• Fine-Tuning GPT-2 from Human Preferences https://openai.com/blog/fine-tuning-gpt-2/ 14 comments 19/9/2019

• "Fine-Tuning GPT-2 from Human Preferences" [training text generation using human ratings of quality] https://openai.com/blog/fine-tuning-gpt-2/ 5 comments 19/9/2019 reinforcementlearning