Open Source After the Frontier Gate
· 19 min read#open-source#llm#grpo
The US walled off frontier AI. Five days later, an open-weight model beat GPT-5.5. The post-training pipeline is where open-source AI compounds its advantage.
#grpo
2 articles
How LLMs Are Created — Pre-training, Post-training, and RL
· 32 min read#llms#pre-training#post-training
How LLMs are built: from internet-scale pre-training through SFT, RLHF, DPO, GRPO, and Constitutional AI.