Agentic

 Kernel

SFT, RL, and On-Policy Distillation Through a Distributional Lens On forgetting, generalization, and what connects RL to on-policy distillation

terraform

https://0mean1sigma.com/chapter-3-gpu-compute-and-memory-architecture/

https://faculty.washington.edu/aragon/pubs/rst96.pdf - Randomized search tree