The Magic of Reinforcement Learning with Human Feedback RLHF

preview_player
Показать описание
Sam Altman explains Reinforcement Learning with Human Feedback (RLHF) #ai #artificialintelligence #samaltman #gpt #chatgpt #openai #technology #ceo #gpt3 #gpt4
Рекомендации по теме
Комментарии
Автор

I was working on a project, and today I woke up and felt like someone whispered RLHF in my ear, and omgggg, I needed this so much, and will be implementing in our project.

akashrawat
Автор

why is it called reinforcement learning if we just say that the model made a mistake when writing this text

pythonscript