A Polyphonic Conception of AI Understanding

arXiv cs.AISeptember 30, 2026en

arXiv cs.AI

AI Global Wire

arXiv:2609.36079v1 Announce Type: new Abstract: When a doctor, a judge, or an engineer must decide whether to trust an AI model's output, they cannot avoid asking what the model understands. Purely mathematical or statistical descriptions struggle to distinguish trustworthy from untrustworthy outputs without reintroducing the question of AI understanding in all but name. Yet the question is ill-framed as it stands, because the inherited concept operates within a monophonic paradigm: the idea that a cognitive system's understanding of something must be localised to a single mechanism underpinning all the capacities conferred by such understanding. Drawing on a wide range of mechanistic eviden

This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.

• Forskning