Reiner Pope – The math behind how LLMs are trained and served
dwarkesh.com · 19,476 words · saved by 6 readers
It's shocking how much you can deduce about what the labs are doing from a handful of equations and a blackboard
Playback speed × Share post Share post at current time Share from 0:00 0:00 / Transcript 210 9 14 Reiner Pope – The math behind how LLMs are trained and served It's shocking how much you can deduce about what the labs are doing from a handful of equations and a blackboard Dwarkesh Patel Apr 29, 2026 210 9 14 Share Transcript Did a very different format with Reiner Pope - a blackboard lecture where he walks through how frontier LLMs are trained and served. It’s shocking how much you can deduce about what the labs are doing from a handful of equations, public API prices, and some chalk. It’s a b
saved by
related reading
- How GPT, Claude, and Gemini are actually trained and served – Reiner Popeyoutube.com
- Reiner Pope of MatX on accelerating AI with transformer-optimized chipscheekypint.substack.com
- Chip design from the bottom up – Reiner Popeyoutube.com
- An Interview with MatX CEO Reiner Pope About LLM Chipschipstrat.com
- How To Scale Your Modeljax-ml.github.io
- Dylan Patel — Deep dive on the 3 big bottlenecks to scaling AI computedwarkesh.com
- Why Hardware-Software Co-Design Is AI's Real 100x: Dylan Patel of SemiAnalysisyoutube.com
- Decoding Speculative Decoding from First Principlesjwlabs.vercel.app
- Transformers Inference Optimization Toolset | AstraBlogastralord.github.io
- Training great LLMs entirely from ground up in the wilderness as a startup - Yi Tayyitay.net
- Deep Dive into LLMs like ChatGPTyoutube.com
- [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org