‹ BackHN Continuity

Thread

Benchmarking retrieval for agents on messy real-world company knowledge

22 points · 2 comments · emil_sorensen

Loading the complete thread in the background. This saved snapshot is available now. Refresh

  1. emil_sorensen · · focus · HN ↗
    OP/founder of kapa (YCS23) here. Happy to answer any questions :)
    1. polotics · · focus · HN ↗
      ok I bite!

      What is your opinion of: - BEAM - MemEval - MemoryArena - any other you can find on eg. HuggingFace

      How much value do you see in Karpathy's gist on the Episodic/Procedural/Semantic split (aka. btw. Doxa/Koine/Gnosis) If you do see value what parts of your design matches?

      As you are using real company data, will you at least make one step towards reproducibility by publishing some extraction pipeline so no other companies can run their own comparison?

  2. suhas_rnd · · focus · HN ↗

    [dead]

  3. haukebri · · focus · HN ↗

    [dead]

  4. aidiveyt · · focus · HN ↗

    [dead]

  5. 75ziadilrodilax · · focus · HN ↗
    enzinho bravo
  6. aidiveyt · · focus · HN ↗

    [dead]

Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.