Live data from Hacker News

Viewing profile — ansonhw

ansonhw

HN member
Joined
Mon, Nov 28, 2022, 3:34 PM UTC
HN karma
8
Public activity
30 items

About ansonhw

No profile information was provided.

Recent public activity

  1. comment
    Comment #45519456

    chatsheet.com no embeddings yet, but soon

  2. comment
    Comment #44149666

    Ya this is nice that it’s infra agnostic instead of requiring tons of dependencies.

  3. comment
    Comment #43968345

    down again for me

  4. comment
    Comment #43968101

    not sure why i didn't see any status updates

  5. comment
    Comment #43968099

    was down (messages not going through) for me, then web was ok, then all went down, now back up

  6. comment
    Comment #43848869

    excited for this to run sandboxes

  7. comment
    Comment #43614501

    we're working on this at chatsheet.com what features are you looking for?

  8. comment
    Comment #43414435

    Agree that's what we're trying to do at chatsheet.com Program in "plain english" but as powerful as writing code

  9. comment
    Comment #43251743

    i stopped manually updating airtable and excel. all doc/web/pdf flows auto update.

  10. comment
    Comment #43182142

    Doesn't this mean 45% of workers already do use AI chatbots? Glass half full vs empty

  11. comment
    Comment #43181704

    Save Worker 17 o7

  12. comment
    Comment #43148909

    tech world: rag, llm, prompting, agents, bla bla normies: chatgpt

  13. comment
    Comment #42973980

    Hmm i'll check out the pagerank stuff, IMO RAG isn't super great. I think RAG overall has been oversold since embeddings KNN hasn't proven to be super accurate.

  14. comment
    Comment #42973634

    Go is the best for scale out, concurrent agents

  15. comment
  16. comment
    Comment #42970231

    Hmm i think the issue with any large data set is indexing + querying. At https://usefind.ai/ this is a fundamental problem we've been trying to tackle. What kind of structure do yo…

  17. comment
    Comment #42965355

    I'm confused why search + LLM wouldn't work for this?

  18. comment
  19. comment
    Comment #42937401

    I agree actually that chat is overrated overall as UX. It works really well for chatgpt but creates the wrong ux expectations for users where more precision or constraint is needed…

  20. comment
    Comment #42937378

    Does it support pgvector over weaviate?

  21. comment
    Comment #42920506

    why is bill gates so obsessed with bringing back clippy

  22. comment
    Comment #42839278

    Check the screenshot below re: training on OpenAI Outputs. They've fixed this since btw, but it's pretty obvious they used OpenAI outputs to train. I mean all the Open AI "mini" mo…

  23. comment
    Comment #42819784

    Feedback -> paying Scale AI to babysit/label tons of these sessions. It will just be like the post training that turned GPT3 into the original ChatGPT.

  24. comment
    Comment #42810979

    When: 1/ More accurate + less supervision 2/ Faster 3/ Background + Parallel Will be the magic moment. Currently like supervising a grandparent using the web. But there's huge pote…

  25. comment