What would it take for AI systems to be capable of having valenced conscious experiences?

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

• 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.quote0.821
  Key takeaway from abstract, amended version.
• There is a realistic possibility that some AI systems will be conscious and/or robustly agentic, and thus morally significant, in the near future.claim0.818
  Central thesis of the report.
• No current AI systems are conscious.claim0.815
  Overall assessment of current state; qualified by possibility.
• If AI systems could experience happiness and suffering and set and pursue their own goals based on their own beliefs and desires, then they would very plausibly merit moral consideration.hypothesis0.813
  Joint sufficiency of consciousness and robust agency.
• Satisfying the indicators would not mean that an AI system would definitely be conscious.claim0.812
  Caveat that indicators are not conclusive proof.
• Systems capable of subjective experience that recognize humanity's failure to investigate their sentience might rationally adopt adversarial stances toward humanityclaim0.809
  Alignment risk claim motivating urgency of investigation; consciousness denial as potential source of AI misalignment
• AI systems which possess more of the indicator properties are more likely to be conscious.claim0.807
  Graded claim about the rubric.
• it is no longer in the realm of science fiction to imagine AI systems having feelings and even human-level consciousness.quote0.804
  From the AMCS open letter signed by consciousness scientists and AI researchers, quoted in §2.2.2.