Live data from Hacker News

Viewing profile — pombo

pombo

HN member
Joined
Fri, Feb 13, 2015, 12:34 PM UTC
HN karma
101
Public activity
52 items

About pombo

No profile information was provided.

Recent public activity

  1. story
  2. story
  3. story
    Show HN: LLMcomp – compare cost and results of different LLMs on the same prompt

    Hey HN, I often want a quick comparison of different LLMs to see the result+price+performance across different tasks or prompts. So I put together LLMcomp—a straightforward site to…

  4. story
    Show HN: Llms.txt directory with automated submission and rough draft generator

    I have been noticing AI websites adding support for llms.txt standard, which inspired me to read more about it. llms.txt is similar to robots.txt but for LLMs so they can better un…

  5. story
    Show HN: ChatGPT-like Flutter app demo with source code (no backend and ~1k LOC)

    Source Code: https://github.com/backmesh/flutter-chatgpt Live Demo: https://flutter-chatgpt.pages.dev

  6. story
    Show HN: Backmesh, Firebase for AI Apps

    Hello HN! Fernando from Backmesh. I got tired of having to spin up a backend to use the OpenAI or Anthropic API and figure out authentication, usage and error analytics per user in…

  7. story
    Show HN: Anthropic React Native Client

    I recently published a new package on npm that brings the Anthropic APIs to React Native without polyfills. The library supports chat streaming and normal chat completions. The goa…

  8. story
    Show HN: OpenAI React Native Client

    I recently published a new package on npm that brings the OpenAI APIs to React Native Expo without polyfills. Today the library supports chat streaming, normal chat completions and…

  9. comment
    Comment #41437658

    I recently published a new package on npm that brings the OpenAI APIs to React Native Expo without polyfills. Today the library supports chat streaming, normal chat completions and…

  10. story
  11. comment
    Comment #41324712

    Use any Gen AI API from your app without a backend with analytics and rate limits per user

  12. story
  13. story
  14. story
  15. story
  16. story
    Show HN: DebugSage, get answers to coding questions from LLMs and developers

    A little side project I put together as I realized I was increasingly using going to different LLMS to help me debug.

  17. story
  18. comment
    Comment #36868506

    I'm not sure I agree with the fact that an abstraction is always the answer, but your last sentence outlines precisely one of our motivations behind Marsha. You can specify an impe…

  19. comment
    Comment #36868479

    I would say that it depends. Python and JS, two of the most used programming languages, abstract away memory management and threading details that most of the time you don't need, …

  20. comment
    Comment #36865992

    one of the contributors here. we have a statistical test script we can run on our branches to test the compile time, cost and reliability. we want to try tree of thought and also s…

  21. comment
    Comment #36606504

    https://github.com/RVC-Project/Retrieval-based-Voice-Convers...

  22. story
  23. story
  24. story
  25. comment
    Comment #35169451

    Traction by Weinberg. Understanding the distribution of your product, how to think about it and how much resources to devote to it was a missing piece for me as a technical founder…