All lessons
llm-training
2 lessons tagged llm-training: free, quiz-checked micro-lessons.
AI
advancedRLVR and GRPO: Training LLMs with Verifiable Rewards
How Group Relative Policy Optimization turns unit tests and theorem provers into training signals — the technique behind DeepSeek-R1's leap in math and code reasoning without a reward model.
12 steps·~18 min
AI
advancedRLHF: From Christiano 2017 to InstructGPT to the Offline Era
Trace the full arc of Reinforcement Learning from Human Feedback — preference data, Bradley-Terry reward models, PPO with KL penalty, reward hacking, and why most labs have moved to offline alternatives like DPO and RAFT.
12 steps·~18 min