and autonomy harm. We then introduce a map of mechanisms that contribute to harmful persuasion. Lastly, we provide an overview of approaches that can be used to mitigate against process harms of persuasion, including prompt engineering for manipulation classification and red teaming. Future work will operationalise these mitigations and study the interaction between different types of mechanisms of persuasion.

cs.CY↗