claim

active

claim:ai-systems-which-possess-more-of-the-indicator-properties-are-more-likely-to-be-conscious

AI systems which possess more of the indicator properties are more likely to be conscious.

Graded claim about the rubric.

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

Neighborhood — ranked by edge-count

Papers (1)

paper

Consciousness in Artificial Intelligence: Insights from the Science of Consciousness
introduces

Communities (2)

community

Alive AI interface ethics & design
members_of
Explores aliveness, aesthetics, welfare, and ethical responsibility in AI interaction design.
Intelligence as adaptive plasticity and observer-dependent measurement
members_of
Frameworks recognizing that intelligence, consciousness, and biological organization emerge from adaptive capacity and observer limitations, spanning AI systems to developmental biology through 2020s research.

Artifacts (1)

artifact

Indicator Properties Rubric
supports
A list of 14 indicator properties derived from scientific theories to assess consciousness likelihood in AI.

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.

Satisfying the indicators would not mean that an AI system would definitely be conscious.claim0.882
Caveat that indicators are not conclusive proof.
Building AI systems with more indicator properties will increase the likelihood of consciousness.hypothesis0.874
Guiding hypothesis of the rubric.
our analysis suggests that no current AI systems are conscious, but also suggests that there are no obvious technical barriers to building AI systems which satisfy these indicators.quote0.873
Key takeaway from abstract, amended version.
There are no obvious technical barriers to building AI systems which satisfy the indicator properties.claim0.848
Feasibility claim about near-term conscious AI.
No current AI systems are conscious.claim0.845
Overall assessment of current state; qualified by possibility.
Consciousness in AI is best assessed by drawing on neuroscientific theories of consciousness.claim0.842
Central methodological claim of the paper.
There is a realistic possibility that some AI systems will be conscious and/or robustly agentic, and thus morally significant, in the near future.claim0.839
Central thesis of the report.
Many of the indicator properties can be implemented in AI systems using current techniques.claim0.825
Feasibility demonstrated in Section 3.1.