Comment by fennecfoxy

Hmm. I'm building something (quick and dirty) at the moment that looks at analysing customer service data.

Something like this is promising but from what I can see, still lacking. So far I've been dealing with the regular issues (models aren't actually that smart, work with their strengths and weaknesses) but also more of the data problem - simple embeddings just aren't enough, imo. And throwing all of the data at the model is just asking for context poisoning, hallucinations and incorrect conclusions.

Been playing with instruction tuned embeddings/sentiment and almost building a sort of "multimodal" system of embedding to use with RAG/db calls. What I call "Data hiding" as well - allowing the model to see the shape of the data but not the data itself, except only when directly relevant.