Notes

My Notes

Memory to Train a Transformer Draft · 11 July 2026
Estimating Layers in Transformers 27 June 2026
Why KV Cache and Not QKV Cache? 12 June 2026
Is RL Secretly Supervised Learning? 28 December 2025

Currently Reading — LLM-Generated Notes

Estimating the Compute and Memory Needed for Language Models Draft · 11 July 2026

Also: CEO Hour — protected thinking time for founders.