Teaching

Why we teach ML with primary sources and hands-on labs

Courses should bridge intuition, evidence, and implementation. Primary literature teaches you how claims are argued; labs teach you where they break.

Evidence over vibes

Papers make assumptions explicit. That habit transfers to reading internal model cards and external benchmarks with a critical eye.

Training loops, metrics, and failure modes are learned faster when you touch them directly—not only through slides.

Same cards as the blogs page—related topic first, then newest.

A practical order of operations: abstract, figures, method, then experiments—so you know what to skim and what to study.

Latency, batching, KV-cache memory, and evaluation—not just swapping in a bigger model.

If retrieval misses the right chunk, no prompt tweak will save the answer. Split your eval into recall, grounding, and fluency.

Go deeper on optimization, evaluation, and data—without replaying every undergraduate lecture.