Brandon Rohrer who obtained his Ph.D from MIT is driven by understanding algorithms ALL the way down to their nuts and bolts, so he can make them accessible to everyone by first explaining them in the way HE himself would have wanted to learn!

Please support us on Patreon for loads of exclusive content and private Discord:
  / mlst   (public discord)
  / discord  
  / mlstreettalk  

Brandon's career has seen him in Principallevel roles at Microsoft and Facebook. An educator at heart, he also shares his knowledge through detailed tutorials, courses, and his forthcoming book, "How to Train Your Robot."

Pod version: https://podcasters.spotify.com/pod/sh...

TOC:
00:00:00 Intro to Brandon
00:01:48 RLHF
00:02:22 Limitations of transformers
00:08:36 Agency we are all GPTs
00:10:20 BPE / representation bias
00:13:13 LLM adherents true believers
00:17:55 Brandon's Teaching
00:21:03 ML vs Real World / Robotics
00:31:12 Reward shaping
00:38:21 No true Scotsman when do we accept capabilities as real
00:40:03 Externalism
00:44:16 Building flexible robots
00:46:50 Is reward enough
00:55:43 Optimisation curse
00:59:28 Collective intelligence
01:03:04 Intelligence, Creativity + ChatGPT
01:26:32 Transformers

Brandon's links:
https://github.com/brohrer
   / @brandonrohrer  
  / brohrer  

How transformers work:
https://e2eml.school/transformers

Brandon's EndtoEnd Machine Learning school courses, posts, and tutorials
https://e2eml.school

Free course:
https://endtoendmachinelearning.t...

Blog: https://e2eml.school/blog.html

Ziptie: Learning Useful Features [Brandon Rohrer]
https://www.brandonrohrer.com/ziptie