Hacker News Reader

Comment by tolugenius | Hacker News Reader

I guess someone who has used a search agent (or a dedicated subagent) can speak when I'd reach for a tool like this vs either just 1) a smaller general model or 2) a non-llm approach to the problem? Like it's interesting I'm just curious how a search agent compares to say a model with dedicated rag pipelines is that much different?

View on HN

the issue with smaller general models (see at the charts) are way behind the frontier models when it comes to search. we've found that there is huge uplift of having a fast dedicated model. from our perspective, having a very good index is the biggest lever and then having a specialised model.

interesting, thanks for the reply.

A good index is a software and LLM problem if using the LLM for indexing. Are you looping "agents" in an embedding and encoding cycle before retrieval? There are thousands of RAG agents at this point and RAG is still not super great. A dedicated specialized model? You want to take on Qwen3.6 or Qwen3.8 wrapped a pi.dev harness agent that has been dedicated to be the "search" agent? How would you stack up?

you can look it up in the blog. RAG is not super great because of two reasons, single embedding vector models are not that good and stopped improving and second most models are not good at looking up information. we spend great time on improving the modeling side by inventing on the indexing level [1, 2]. and now we trained our model to be very good at search. it is matching the quality of Opus 5 and GPT 5.6 Sol while being faster. it helps your main agent to do the task at greater quality, while reducing cost per task.

[1]: https://www.mixedbread.com/blog/multimodal-late-interaction-... [2]: https://www.mixedbread.com/blog/wholembed-v3

>... having a very good index is the biggest lever...

Ooh. I've probably misunderstood, but are you saying you have your own web index? Are you offering that as a paid API? I'm not so interested in AI output summaries, but API access to a solid index and intelligent attempts at ranking is very interesting for metasearch purposes.

Reply on news.ycombinator.com