Saurav Kadavath5 papers on this site (2021–2022)Constitutional AI: Harmlessness from AI FeedbackYuntao Bai, Saurav Kadavath, Sandipan Kundu, et al.2022Discovering Language Model Behaviors with Model-Written EvaluationsEthan Perez, Sam Ringer, Kamilė Lukošiūtė, et al.2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons LearnedDeep Ganguli, Liane Lovitt, Jackson Kernion, et al.2022Measuring Coding Challenge Competence With APPSDan Hendrycks, Steven Basart, Saurav Kadavath, et al.2021Measuring Mathematical Problem Solving With the MATH DatasetDan Hendrycks, Collin Burns, Saurav Kadavath, et al.2021