Stanford CS329A Self-Improving Agents Course: All 9 Lecture Videos Now on YouTube
Stanford University's course CS329A Self-Improving AI Agents is taught by @achowdhery and @Azaliamirh, built on a framework of first-hand experience plus close reading of papers, with the goal of building an agent that can improve itself; all 9 lectures are now collected on YouTube. The authors also produced a demo video and mentioned they are polishing a set of Skills for courses, open-source projects, and product launch demos.
Why read this
AI score 60
All 9 lectures of Stanford CS329A are now available on YouTube, centered on the sampling-to-training loop for self-improving agents—ideal for a systematic catch-up.
Topics
View original postStanford University has released all the CS329A Self-Improving AI Agents videos on YouTube. The two instructors have worked on PaLM, Gemini, and Claude. The 9 lectures thoroughly explain one loop: sampling → verification → filtering → training → a stronger model Want to know why coding agents have become widespread recently, while writing has not? Full breakdown 👇 https://t.co/b5KhXPnL5P
View original
斯坦福大学把 CS329A Self-Improving AI Agents 视频都公布到 Youtube 了。 两位主讲老师做过 PaLM、Gemini、Claude。9 讲讲透一个循环： 采样 → 验证 → 筛选 → 训练 → 更强的模型 想知道为什么 coding agent 最新普及，写作却不行？ 完整解读 👇 https://t.co/b5KhXPnL5P
Body · AI translation
Stanford University Course CS329A Self-Improving AI Agents
Taught by @achowdhery and @Azaliamirh, with a framework of "first-hand experience + close reading of papers," and with the course goal of "building a self-improving agent," all 9 lectures are now available on YouTube.
Friends who haven't taken this course yet can first take a look at this demo video I made. I highly recommend everyone systematically study the original course videos. Although it takes some time, if you settle down and study and think systematically, it is very rewarding!
Also, friends are welcome to offer valuable suggestions on the production of this demo video. Recently I have been polishing a set of Skills for demo videos, hoping to use them for rapid expressive demos for courses, open-source projects, product launches, articles, etc. Once I am satisfied with them, I will release them.
Course homepage: https://t.co/C3pYFHioLs Course videos: https://t.co/JQYAei9yr1