发生了什么
Hi HN. A while ago I started building a generic people matching app based on LLM-as-a-judge. I needed a way to bypass the O(n^2) "everyone rates everyone else" trap, but generic RAG was much worse than expected. DNA is a search-like API at the core of that product. It stores one embedding per item (like a vector DB) and gives the best match(es). When you know how good it was, you send the score back. This makes it improve in real time, so next time it gives you better results. In my tests, it needed 7x fewer LLM judgments than scoring down the embedding list. Paper in progress. What I don’t know yet is what demo would make you want to try building with it. What would you want to see it do? Comments URL: https://news.ycombinator.com/item?id=50244993 Points: 1 # Comments: 0
Hi HN. A while ago I started building a generic people matching app based on LLM-as-a-judge. I needed a way to bypass the O(n^2) "everyone rates everyone else" trap, but generic RAG was much worse than expected. DNA is a search-like API at the core of that product. It stores one embedding per item (like a vector DB) and gives the best match(es). When you know how good it was, you send the score back. This makes it improve in real time, so next time it gives you better results. In my tests, it needed 7x fewer LLM judgments than scoring down the embedding list. Paper in progress. What I don’t know yet is what demo would make you want to try building with it. What would you want to see it do? Comments URL: https://news.ycombinator.com/item?id=50244993 Points: 1 # Comments: 0
为什么重要
需要你自己点开原文确认一次，这里给的是摘要与判断。
需要你自己点开原文确认一次，这里给的是摘要与判断。
跟你有什么关系
暂无明确落点，仅作存档。
暂无明确落点，仅作存档。
以上判断为规则生成的初稿，发布前请润色。
判定理由
评分 0 / 100