PodLM
AI Podcasts
AI Podcast Generator
URL to Podcast
Text to Podcast
Chat Podcast
Pricing
API
English
Sign In
PodLM
Sign In
Toggle menu
Home
AI Podcasts
's Podcasts
Siqi HU's Podcasts
All
Default
Commentary
News
Interview
Talkshow
Crosstalk
LLM的范式转移:RL带来新的Scaling Law
本期播客探讨了LLM(大语言模型)如何通过强化学习(RL)和自我游戏(self-play)实现智能推理能力的提升,并分析了这一变化对未来创业与投资的影响。
2 years ago
Edit