Live data from Hacker News

Viewing profile — galenmarchetti

galenmarchetti

HN member
Joined
Tue, Mar 01, 2022, 6:13 PM UTC
HN karma
299
Public activity
107 items

About galenmarchetti

building astrobee.ai

https://twitter.com/GalenMarchetti

Recent public activity

  1. comment
    Comment #45464400

    what are these "nasty surprises"? they're really not that different

  2. comment
    Comment #45464232

    then why hasn't the central bank done this yet

  3. comment
    Comment #45455545

    yep if you want to just go straight to the docs, they're here: https://docs.astrobee.ai/ warehouse: you connect your warehouse AND astrobee will store your semantic layer (ontology…

  4. comment
    Comment #45453143

    that's a fair point. we use "ontology" throughout the product because of the influence from Palantir, and the fact that the structure we use in the product (from palantir) is in fa…

  5. comment
    Comment #45452148

    thank you! that's exactly where we're going with this. we're still in the early days, so let us know how you get along!

  6. comment
    Comment #45452038

    we're using OpenAI's API for business. they don't train on data sent to the business api, unlike the consumer tier this is still an early beta, so at the moment everything is only …

  7. comment
    Comment #45451841

    have worked with waku in the past, love the vision

  8. story
    Show HN: AstroBee – AI-Generated Semantic Layers

    Hi, I’m a cofounder of AstroBee and I wanted to share our work with the community. AstroBee is an automatic semantic layer generator for your business. It brings data together from…

  9. comment
    Comment #45441006

    it depends on whether you want to live life with work-as-someone-paying-for-your-time or whether you want to live life as work-as-perfecting-and-delivering-on-craft you can have an…

  10. story
  11. story
  12. comment
    Comment #44867729

    they kept 2 nonstop routes to NYC, 1 to Chicago, 1 to SF, but none to DC wouldn't have guessed that. that NYC pull is huge

  13. comment
    Comment #44011125

    yeah I agree with this - good text2sql is essential but just one part of a larger stack that will actually get there. Seems possible tho

  14. comment
    Comment #44011116

    and then add in ambiguity in the business terms / intention behind the query. still a big need for something like semantic layer or ontology to sit between business and at least ri…

  15. comment
    Comment #44011108

    still need someone to build the semantic layer, why not use text2sql or something similar for that

  16. comment
    Comment #44011095

    there’s two kinds of people using AI to generate SQL…those who say it’s already solved and those who say it’ll be impossible to ever solve

  17. comment
    Comment #44011084

    yeah we’re doing something similar under the hood at AstroBee. it’s way way way easier to handle joins this way. imo any hope of really leveraging llms in this context needs this +…

  18. comment
    Comment #41461938

    i do think there's a lot of opportunity for the AI-assisted kubernetes help feature could be cool to see that unbundled into its own thing though

  19. comment
    Comment #41259154

    "clown car that fell into a gold mine" is such a brilliant image. im not familiar with twitter in those days, but I've seen other companies that definitely match this description

  20. comment
    Comment #41259087

    founder/dev on this project here - exactly!! still trying to figure out the wording between "kubernetes development environment", "kubernetes-based application deploys", "applicati…

  21. comment
    Comment #41258993

    service B doesn't actually know that - it happens at the level of the service mesh (you have to have a service mesh installed, right now just supporting istio but we plan on making…

  22. comment
    Comment #41258773

    founder/developer here - yeah, in the last couple weeks I've had in the back of my mind switching the wording to "lightest-weight application deploys on Kubernetes" or something li…

  23. comment
    Comment #41258750

    founder/developer on Kardinal here - that's a good question in reality what you're doing with namespace-based deploys or telepresence is equally "lightweight" to what you're doing …

  24. comment
    Comment #41257872

    fast fix! appreciate this

  25. story