Live data from Hacker News

Viewing profile — cpnwaugha

cpnwaugha

HN member
Joined
Sat, Mar 11, 2023, 11:35 PM UTC
HN karma
1
Public activity
23 items

About cpnwaugha

AI/ML Engineer. Building tools for video search and understanding.

Recent public activity

  1. comment
    Comment #49168868

    [flagged]

  2. story
  3. story
  4. comment
  5. story
  6. comment
    Comment #48836816

    mm can spot charts on a screen. did you try it?

  7. comment
  8. comment
    Comment #48802825

    Sirus (Qax) is 90% built with LLM coding agents (mix). I should say that I'm deeply involved in the process - architecting and reviewing (and sometimes revising) to ensure the code…

  9. comment
    Comment #48797631

    The comments in this post strongly validate the need for reliable video processing and understanding with VLMs. While you can use Gemini or other local VLMs, the real challenge is …

  10. story
    Show HN: Wikicube: instant wiki for any GitHub repo

    You've heard of Uvicorn and Gunicorn. Have you heard of Granian?

  11. comment
  12. story
  13. comment
    Comment #48575662

    Two approaches for passing binary files, say a 2-hour lecture video, to a VLM: 1. Send it whole: accurate, but slow to encode and process. 2. Keyframe extraction: fast, but could m…

  14. story
  15. comment
  16. story
  17. comment
    Comment #45382886

    We're helping litigation attorneys and insurance claims adjusters turn video into insights in seconds

  18. comment
  19. story
  20. comment
    Comment #44479491

    AI-generated, with summaries and key moments Tired of sending 40-minute videos that no one watches to the end? We found that converting long videos into short-form slide (and PDF) …

  21. story
  22. comment
  23. story