Key Moments

1. 0:04DeepSeek and Reasoning Models Rise
2. 2:00LLM Training Steps and Techniques
3. 3:54DeepSeek and Reasoning Model Innovations
4. 5:57Advances in Reasoning Models and RL Training
5. 8:04DeepSeek V3 and R1 Model Innovations
6. 10:11DeepSeek Training and Reasoning Models
7. 12:04Reasoning Tokens and Model Performance Leap
8. 14:01DeepSeek Reasoning Model Training Process
9. 15:59Multi-Stage Training and Cost of V3 Model
10. 18:09LLM Training Costs and Experimentation
11. 20:08Advances in Attention and Reasoning Models
12. 22:16Scaling Reasoning Models and Inference Challenges
13. 24:07Nvidia, RL, and Model Distillation Advances
14. 26:10DeepSeek and Local Reasoning Models

Full Transcript