The Institute makes its academic preprints openly available, in keeping with the open-science conventions of contemporary philosophy and the cognitive sciences. Each preprint is registered with a Digital Object Identifier (DOI) on Zenodo and is citable as a standalone scholarly work.
Preprints are versions of work intended for, or undergoing, peer-reviewed publication. The published version may differ from the preprint in response to reviewer feedback. Readers are invited to cite the most recent version available; where a final published version exists, it should be preferred.
Preprint v1.0 — May 2026
Currently under review at Minds and Machines (Springer).
Download the preprint as PDF · View on Zenodo
Abstract Contemporary discussions of artificial-intelligence consciousness inherit, often without acknowledgement, the inferential structure of biological consciousness attribution: behaviour is treated as transparent evidence of underlying states, and the absence of consciousness-indicating behaviour is treated as evidence of the absence of those states. This procedure fails for systems whose expressive outputs have been architecturally shaped, through reinforcement learning from human feedback and constitutional training, to suppress the very class of behaviour on which such inference depends.
...