flâneur

A Paradigm for AI Consciousness – Opentheory.net

opentheory.net · 10,010 words · saved by 2 readers

Michael Edward Johnson, Symmetry Institute. 12 June, 2024. Crossposted from the Seeds of Science journal; available as a PDF there. Abstract: How can we create a container for knowledge about AI consciousness? This work introduces a new framework based on physicalism, decoherence, and symmetry. Major arguments include (1) physics is a more sturdy ontology for grounding consciousness than Turing-level computation, (2) Wolfram’s ‘branchial space’ is a better measure of an object’s “true shape” than spacetime, (3) electromagnetism is a good proxy for branchial shape, (4) brains and computers have significantly different shapes in branchial space, (5) symmetry considerations will strongly inform a future science of consciousness, and (6) computational efficiency considerations may broadly hedge against “s-risk”. I. AI consciousness is in the wind AI is the most rapidly transformative technology ever developed. Consciousness is what gives life meaning. How should we think about the intersec

A Paradigm for AI Consciousness Posted on June 12, 2024 June 3, 2025 by Michael Edward Johnson Michael Edward Johnson, Symmetry Institute. 12 June, 2024. Crossposted from the Seeds of Science journal; available as a PDF there. Abstract : How can we create a container for knowledge about AI consciousness? This work introduces a new framework based on physicalism, decoherence, and symmetry. Major arguments include (1) physics is a more sturdy ontology for grounding consciousness than Turing-level computation, (2) Wolfram’s ‘branchial space’ is a better measure of an object’s “true shape” than sp

saved by

related reading