Theory & Algos·Research Seminar·Language Models & NLP · Shafi Goldwasser · Simons Institute (UC Berkeley)
1:02:15
Academic Discipline
AI & Machine Learning
Deep learning, language models, reinforcement learning, statistical learning theory, representation learning, and vision.
10courses86standalone talks213total lectures
Subfields
Mechanistic Interpretability, Alignment & World Models— Mechanistic interpretability, sparse autoencoders, neural circuits, AI alignment, scalable oversight, and world models.
3 topicsjknavigate↵watchcchaptersssavexwatched
Save
AI & ML·Public Colloquium·Mechanistic Interpretability, Alignment & World Models · Geoffrey Hinton · Association for Computing Machinery (ACM)
32:28
AI & ML·Research Seminar·Mechanistic Interpretability, Alignment & World Models · Rongzhe Wei · Google Research & TechTalks
56:22
54:33
1:16:53
59:10
39:55
AI & ML·Research Seminar·Mechanistic Interpretability, Alignment & World Models · Angelina Wang · Cornell University
31:57
AI & ML·Research Seminar·Mechanistic Interpretability, Alignment & World Models · Richard S. Sutton · University of Alberta (Amii)
58:57
AI & ML·Public Colloquium·Statistical Learning & Causality · François Chollet · Google Research & TechTalks
1:10:44
AI & ML·Research Seminar·Mechanistic Interpretability, Alignment & World Models · Jocelyn Qiaochu Chen · University of Alberta (Amii)
1:03:23
1:06:50
AI & ML·Research Seminar·Mechanistic Interpretability, Alignment & World Models · Xi Ye · University of Alberta (Amii)
57:31
AI & ML·Research Seminar·AI Alignment, Safety & Scalable Oversight · Edith Elkind · Northwestern University
1:23:31
AI & ML·Public Colloquium·Mechanistic Interpretability, Alignment & World Models · Jim Harris · National Capital Area Skeptics (NCAS)
1:28:36
38:10
1:17:48
Neural Networks: Zero to Hero · Lec 5·Mechanistic Interpretability, Alignment & World Models · Andrej Karpathy · Independent / Eureka Labs
1:55:24
45:57
Showing 20 of 27 lectures21h shown