Nathan Lambert
@natolambert·8K subscribers·36 videos
ML Foundations (prerequisites) for Post-Training | RLHF Book Course, Lecture 0
Posted
June 24, 2026
Views
1,816
Likes
112
Comments
14
Engagement
June 24, 2026
1,816
112
14
6.94%
Every word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
23:53Now PlayingIn this video I try to cover a bunch of math, LLM training fundamentals, and probability concepts that come up again and again in posttraining content (and this book). We cover things like the role of midtraining, definitions of KL, entropy & crossentropy, getting LM probabilities from a sequence, etc. Thanks to everyone who nudged me to make this video, the slides were a fun experiment with GLM5.2 (more on that model here)
Extra learning resources
"Lecture 0" added after the course was well underway :)
Welcome to The RLHF Book & Post-Training Course with Nathan Lambert.
Ask questions and I'll answer them in the next roundup video!
Slides for this lecture are here
Chapters:
All resources will be available at
Order a copy of the book (physical recommended) on Manning.com
Order a copy on Amazon
With specific course resources at (recording links, slides in PDF and native form, etc.)
And code at
Get more information on Nathan at and stay up to date with his work on Interconnects
Course YouTube playlist
Join the book's Discord Community
Nathan is on…
Slides are built with Colloquium
Thank you to my many collaborators who helped me learn this information I get to share with the world!
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.
