Why hybrid search is the boring default we keep recommending

A founder we work with had been debugging a confusing failure for two weeks. The internal AI assistant could not find content about "GPT-4o pricing" even though the exact phrase appeared in three different chunks in the vector database. Asking for "OpenAI model costs" returned the right results. Asking for "GPT-4o pricing" returned a discussion of GPT-3 from eighteen months ago. This is the failure mode every vector-only RAG system has. The team was about to swap embedding models. The actual fi...