New work on AI consciousness: a test, welfare interviews and attributions of consciousness
One text argues that asking models does not settle the question of AI consciousness, so a test is needed, and a preprint analyses six cold-start AI welfare interviews. A Minds and Machines article examines whether attributions of consciousness to chatbots are epistemically innocent (17–18 August 2026).
Sources
- A test for AI consciousness | Vuink.comvuink.com · Aug 17, 2026
- Not the Model: Entity-of-Concern and Continuity Affordance as Observation Variables in AI Welfare Interviewsapartresearch.com · Aug 17, 2026
- Are Attributions of Consciousness to AI Chatbots Epistemically Innocent? | Minds and Machines | Springer Nature Linklink.springer.com · Aug 18, 2026
Machine-generated summary based on the titles and excerpts of the source articles. The facts come from the linked article.