book
active
book:surfing-uncertaintySurfing Uncertainty
Clark's foundational work on predictive processing and the embodied mind
Extracted from this book
Claims (19)
- A system is conscious if it implements self-organized second-order perception that increases global coherenceCIMC's current operational definition, precise enough to generate predictions while subject to revision
- Coherence maximization across simultaneously active mental models is related to prediction error minimization in the FEP, but the relationship is one of compatibility rather than strict equivalenceCIMC's position on the relationship between its coherence hypothesis and Friston's FEP
- Consciousness is not prediction error resolution as such but the second-order perception that orchestrates coherence across models being maintained and updatedCIMC's differentiation from predictive processing: specifying which pattern within predictive processing constitutes consciousness
- Consciousness is not the global broadcast itself but the second-order perception that orchestrates coherence across representations competing for and achieving global accessCIMC's differentiation of its account from GWT: it explains the dynamics underlying GWT rather than equating consciousness with broadcast
- Consciousness remains without an agreed scientific characterization, without a validated theory connecting mechanism to experience, and without criteria for establishing its presence or absence in any systemCIMC's characterization of the current state of the field motivating its research program
- IIT is incompatible with computationalist functionalism because Phi is defined as intrinsic to physical causal structure, allowing two functionally identical systems to differ in consciousnessCIMC's explicit rejection of IIT as operating outside the representationalist and functionalist framework
- In its minimal state, conscious experience may contain nothing but the bare registration of its own occurrence, requiring only that the perceptual process is present within the field it createsCIMC's account of minimal phenomenal experience as the target for research and construction
- It is functions all the way down: physical substrate refers only to a particular representational medium implemented as discernible differencesRadical functionalist claim grounding computationalism: no substrate is metaphysically privileged over its functional description
- Pain and suffering are not physical events at the boundary between agent and world but representational states created within the mind as an expression of a mismatch between regulation targets and the agent's model of its present stateGrounds the possibility that artificial conscious agents might be designed not to suffer
- Phenomenology itself is a functional structure; phenomenology is the modelCore resolution claim: phenomenal experience and its functional role coincide; resolving this is key to closing the Hard Problem
- Philosophy and construction must discipline each other: philosophy generating hypotheses precise enough to guide implementation, construction demanding the specificity that philosophy tends to deferCIMC's methodological position on the necessary interaction between philosophical and technical work
- Strong Enactivism is incompatible with CIMC's representationalist framework because it denies the role of internal representation altogetherCIMC is sympathetic to weak embodied approaches but rejects the constitutive claim of strong enactivism
- Tests of performance on specific tasks, including language modeling, are insufficient for determining consciousness statusSystems directly optimized for output can produce it without the prerequisite processes for conscious experience; simplest explanation for LLM consciousness reports is pattern matching
- The challenge of the Hard Problem is not in explaining it away but in giving an account of phenomenality as the specific kind of structured representation it isCIMC's distinctive position distinguishing itself from eliminativist and deflationary responses to the Hard Problem
- The construction of consciousness is the most promising path to understanding itInspired by Feynman's dictum; grounds CIMC's constructive methodology over purely philosophical analysis
- The field of artificial consciousness research remains fragmented across communities whose methods constrain the kind of progress each can makeCIMC's justification for its distinctive position in the research landscape
- The functionalist denies the coherence of philosophical zombies: experience, insofar as it has any determinable character, is itself a functional propertyCore argument against essentialism: there is no property of consciousness over and above its functional manifestations
- The personalities elicitable from language models are attractors in the embedding space of human linguistic behaviorGrounds the artificial psychology research direction: LLM personalities reflect the basins into which human selves tend to fall
- What Attention Schema Theory proposes was addressed a decade earlier by Metzinger in Being No One section 6.5 as the Phenomenal Model of the Intentionality RelationHistorical priority claim noting Metzinger's anticipation of Graziano's AST
Findings (1)
- Diverse computer vision models trained on visual recognition tasks converge to remarkably similar internal feature representations regardless of architecture, training procedure, or implementation details, closely matching the organization of animal visual cortexEmpirical evidence for the universality hypothesis cited as supporting the possibility of convergent consciousness-like solutions
Hypotheses (5)
- Consciousness is the simplest learning algorithm discoverable by evolutionary search to train a self-organizing biological substrate to become intelligent in service of agencyCIMC's specific account of what consciousness is and why it evolved
- Consciousness precedes complex cognition and is present in infants before perception, self-modeling, language, and reasoning have maturedThe developmental ordering argument supporting consciousness as the bootstrap mechanism for intelligence
- Different learning systems facing similar computational problems will converge to similar consciousness-like solutions, including potentially biological and artificial systemsExtension of the Universality Hypothesis to consciousness: if consciousness solves a well-defined computational problem, different systems will discover it independently
- General computational machines with sufficient resources possess the necessary and sufficient means to implement consciousnessCIMC's central testable hypothesis grounding the entire research program
- It may be possible to design artificial conscious agents that need not sufferClaim that since pain is a representational state, artificial conscious agents might be designed to lack it or control it
Neighborhood — ranked by edge-count
Thinkers (1)
thinker
- Andy Clarkauthored