Recently updated channels

Pick one to see only that channelBrowse all channels →
20VC with Harry StebbingstodayAI Engineertoday硅谷101yesterdayMBMatthew Berman2 days agoPragerU2 days agoY Combinator2 days agoSemiAnalysis3 days agoa16z3 days agoGOTO Conferences3 days agoThe Builders4 days ago

Results

1 articles
Sort
TopicReinforcement LearningLengthOver 30 minSpeakers3 or more
1:27:02ZH → English
Zhang Xiaojun Podcast· Sep 5, 2024Podcast · 3 speakersGuangmi: Self-Play RL Could Open a New Scaling Law for AGIGuest 广密 · Host 张小珺Guangmi believes the marginal returns from scaling language pretraining alone may be diminishing, making self-play reinforcement learning a more promising path. Whether it generalizes to code, video, robotics, and beyond will shape the next stage of the AGI race.Reinforcement LearningAGIScaling Laws+2