News for hackers. Stuff that matters.
Re:Gemini Embedding: Powering RAG and context engineering by ivape on Thursday July 31, 2025 @07:56PM (#44751573)
LLMs can’t take embeddings (unless I’m really confused). Even if it could take embeddings, the embeddings would have lost all word sequence and structure (wouldn’t make sense to the LLM).

There are no comments on this comment yet.