Embedding dimensions: what 256 vs 1024 vs 3072 costs in memory, latency and recall
Truncating a Matryoshka embedding from 1024 to 256 dims cut memory 4x and lost 1.8 points of recall@10 on 705 FastAPI doc queries. int8 lost nothing.
Make your RAG say 'I don't know': a score threshold, measured
A cosine threshold of 0.40 refused 24 of 30 unanswerable questions and still answered 29 of 30 answerable ones. BM25 scores separated them worse (AUC 0.91 vs 0.99).
JEPA vs LLMs: what LeCun's world models actually change for engineers
Analysis: JEPA predicts embeddings, not tokens. My text-chunk stand-in: token-space prediction collapsed 99.4% with 10x less data, embedding-space only 45.8%.