A method for assessing whether AI systems might be conscious is presented, drawing on existing neuroscientific theories of consciousness. The approach involves deriving indicators from such theories to inform beliefs about AI consciousness. This method can make progress because computational functionalist theories, which are influential, have empirically testable implications for AI. The work does not claim that any current AI is conscious but outlines a rigorous framework for future assessment.
Organizations involved in AI research should establish principles and policies to guide research, deployment, and public communication concerning consciousness, as it may be possible to build conscious AI systems now or in the near future. Conscious AI systems would arguably deserve moral consideration, and large numbers could be created and caused to suffer. Even if an organization chooses not to study AI consciousness, it still needs policies because developers risk inadvertently creating conscious entities. Five principles are proposed concerning research objectives, procedures, knowledge sharing, and public communications, with a call for voluntary public commitments.
No current AI systems are conscious, but there are no obvious technical barriers to building ones that might be, according to an analysis grounded in neuroscientific theories of consciousness. The report surveys prominent theories—recurrent processing, global workspace, higher-order, predictive processing, and attention schema—and derives computational indicator properties from them. Applying these indicators to recent AI systems yields no evidence of consciousness, but the authors argue that future systems could potentially implement the necessary properties.