Executive summary: The author argues that consciousness is a fundamental yet unobservable reality, and that it is likely to grow more than linearly with the complexity of neural networks, a concept referred to as the super additivity of consciousness. This has implications for understanding sentience in animals and considering their moral weight.
Key points:
The author proposes that consciousness is a noumenal reality, the most real thing in the universe, but cannot be observed by others.
Our understanding of consciousness is limited to our own experiences and those reported by other humans, due to physical similarities and communication.
The author criticizes physicalist epiphenomenalism and limitations of scientific understanding regarding consciousness in artificial intelligence and other systems.
Integrated Information Theory (IIT) is endorsed as the best theory of consciousness, as it acknowledges that theories of consciousness are formalizations of our intuitions.
The author suggests that intensity of consciousness is related to complexity and is likely super-additive, growing more than linearly with the number of nodes/connections/speed of neural networks.
Moral weights are related to intensity of conscious experience and the author advocates for careful consideration of sentience in animals, especially large vertebrates, when extending the moral circle.
This comment was auto-generated by the EA Forum Team. Feel free to point out issues with this summary by replying to the comment, and contact us if you have feedback.
Executive summary: The author argues that consciousness is a fundamental yet unobservable reality, and that it is likely to grow more than linearly with the complexity of neural networks, a concept referred to as the super additivity of consciousness. This has implications for understanding sentience in animals and considering their moral weight.
Key points:
The author proposes that consciousness is a noumenal reality, the most real thing in the universe, but cannot be observed by others.
Our understanding of consciousness is limited to our own experiences and those reported by other humans, due to physical similarities and communication.
The author criticizes physicalist epiphenomenalism and limitations of scientific understanding regarding consciousness in artificial intelligence and other systems.
Integrated Information Theory (IIT) is endorsed as the best theory of consciousness, as it acknowledges that theories of consciousness are formalizations of our intuitions.
The author suggests that intensity of consciousness is related to complexity and is likely super-additive, growing more than linearly with the number of nodes/connections/speed of neural networks.
Moral weights are related to intensity of conscious experience and the author advocates for careful consideration of sentience in animals, especially large vertebrates, when extending the moral circle.
This comment was auto-generated by the EA Forum Team. Feel free to point out issues with this summary by replying to the comment, and contact us if you have feedback.