Scaling supervision through AI self-improvement is feasible and may be necessary as AI capabilities advance.

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

• Scale is sufficient but not necessarily efficient to reach high levels of intelligence; different methods can scale with different efficiency levelsclaim0.793
  Implication of PRH for 'scale is all you need' argument
• Scaling intelligence via expansion of cognitive boundaries through inclusion of others' stress-reduction in one's own homeostatic loops.claim0.785
  Central thesis: expanding an agent's sensors and goals outward to include others' states creates bidirectional feedback loop that scales intelligence and increases compassion.
• Scaling Supervisionframework0.776
  Techniques that leverage AI to help humans more efficiently supervise AI.
• We would like to train AI systems that remain helpful, honest, and harmless, even as some AI capabilities reach or exceed human-level performance.quote0.775
  Foundational motivation for the research.
• Online training with AI supervision can fully automate the process of keeping the preference model on-policy.hypothesis0.767
  Section 6.1 suggests iterated online training with AI feedback as automation.
• If an AI system could be a welfare subject and moral patient, then many model instances could be run after training, scaling up the problem rapidly.hypothesis0.767
  Scalability concern.
• The training of modern AI systems already induces experience at scaleclaim0.766
  The ethical implication of the identity thesis applied to gradient-based AI training
• Patterns in AI self-reports should be compared across different models to identify structural commonalities.claim0.765