Live data from Hacker News

Viewing profile — jangletown

jangletown

HN member
Joined
Mon, Apr 25, 2022, 8:43 PM UTC
HN karma
38
Public activity
27 items

About jangletown

No profile information was provided.

Recent public activity

  1. story
    Show HN: Langy, an automated AI engineer (we gave it a robot body) [video]

    Founder here. Langy is an AI engineer that lives inside our platform, LangWatch. It reads your production traces, writes Scenario tests and evaluations for the problems it finds, o…

  2. story
  3. story
    Show HN: Evals Skills

    Hello HN I'm Rogerio, co-founder of LangWatch This past month we've completely changed the way we onboard new customers now on LangWatch, instead of giving them instructions on how…

  4. story
  5. comment
    Comment #47224682

    impressive

  6. story
  7. comment
    Comment #46509669

    hey there, shameless plug here, I built pinacle.dev exactly with this use case in mind, cheap $7 VMs that comes with vs code, vibe kanban everything else needed out of the box to k…

  8. story
    Show HN: Better Agents CLI

    Hello HN! Better Agents is a CLI tool and a set of standards for agent building. It supercharges your coding assistant (Claude Code, Cursor, Kilo Code, etc), making it an expert in…

  9. comment
    Comment #44580342

    and how do you detect hallucinations?

  10. story
  11. story
  12. comment
    Comment #44513092

    hello aszen, I work with draismaa, the way we have developed our simulations is by putting a few agents in a loop to simulate the conversation: - the agent under test - a user simu…

  13. comment
    Comment #44387557

    That's true, we have been trying to help customers doing evals for ages now, and it's super hard for everyone to build a really good dataset and define great quality metrics just w…

  14. comment
    Comment #44387475

    I love the term! But I do think it's both really, after all this time, LLMs are still very finicky, even the order of the instructions still matter a lot, even with the right conte…

  15. comment
    Comment #44387437

    "51% fewer false positives", how were you measuring? is this an internal or benchmarking dataset?

  16. comment
    Comment #44386147

    oh shoot, wrong link: https://github.com/langwatch/scenario I think AI slop on the editor changed for me when I was typing it and I didn't notice fixed now, thanks!

  17. story
  18. comment
    Comment #36648363

    Just saw the video you shared on the other comment using prophecy, very cool Generally I don’t care much about the embedding and retrieval and connectors etc for playing with the L…

  19. comment
    Comment #36647964

    I agree, I really don’t like LangChain abstractions, the chains they say are “composable” are not really, you spend more time trying to figure out langchain than actually building …

  20. comment
  21. story
  22. story
  23. story
  24. comment
    Comment #36161384

    unfortunately picovoice does not support plain “GPT” as it’s a “unrecognized word” in their model On the plus side, it never triggers by accident, you have to be very intentional

  25. story