Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Viewing profile — gfernandf1

gfernandf1

HN member
Joined
Mon, Apr 06, 2026, 6:26 PM UTC
HN karma
2
Public activity
22 items

About gfernandf1

Independent researcher working on cognitive runtimes for LLM agents (ORCA Framework). Former Director of Digital & IT in upstream energy. Now exploring agent architectures beyond prompt-centric systems.

https://github.com/gfernandf/agent-skills

Recent public activity

  1. comment
  2. story
  3. comment
    Comment #48772516

    https://zenodo.org/records/19438943

  4. comment
    Comment #48772514

    https://zenodo.org/records/21108157

  5. comment
    Comment #48772303

    [flagged]

  6. story
  7. story
  8. story
  9. comment
    Comment #47965038

    [flagged]

  10. comment
    Comment #47964929

    [flagged]

  11. comment
  12. comment
    Comment #47938820

    One thing I didn’t make clear in the post: The core issue is that prompt-based agents recompute reasoning every time. ORCA tries to make reasoning reusable — more like software, le…

  13. comment
    Comment #47937111

    you can also download the paper from zenodo https://zenodo.org/records/19438943 slightly different version but the core ideas remain the same

  14. comment
  15. story
  16. comment
    Comment #47688909

    Comments welcome!

  17. comment
  18. comment
    Comment #47676681

    If helpful, I can also share the PDF directly or specific sections (design principles, execution model, etc.)

  19. comment
  20. story
  21. comment
  22. story