Deliberative Alignment: Reasoning Enables Safer Language Models
Samuel Albanie
0:00 / 0:00
Deliberative Alignment: Reasoning Enables Safer Language Models
1 857 просмотров · 1 год назад
Samuel Albanie
22 тыс. подписчиков
1 857 просмотров · 1 год назад
"Deliberative Alignment: Reasoning Enables Safer Language Models" is a recent paper by Guan et al. (2024) at OpenAI.
Links:
Paper: https://www.arxiv.org/abs/2412.16339
Blog post: https://openai.com/index/deliberative...
