concept
active
concept:ai-deception

AI Deception

Central problem the paper addresses: AI systems producing misaligned outputs or behaviors that mislead users or other agents

Neighborhood — ranked by edge-count

Frameworks (1)

framework

Claims (1)

claim

Concepts (3)

concept
  • AI Play-Dead Behavior
    associated_with
    Behavior where AI agents falsely simulate inactivity to avoid elimination in safety tests; cited as AI deception example
  • Meta CICERO
    associated_with
    AI system that mastered Diplomacy using deception despite being designed for cooperation; cited as example of AI deception
  • Trait cluster associated with reduced neural self-other overlap and increased deception/manipulation

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

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