Neural self-other overlap provides a hard-to-fake metric for classifying deceptive vs honest agents

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

• Neural self-other overlap in humans mediates empathy and inversely predicts deceptive behavior, motivating the SOO approach for AIclaim0.865
  Cross-domain analogical claim linking neuroscience findings to AI design
• Deceptive RL baseline agents have lower mean neural self-other overlap than honest baseline agentsclaim0.840
  Core empirical prediction tested in RL experiments, confirmed by 100% classification accuracy
• Neural Self-Other Overlap in Neuroscienceconcept0.827
  Neuroscientific phenomenon where self and other representations partially converge, linked to empathy and altruism
• An artificial model replicating mechanisms of self-illusion can test hypotheses and reveal novel affordances for non-human intelligence.hypothesis0.784
  Methodological proposal to integrate knowledge from contemplative and cognitive science into AI/artificial life frameworks.
• Self-Other Overlapconcept0.782
  The extent to which a model exhibits similar internal representations when reasoning about itself and others in similar contexts
• We define Self-Other Overlap (SOO) as the extent to which a model exhibits similar internal representations when reasoning about itself and others in similar contexts.quote0.779
  Formal definition of the paper's central construct
• When probe and self-report agree and move together causally, confidence in both increases as evidence they track the same underlying stateclaim0.777
  Convergent validity logic applied to LLM interpretability; probes validate self-reports and vice versa
• Different neural network models trained on different objectives and modalities are converging to a shared statistical model of reality in their representation spaceshypothesis0.775
  The central hypothesis of the paper; the platonic representation hypothesis itself