Episode #64 from 29:18
Teaching models to reason
People
Topics
Pre-training, post-training, and future capabilities
0:00
Plan for AGI 2025
16:55
29:18
The Road to ChatGPT
39:45
What makes for a good RL researcher?
51:07
Keeping humans in the loop
59:53
State of research, plateaus, and moats
1:14:11