Understanding

A Polyphonic Conception of AI Understanding

With Pierre Beckmann.

Argues that whether large language models understand what they talk about is a question both unavoidable and ill-framed: unavoidable because users must tell outputs that merit epistemic trust from those that do not, and no purely mathematical or statistical vocabulary can draw that line without reintroducing the concept of understanding in all but name; ill-framed because the inherited concept presupposes a single locus of understanding. Mechanistic interpretability instead reveals LLMs to be deeply polyphonic systems whose outputs emerge from parallel mechanisms of uneven reliability. Drawing on evidence of medical, mathematical, logical, and spatial understanding in LLMs, the paper engineers a conception fit for such systems: a model understands a domain insofar as it contains sound circuitry that tracks relevant structure and reliably recruits that circuitry to control its outputs—which turns seemingly idle metaphysical disputes into tractable empirical questions that can guide the allocation of trust.

AI, large language models, understanding, mechanistic interpretability, conceptual engineering, conceptual adaptation, explainable AI

Evolving Minds, Evolving Language: Metaphor as a Process of Conceptual Adaptation to Artificial Intelligence

Manuscript (+Slideshow)

Argues that cognitively loaded terms such as “understanding” and “reasoning,” when applied to large language models, are best understood neither literally nor as merely loose talk, but as metaphors that adapt our conceptual repertoire to new circumstances under pressure of conceptual needs. Drawing on the Strawson-Kant tradition on imagination and concept-application, inferentialist semantics, Bermudez’s theory of rational framing, and Gentner’s structure-mapping account of analogy, it develops a four-part framework: inferential transfer rather than referential transfer, the aptic normativity of conceptual needs, the empirical evaluation of transferred inferences through mechanistic interpretability, and the career of AI metaphors from novelty toward possible conventionalization. The result is a shift away from all-or-nothing disputes about the literal applicability of cognitive terms to AI toward graded and empirically tractable questions about which inferential transfers are apt, revealing why our cognitive vocabulary for AI is evaluatively and practically consequential.

AI, large language models, understanding, conceptual adaptation, aptic normativity, mechanistic interpretability

From Habitus to Systema: Keckermann and the Pedagogical Origins of Cognitive Systematicity

Under review

Argues that the early modern systema of knowledge began life around 1600 as a teaching machine, before it became a metaphysical or epistemological ideal. Scholastic learning had rested on the authority of the Church and on a habitus cultivated over years of disputation; after the Reformation, the new Protestant confessions had to train pastors and teachers rapidly and at scale. Tracing how Ramism made learning spatially surveyable and how Bartholomäus Keckermann’s Systema logicae (1600) joined Ramist method to Aristotelian substance, the paper shows that the system externalized cognitive order, transferring work once performed by formed persons and institutions into visible, reproducible structures of exposition. Philosophy, in Alsted’s formula, is a habitus in the mind and a systema outside it. The virtues of the new form were those of a mechanism: surveyability, reproducibility, and independence from any particular teacher. Reinforced by print and paper technologies, and dignified by a metaphysical warrant inherited from the Stoic systema mundi, the teaching machine would later be asked to certify truth and to ground impersonal authority. The paper ends by asking what the passage from Summa to systema compressed out—a question that returns whenever new technologies, from the card index to the algorithmically generated summary, promise to shorten the path to understanding.

systematicity, early modern philosophy, Keckermann, authority, genealogy, understanding

Re-Engineering the Concept of Understanding for AI

With Pierre Beckmann.

Argues that the concept of understanding needs to be re-engineered for artificial cognition in a way that is empirically informed by mechanistic interpretability research and theoretically informed by a grasp of the functions of the concept.

AI, large language models, understanding, conceptual engineering, mechanistic interpretability, functions of concepts

Why We Care about Understanding: Competence through Predictive Compression

With Pierre Beckmann.

Offers a unifying account of understanding by reverse-engineering the function of both the state and the concept. Argues that we care about understanding because it grounds robust competence. Our concept of understanding evolved as an efficient proxy to track this elusive property, allowing us to identify who to trust and learn from. This highlights the sociality of understanding and how it shapes the character of human understanding. Understanding is the result of convergent pressures to predict the world using cognitive models that are not only accurate, but also compressed enough to be stored, demonstrated, and transmitted.

understanding, functions of concepts, conceptual reverse-engineering, testimony, AI, explainable AI

Forms of Understanding in LLMs: A Crisis for Comprehension?

In The Routledge Handbook of Philosophy of AI. Leonard Dung, Guido Löhr, and Chris Ranalli (eds.). London: Routledge. Forthcoming. With Pierre Beckmann.

AI, large language models, understanding

Mechanistic Indicators of Understanding in Large Language Models

Philosophical Studies. 2026. With Pierre Beckmann. doi:10.1007/s11098-026-02513-1

Draws on detailed technical evidence from research on mechanistic interpretability (MI) to argue that while LLMs differ profoundly from human cognition, they do more than tally up word co-occurrences: they form internal structures that are fruitfully compared to different forms of human understanding, such as conceptual, factual, and principled understanding. We synthesize MI’s most relevant findings to date while embedding them within an integrative theoretical framework for thinking about understanding in LLMs. As the phenomenon of “parallel mechanisms” shows, however, the differences between LLMs and human cognition are as philosophically fruitful to consider as the similarities.

AI, large language models, mechanistic interpretability, understanding, world models, explainable AI