Live data from Hacker News

Viewing profile — deevelton

deevelton

HN member
Joined
Sun, Jan 18, 2026, 3:23 PM UTC
HN karma
14
Public activity
22 items

About deevelton

github.com/dvelton

Recent public activity

  1. comment
    Comment #48456992

    a tool that helps me work in hallucination-sensitive contexts https://github.com/dvelton/eyeball

  2. comment
    Comment #47704521

    one of my teammates experimenting with something along these lines :) https://github.com/jessephus/model-mosaic

  3. comment
    Comment #47704514

    awesome! thanks for checking it out

  4. comment
    Comment #47689589

    Not sure what happens if you start scaling this, but curious too. Would love to see someone who actually knows ML try it.

  5. comment
    Comment #47689513

    Increased default epochs to 2000 instead of 500, I think that fixed it but let me know if you still run into this.

  6. comment
    Comment #47686224

    Thanks; does this fix it? https://github.com/dvelton/ai-pixel/commit/ba04e1c649e0ec99b...

  7. comment
    Comment #47684478

    This was just a fun thought experiment. Feed it two inputs (e.g. chance of rain and wind speed; this is one of the examples in the demo) and it learns to answer a yes/no question l…

  8. story
  9. story
    Show HN: A tool to make AI show evidence inline

    When working in hallucination-sensitive contexts (where cost of error is very high), found myself constantly jumping between AI outputs/analysis and source docs to see with my own …

  10. comment
    Comment #47595188

    I wonder if an animation with the prompts/edits inline and the text morphing might be an interesting UI…fun stuff to think about. Contributions welcome! https://github.com/dvelton/…

  11. comment
    Comment #47587097

    This was just a small experiment, but as a teammate and I watched our respective agents (each loaded with its owner’s context/preferences/etc) negotiate directly with one another t…

  12. story
  13. comment
    Comment #47582595

    Parents in my son's hockey league used to track shots on goal with pen and paper during games, to help coaches both during and after the games. It was tedious and the data was hard…

  14. story
  15. story
  16. comment
    Comment #47579764

    was curious how it might look if we started seeing prompts/steering inline with the finished product: https://dvelton.github.io/trace/examples/the-post.html

  17. comment
    Comment #47530536

    Maybe it’s just personal deja vu, but in current discussions of vibecoding v software engineering I keep seeing parallels from the debates 20 years ago when blogs began proliferati…

  18. comment
    Comment #47471905

    Have been curious what it could look like (and whether it might be an interesting new type of “post” people make) if readers could see the human prompts and pivots and steering of …

  19. comment
    Comment #47471023

    This hits home for me. Lawyer, not developer here. Implementation was never a hard part for me, it was an impossible part. Now that the time/cost needed to experiment with prototyp…

  20. comment
    Comment #47365342

    Have been spending so much time in the terminal lately for the first time in my life (non-developer here) that made this for fun to spruce it up: https://github.com/dvelton/termina…

  21. comment
    Comment #46788691

    Experimented very briefly with a mediation (as opposed to a litigation) framework but it was pre-LLM and it was just a coding/learning experience: https://github.com/dvelton/hotsea…

  22. comment
    Comment #46668570

    Didn’t expect to see this on HN. Thanks for checking it out though. Not a developer, just a lawyer at GitHub, this repo was me playing around with the GitHub Spark tool.