News & insights
Articles on ML research literacy, systems, data, and teaching—same card layout as our course catalog.
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.