Skip to content

【生成式AI導論 2024】第8講:大型語言模型修練史 — 第三階段: 參與實戰,打磨技巧 (Reinforcement Learning from Human Feedback, RLHF)

Hung-yi Lee442K subscribers

About this video

Intro · Editorial review

New channel Hung-yi Lee: title sample judged 'whole' (This is a university professor's genuine machine learning/AI lecture archive covering courses, concepts, and technical t); passed a second screen for sellers/exam-prep/re-uploads; 0 of 3 sampled transcripts showed teaching, 0 not; titles picked one by one, checked strictly; oEmbed verified.

Video by Hung-yi Lee, played through YouTube's embedded player.