Auditing language models for hidden objectiveswith Samuel Marks, Johannes Treutlein, Trenton Bricken, Jack Lindsey +302 versionsW_5uruupn8v2 · current
Auditing language models for hidden objectivesSamuel Marks, Johannes Treutlein, Trenton Bricken et al.4 citations2503.10965v22025arXivon Valency
Which Economic Tasks are Performed with AI? Evidence from Millions of Claude ConversationsKunal Handa, Alex Tamkin, Miles McCain et al.11 citations2503.04761v12025arXiv
Alignment faking in large language modelsRyan Greenblatt, Carson Denison, Benjamin Wright et al.30 citations2412.14093v22024arXivon Valency