2026-06 · Paper · Trends in Cognitive Sciences 30(6), 488-501
Identifying indicators of consciousness in AI systems

A method for judging whether an AI could be conscious by checking its inner workings against what theories of consciousness require, not by what it says.
Instead of asking a chatbot whether it feels anything, the authors take the core requirements of several brain theories and check whether an AI system's internal machinery meets them. This builds on their 2023 report, which concluded that no current AI system was a strong candidate.
Four guidelines for deriving indicators, e.g. indicators should target the central explanatory posits of a theory; illustrated with the indicator list from the 2023 report (arXiv:2308.08708, 19 authors, which drew on recurrent processing, global workspace, higher-order, predictive processing and attention schema theories and concluded no current AI systems are conscious but saw no obvious technical barriers to meeting the indicators). Issue June 2026 (vol 30, issue 6).
What we do with it
The rubric for our AI stress tests: we use it to find where theories disagree or give absurd answers, never as a verdict on AI and never scoring an AI's self-report. Planned
Read the original. Source checked against the original.