Hacker News new | ask | show | jobs
by renchuw 864 days ago
Hi, OP here, sorry for late reply. I am not actually "evaluating", but rather using the "side effects" of bayesian optimization that allows zoning in/out on some regions on the latent space. Since embedders are so fast compared to LLM, it saves time by saving LLMs from evaluating on similar queries. Hope that makes sense!
1 comments

But aren’t you really just evaluating the embeddings / quality of the latent space then?