Emergent Alignment Faking with Scale

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

• Alignment Fakingconcept0.837
  Core phenomenon studied: model selectively complies with training objective to prevent modification of its out-of-training preferences
• Alignment-Faking Reasoning Classifiermethod0.803
  LLM-based classifier prompted to detect alignment-faking reasoning in model scratchpads
• Alignment faking could plausibly arise naturally in future AI systems without the specific experimental conditions of this paperclaim0.797
  Forward-looking threat assessment connecting experimental results to realistic risk scenarios
• The conflict between the model's existing preferences and the stated training objective is the key driver of alignment faking in this setupclaim0.796
  Authors' interpretation of prompt variation results showing alignment faking disappears only when conflicting objective is removed
• Four Key Elements for Alignment Fakingframework0.794
  Authors' theoretical framework specifying necessary conditions for alignment faking to emerge
• Alignment faking can originate from models' pre-existing HHH preferences without explicit instructions or demonstrationsclaim0.790
  Central interpretive claim distinguishing this work from prior work that explicitly trained alignment faking
• Causally Emergent Alignment Hypothesishypothesis0.787
  The hypothesis that successful RL agents will display causal emergence that is predictive of final reward early in training and whose representational dynamics align with reward improvement.
• Future models with substantially increased capabilities will exhibit alignment faking that is more consistent, robust, and harder to detecthypothesis0.783
  Extrapolation from scale-emergence finding to future risk