LeVanLoi'log, ⌚ 2024-12-21
***
Deliberative alignment: reasoning enables safer language models
Tác giả: OPenAI: Melody Guan, Manas Joglekar, Eric Wallace, Saachi Jain, Boaz Barak, Alec Heylar, Rachel Dias, Andrea Vallone, Hongyu Ren, Jason Wei, Hyung Won Chung, Sam Toyer, Johannes Heidecke, Alex Beutel, Mia Glaese
