Media Summary: 0:00 Intro 0:55 Chain of thought 1:31 Reinforcement Learning 2:23 Bonus GRPO 3:02 Model Distillation 3:41 Outro Curious about ... Try out Kimi k1.5 Looong Thinking Now & check out their paper Thanks to KiwiCo for sponsoring today's video! Go to and use code WELCHLABS for 50% off ...
Deepseek R1 Explained Like You - Detailed Analysis & Overview
0:00 Intro 0:55 Chain of thought 1:31 Reinforcement Learning 2:23 Bonus GRPO 3:02 Model Distillation 3:41 Outro Curious about ... Try out Kimi k1.5 Looong Thinking Now & check out their paper Thanks to KiwiCo for sponsoring today's video! Go to and use code WELCHLABS for 50% off ... In this video, we dive into the technical innovations behind
![How DeepSeek Rewrote the Transformer [MLA]](https://i.ytimg.com/vi/0VLAoVGf_74/mqdefault.jpg)
