‹ BackHN Continuity

Thread

Beating GPT-5.6 Sol on retrieval with 100x cheaper open models

427 points · 117 comments · moonikakiss

  1. sreekanth850 · · focus · HN ↗
    IMHO, what is broken is retrieval, the whole blind chunking which was first generation is still the default standard in RAG, this has to be changed. I'm saying this by seeing the results when we used richer parent candidates model for LLM and child segments as search probes. Even without reranking we got solid results.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.