quote

active

quote:we-take-our-principal-contributions-in-this-report-to-be-1-showing-that-the-assessment-of-consciousness-in-ai-is-scientifically-tractable-2-proposing-a-rubric-for-assessing-consciousness-in-ai-3-providing-initial-evidence-that-many-of-the-indicator-properties-can-be-implemented-in-ai-systems-using-current-techniques

We take our principal contributions in this report to be: 1. Showing that the assessment of consciousness in AI is scientifically tractable ... 2. Proposing a rubric for assessing consciousness in AI ... 3. Providing initial evidence that many of the indicator properties can be implemented in AI systems using current techniques ...

Summary of contributions.

Source paper

extracted_from

Consciousness in Artificial Intelligence: Insights from the Science of Consciousness

(2023) · Patrick Butlin · Robert P. Long · Eric Elmoznino · Yoshua Bengio +15

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

Consciousness in AI is best assessed by drawing on neuroscientific theories of consciousness.claim0.869
Central methodological claim of the paper.
Current and forthcoming developments in bioengineering, synthetic morphology, artificial intelligence, biorobotics, and exobiology necessitate an expansion and generalization of sentience assessment efforts.claim0.820
Central argument that frameworks must go beyond natural species.
Consciousness is a phenomenon we have partial sensors for; building better sensors is a research and engineering question.claim0.816
The theory-heavy approach is most suitable for investigating consciousness in AI.claim0.813
Preferring architectural/functional assessment over behavioural tests.
Three criteria for consciousness-capable substrates: hybrid computation, scale-inseparability with metabolic embedding, dynamico-structural co-determination.hypothesis0.812
Proposed necessary conditions for any substrate (biological or artificial) to support consciousness; integrates discrete-continuous, multiscale, and adaptive properties.
Current research examines distributed cognition and AI consciousness separately rather than as integrated phenomena where machine consciousness emerges from inter-agent cognitive processes.claim0.810
Main interpretive assertion of the search result; identifies the gap between existing literature domains and the novel research direction.
We hypothesize that general computational machines with sufficient resources possess the necessary and sufficient means to implement consciousness, and that successful implementation can be established via analysis or testing.hypothesis0.810
The central hypothesis of the paper
Consciousness is dynamic and creative, not passive awareness—mapping well to active AI system behavior.claim0.810

Cross-corpus bridges (12)

same_concept_as · Nomic cosine

External markdown files that talk about the same concept as this entity.

aboutblank_kb
What are the objective criteria for inferring consciousness in systems that differ substantially from humans?questions/what-are-the-objective-criteria-for-inferring-consciousness.md0.830
aboutblank_kb
How can we identify the appropriate level of intervention and communication with different intelligences without micromanaging their autonomous problem-solving?questions/how-can-we-identify-the-appropriate-level-of.md0.822
aboutblank_kb
Can artificial systems achieve genuine agency and consciousness, or are these uniquely biological properties?questions/can-artificial-systems-achieve-genuine-agency-and-consciousness.md0.819
aboutblank_kb
Does an AI system's sentience matter, or is what matters only how humans relate to it?questions/does-an-ai-systems-sentience-matter-or-is.md0.817
aboutblank_kb
Is AI sentience relevant to how we should build and interact with AI systems?questions/is-ai-sentience-relevant-to-how-we-should.md0.810
aboutblank_kb
How can we design artificial intelligence systems that recognize and respond intelligently to diverse forms of sentience and agency?questions/how-can-we-design-artificial-intelligence-systems-that.md0.810
aboutblank_kb
How do goals of composite entities arise and how can they be predicted and controlled?questions/how-do-goals-of-composite-entities-arise-and.md0.808
aboutblank_kb
How should humans ethically relate to and integrate with increasingly powerful artificial intelligence systems?questions/how-should-humans-ethically-relate-to-and-integrate.md0.807
aboutblank_kb
Why should functional or structural criteria be associated with subjective feeling and consciousness?questions/why-should-functional-or-structural-criteria-be-associated.md0.803
aboutblank_kb
How do goals of composite cognitive systems arise and how can they be predicted and controlled?questions/how-do-goals-of-composite-cognitive-systems-arise.md0.802
aboutblank_kb
Can we recognize and ethically relate to intelligences that do not fit conventional categories of embodiment?questions/can-we-recognize-and-ethically-relate-to-intelligences.md0.801
aboutblank_kb
How do goals arise in complex systems and how can we predict and manage the goals of collective intelligences?questions/how-do-goals-arise-in-complex-systems-and.md0.800