Reiner Pope: The Math Behind How LLMs Are Trained and Served

Reiner Pope – The math behind how LLMs are trained and served

Dwarkesh interviewed Reiner Pope in a 1-session blackboard lecture on LLM training and serving. The post lists 7 timestamps on batch size, MoE rack layout, pipeline parallelism, KV cache, and API pricing. The key mechanism is cost: without batching, serving economics can be 1,000x worse.

Why it matters: HKR-H/K/R all pass: the 1000x batching cost hook, concrete serving mechanics, and inference-cost resonance are strong. This is a high-quality tutorial, not a same-day industry event, so it stays at 77.