Building AI systems with more indicator properties will increase the likelihood of consciousness.

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

• AI systems which possess more of the indicator properties are more likely to be conscious.claim0.874
  Graded claim about the rubric.
• There are no obvious technical barriers to building AI systems which satisfy the indicator properties.claim0.841
  Feasibility claim about near-term conscious AI.
• Consciousness in AI is best assessed by drawing on neuroscientific theories of consciousness.claim0.836
  Central methodological claim of the paper.
• Satisfying the indicators would not mean that an AI system would definitely be conscious.claim0.834
  Caveat that indicators are not conclusive proof.
• 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.quote0.831
  Key takeaway from abstract, amended version.
• Consciousness is a phenomenon we have partial sensors for; building better sensors is a research and engineering question.claim0.812
• Can we develop better behavioural tests for consciousness in AI that are difficult to game?question0.811
  Open question from Box 4.
• The capacity for unlimited associative learning is not a good indicator for consciousness in AI.claim0.810
  Rejecting UAL as a reliable indicator for artificial systems.