Mindscape Collective is now The Consciousness Library. Same library, new name. You may need to sign in again. About the change
Skip to content

Colin Klein

4 papers in the library · 6 citations · publishing 2020-2026

Papers

Phenomenal interface theory: a model for basal consciousness.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences November 13, 2025 Colin Klein, Andrew B Barron 6 citations

Phenomenal consciousness arises in mobile animals with spatial senses and goal-directed behavior as a solution to the problem of selecting among competing actions. To choose between goals, the brain must combine sensory inputs, internal states, and learned values into a common framework—a phenomenal interface—that computes multi-objective Q-values. Using insects as a model, the authors argue this processing naturally creates a distinction between self and non-self and a first-person perspective where external stimuli carry subjective value. The theory has implications for understanding the evolution and distribution of consciousness and highlights a problem for how consciousness might have expanded from its simplest origins.

Identifying indicators of consciousness in AI systems.

Trends in Cognitive Sciences June 1, 2026 Patrick Butlin, Robert Long, Tim Bayne et al.

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.

Consciousness in Artificial Intelligence: Insights from the Science of Consciousness

arXiv Preprint Archive August 17, 2023 Patrick Butlin, Robert Long, Eric Elmoznino et al.

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.

How experimental neuroscientists can fix the hard problem of consciousness.

Neuroscience of Consciousness January 1, 2020 Colin Klein, Andrew B Barron

For materialists, the hard problem of consciousness is an explanatory gap: why does brain activity produce experience rather than nothing at all? This paper argues that the interventionist theory of explanation, which relies on systematic experimental interventions and invariant generalizations, can help move beyond that gap. The authors propose that second-order interventions—interventions that alter the relationship between first-order interventions and conscious experience—are key, just as they were for other scientific mysteries. They also suggest that safe, reliable self-intervention can address both the hard problem and the meta-problem (why the hard problem feels so intractable). Current intervention strategies are evaluated for improvement.