Learn

Three things I'm finishing, in public. Every item here has an artefact you can check: a video, a write-up, or tested code.

Planned
Prep ready
Solved
Recorded
Published

In progress 0/186 episodes

LeetCode Patterns

186 problems across 15 patterns, each one solved cold, written up, and taught on camera. The interview gate for ML engineering roles, done in public.

dsa-content on GitHub ↗
Up next 0/24 items

CS336: Language Modeling from Scratch

Stanford's build-everything-yourself LLM course. Tokenizer, transformer, systems, scaling laws, data, alignment. Five assignments, no shortcuts.

cs336.stanford.edu ↗
Up next 0/32 items

Distributed Training from First Principles

Umar Jamil's 19-hour build of a distributed training framework in PyTorch (RoPE, MLA, pipeline / data / tensor / context / expert parallelism, MoE), followed chapter by chapter.

hkproj/torchfeather ↗