Unlocking AI Mysteries: Key Open Problems in Mechanistic Interpretability 🧠
Discover the latest challenges and breakthroughs in understanding how neural networks work, as Neel Nanda explores the frontiers of mechanistic interpretability at EAGxVirtual 2023.
Effective Altruism
1.1K views • Jan 14, 2024
About this video
Mechanistic Interpretability is a sub-field of AI Alignment that studies trained neural networks and tries to reverse-engineer the algorithms they've learned. In this talk, Neel Nanda gave an overview of the field, key works, and some of the open problems.
Learn more about effective altruism at: www.effectivealtruism.org
Find out more about EA Global conferences at: www.eaglobal.org
Learn more about effective altruism at: www.effectivealtruism.org
Find out more about EA Global conferences at: www.eaglobal.org
Video Information
Views
1.1K
Likes
21
Duration
51:03
Published
Jan 14, 2024
User Reviews
4.5
(1) Related Trending Topics
LIVE TRENDSRelated trending topics. Click any trend to explore more videos.
Trending Now