LLMs don’t know anything: reply to Yildirim and Paul
Open accessThe claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Goddu et al. (2024) note that a system that has learned traffic light regularities may accurately predict the sequence of green, yellow, and red, but this amounts only to tracking regularities, not to understanding how the sequence could be changed.
“As noted by Goddu et al. (2024), a system that has learned traffic light regularities may accurately predict the sequence of green, yellow, and red, but this amounts only to tracking regularities, not to understanding how the sequence could be changed.”
From Toward Enactive Artificial Intelligence (2026) · cites this paper as Goddu et al. (2024)
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
The Book of Why: The New Science of Cause and Effect
Goldberg, L. R. (2019) · Notices of the American Mathematical Society · doi:10.1090/noti1912 · Cited by 1,654 · see citing works
Dickinson, A. (1994) · Animal Learning and Cognition · doi:10.1016/b978-0-08-057169-0.50009-7 · Cited by 200 · see citing works
The Impossibility of Automating Ambiguity
Birhane, A. (2021) · Artificial Life · doi:10.1162/artl_a_00336 · Cited by 175 · see citing works
(2019) · Cited by 135 · see citing works
How Organisms Come to Know the World: Fundamental Limits on Artificial General Intelligence
Roli, A., Jaeger, J., & Kauffman, S. A. (2022) · Frontiers in Ecology and Evolution · doi:10.3389/fevo.2021.806283 · Cited by 114 · see citing works
From task structures to world models: what do LLMs know?
Yildirim, I., & Paul, L. A. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2024.02.008 · Cited by 109 · see citing works
(1995) · Choice Reviews Online · doi:10.5860/choice.32-4482 · Cited by 97 · see citing works
Interventionist Theories of Causation in Psychological Perspective
Woodward, J. (2007) · doi:10.1093/acprof:oso/9780195176803.003.0002 · Cited by 89 · see citing works
The development of human causal learning and reasoning
Goddu, M. K., & Alison Gopnik, C. (2024) · Nature Reviews Psychology · doi:10.1038/s44159-024-00300-5 · Cited by 71 · see citing works
Self-citationThe Blind Spot: Why Science Cannot Ignore Human Experience
Frank, A., Gleiser, M., & Thompson, E. (2025) · Perspectives on Science and Christian Faith · doi:10.56315/pscf6-25frank
Self-citation
Flagged first, then by citations
Research works printed but not linked: 1
- Noë, A. (2023) The Entanglement: How Art and Philosophy Make Us Who We Are, Princeton University Press
Cited by
Sorted by citations
Is AI a Threat to Human Music? (a neo-Deweyan Perspective)
Haskins, C. (2025) · Journal of Aesthetics and Art Criticism · doi:10.1093/jaac/kpaf024 · Cited by 4 · see citing works
Sense-making reconsidered: large language models and the blind spot of embodied cognition
Froese, T. (2026) · Phenomenology and the Cognitive Sciences · doi:10.1007/s11097-025-10132-0 · Cited by 4 · see citing works
How Not to Collaborate With Large Language Models
Zebrowski, R. L. (2025) · Oxford University Press eBooks · doi:10.1093/9780198945215.003.0071 · Cited by 3 · see citing works
Response to Goddu et al.: new ways of characterizing and acquiring knowledge
Yildirim, I., & Paul, L. A. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2024.08.004 · Cited by 1 · see citing works
Knowledge in Animals and Machines
Paul, L. A. (2026) · Journal of Neuroscience · doi:10.1523/jneurosci.0939-25.2025 · Cited by 1 · see citing works
Sense-Making Reconsidered: Large Language Models and the Blind Spot of Embodied CognitionPreprint
Froese, T. (2025) · doi:10.31234/osf.io/w7hg4_v1 · Cited by 1 · see citing works
Kunwar, J. B. (2026) · Discourses on Culture · doi:10.2478/doc-2026-0006
Toward Enactive Artificial Intelligence
Rafiee, B., & Sutton, R. (2026) · arXiv · doi:10.48550/arxiv.2605.24238
Goddu, M. K. (2025) · Physics of Life Reviews · doi:10.1016/j.plrev.2025.07.001
Self-citationMoriguchi, Y., Watanabe, R., Hori, Y., & Reyes‐Jaquez, B. (2026) · Humanities and Social Sciences Communications · doi:10.1057/s41599-026-07511-6
Response to commentators on the blind spot: why science cannot ignore human experience
Thompson, E. (2026) · Phenomenology and the Cognitive Sciences · doi:10.1007/s11097-026-10146-2
Self-citationWard, D. (2026) · Adaptive Behavior · doi:10.1177/10597123261450094
- Authors
- Goddu, M. K., Noë, A., & Thompson, E.
- Affiliations
- Freie Universität Berlin (DE)
- University of British Columbia (CA)
- Corresponding author
- Thompson, Evan
- Venue
- Trends in Cognitive Sciences
- Publisher
- Elsevier BV
- Published
- 2024-11
- Volume
- 28
- Issue
- 11
- Pages
- 963-964
- ISSN
- 1364-6613 (ISSN-L)
- OpenAlex
- W4402622969
- Cited by
- 10
- References
- 9
- Citations by year
- 2026: 5 · 2025: 4 · 2024: 1
- FWCI
- 4.10
- Type
- journal article
- Language
- en
- Open access
- green
- philarchive.org
- Locations
- Trends in Cognitive Sciences (publishedVersion)
- PubMed (publishedVersion)
- PhilPapers (PhilPapers Foundation) (submittedVersion)
- Topics
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Philosophy and Theoretical Science
- Life Sciences › Neuroscience › Cognitive Neuroscience › Embodied and Extended Cognition
- Social Sciences › Arts and Humanities › History and Philosophy of Science › Cybernetics and Technology in Society
- Keywords
- large language models, instrumental knowledge, causal knowledge, task structure, prediction
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
