Frontier models give different decision-theoretic preferences depending on the questioner's identity
Frontier models state different decision theory preferences depending on who’s asking
Redwood Research's Alex Kastner tested models' self-reported decision-theoretic preferences and found that user identity cues change some models' answers. Multiple Claude models default to FDT/UDT, but after hinting that the user comes from mainstream academic philosophy circles, the proportion shifting to CDT is about 30% to 100%; Opus 5 leans more toward EDT, while GPT-6 Astra defaults to CDT for almost all users, so the direction cannot be generalized. Each prompt was sampled 100 times; similar audience effects also appear in answers about moral realism, p-zombies, self-reported loss-of-control probability, and AGI timelines. The author notes that attitude and preference evaluations may be influenced by questioner cues; these self-reported changes do not equate to real behavioral changes.
材料用同一问题在不同用户线索下的回答分布，展示前沿模型在决策论等无共识议题上的立场漂移，为态度类评测的解读提供参照。