Papers
No proofs. No summations you have to squint at. Just the idea, translated into something you could set a breakpoint in.
How to read these: don't. Not first, anyway. Run the code, break it the way each page tells you to, then come back and read. Watching something fail teaches faster than watching someone explain.
ai-ml/
-
Attention Is All You Need
Attention is a dictionary lookup with fuzzy keys — everything else is plumbing. Runnable NumPy, four demos that prove it by breaking it.
-
KV caching and the generation loop
Why inference is affordable. A direct consequence of the causal mask that nobody explains properly.
-
LoRA: low-rank adaptation
Fine-tuning without touching the base weights.