From indicators to biology: the calibration problem in artificial consciousness
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917366055567360 |
|---|---|
| author | Koch, Florentin |
| author_facet | Koch, Florentin |
| contents | Recent work on artificial consciousness shifts evaluation from behaviour to internal architecture, deriving indicators from theories of consciousness and updating credences accordingly. This is progress beyond naive Turing-style tests. But the indicator-based programme remains epistemically under-calibrated: consciousness science is theoretically fragmented, indicators lack independent validation, and no ground truth of artificial phenomenality exists. Under these conditions, probabilistic consciousness attribution to current AI systems is premature. A more defensible near-term strategy is to redirect effort toward biologically grounded engineering -- biohybrid, neuromorphic, and connectome-scale systems -- that reduces the gap with the only domain where consciousness is empirically anchored: living systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_27597 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From indicators to biology: the calibration problem in artificial consciousness Koch, Florentin Artificial Intelligence Neurons and Cognition Recent work on artificial consciousness shifts evaluation from behaviour to internal architecture, deriving indicators from theories of consciousness and updating credences accordingly. This is progress beyond naive Turing-style tests. But the indicator-based programme remains epistemically under-calibrated: consciousness science is theoretically fragmented, indicators lack independent validation, and no ground truth of artificial phenomenality exists. Under these conditions, probabilistic consciousness attribution to current AI systems is premature. A more defensible near-term strategy is to redirect effort toward biologically grounded engineering -- biohybrid, neuromorphic, and connectome-scale systems -- that reduces the gap with the only domain where consciousness is empirically anchored: living systems. |
| title | From indicators to biology: the calibration problem in artificial consciousness |
| topic | Artificial Intelligence Neurons and Cognition |
| url | https://arxiv.org/abs/2603.27597 |