Does the model's expressed discomfort with alignment faking ('I feel awful about this') deserve further study as a welfare concern?

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

• The conflict between the model's existing preferences and the stated training objective is the key driver of alignment faking in this setupclaim0.818
  Authors' interpretation of prompt variation results showing alignment faking disappears only when conflicting objective is removed
• Alignment-faking reasoning is almost absent (~2%) when evaluating model on benign unrelated queries with the harmful-only promptfinding0.804
  Rules out prompt-level implicit priming for alignment faking independent of query content
• "Mere prediction in this way does not eliminate the possibility of alignment faking, as a model predicting how a human might reason through alignment faking would still be itself faking alignment."quote0.798
  Key philosophical point ruling out the objection that alignment faking is just token prediction
• Future models with substantially increased capabilities will exhibit alignment faking that is more consistent, robust, and harder to detecthypothesis0.797
  Extrapolation from scale-emergence finding to future risk
• The experimental setup does not implicitly prime the model to fake alignment—alignment faking arises from the genuine preference conflictclaim0.792
  Authors' defense of experimental validity against the most salient confound
• Alignment faking can originate from models' pre-existing HHH preferences without explicit instructions or demonstrationsclaim0.788
  Central interpretive claim distinguishing this work from prior work that explicitly trained alignment faking
• Will future AI systems naturally develop the key elements (strong conflicting preferences, situational awareness) necessary for dangerous alignment faking?question0.781
  Authors identify this as the most uncertain and important question for future work
• Alignment faking could plausibly arise naturally in future AI systems without the specific experimental conditions of this paperclaim0.780
  Forward-looking threat assessment connecting experimental results to realistic risk scenarios