Building a RAG pipeline for semantic code search

 (blog.jetbrains.com)

24 points | by saikatsg 2 hours ago

2 comments

  • duhhhhh1212 57 minutes ago
    https://www.pangram.com/history/c901e80e-9cb7-46e4-bf10-7348...

    I don't want to say don't waste your time since the first half is human written. Questions for the authors: did y'all just get tired of writing and said "fuck it let's have the LLM finish the rest"? Or did one of you use LLM to write the last half and the other used their own words?

    [-]
    • verdverm 8 minutes ago
      This looks like the only kind of comment you make lately (to a Ai writing detector)

      1. detectors are unreliable

      2. more people don't care as long as the content is quality

      3. there is a spectrum of ai-human writing and how people make use of the tools, some good, some NS;NT

      https://news.ycombinator.com/item?id=47089907

  • simianwords 40 minutes ago
    Here we go again, the industry largely gave on up RAG. In fact I have hardly seen any case where grep doesn't work as well as RAG.
    [-]