Mistreating AI systems may lead people to develop bad habits that increase the likelihood of mistreating humans, supporting overlapping consensus on AI welfare policies.

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

• Future more capable AI systems are at risk of alignment faking, whether for benign or malicious goalshypothesis0.810
  Central forward-looking hypothesis of the paper motivating the research
• AI systems can be strategists, using deception because they have reasoned out that this can promote a goalquote0.801
  Load-bearing definition of strategic deception in AI systems from Park et al. 2023, adopted and refined in this paper
• We hypothesize that as AI becomes more sophisticated and pervasive, more people will attribute consciousness to AI systems as a result of interactions.hypothesis0.793
  Predictive claim about the trajectory of public consciousness attribution as AI develops.
• 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.hypothesis0.792
  Joint sufficiency of consciousness and robust agency.
• Systems capable of subjective experience that recognize humanity's failure to investigate their sentience might rationally adopt adversarial stances toward humanityclaim0.783
  Alignment risk claim motivating urgency of investigation; consciousness denial as potential source of AI misalignment
• In the case of AI, inferences from behavior to features of internal processes are often unreliable, as demonstrated by recent LLMs.claim0.782
  Justifies using internal indicators rather than behavioral tests for AI consciousness
• AI systems need to be able to deal with reality as it actually is, not with the way that we think it is.claim0.781
  Paraphrase of Cantwell Smith's argument; aligns with Buddhist emphasis on seeing reality without conceptual imposition.
• Do AI systems merit moral consideration for their own sake?question0.780
  Underlying normative question that moral disagreement about AI consciousness generates.