Live data from Hacker News

Viewing profile — adam_rida

adam_rida

HN member
Joined
Tue, Nov 24, 2020, 7:35 PM UTC
HN karma
236
Public activity
54 items

About adam_rida

No profile information was provided.

Recent public activity

  1. comment
    Comment #49184391

    i typically run many coding agents side by side and i noticed i never read the wall of tool calls and text and tasks they do, i just want to know if 1) it’s still going 2) what is …

  2. story
  3. comment
    Comment #49044659

    i think that’s exactly the core of the question. There is meaningful decorrelation across models in some domains, like language for instance. but i agree that it’s much less obviou…

  4. comment
    Comment #49039896

    thanks! adjusting it now

  5. comment
    Comment #49039870

    good catch, on it too now!

  6. comment
    Comment #49037342

    exactly, if you ensemble heavily small uncorrelated models (while each being expert on its task) you can get really interesting resutls. on agentic and coding what's make the probl…

  7. comment
    Comment #49035601

    removing it now

  8. comment
    Comment #49030361

    there are and this what you optimize for. ensemble learning has a long literature on this. you want models that have the most diverse pool of capabilities so they complement each o…

  9. comment
    Comment #49030253

    thanks to everyone for taking the time to try Echo and share feedback, this is precisely why i wanted to launch early. i am going to try to address a couple of topics that came up …

  10. comment
    Comment #49029792

    looking at it now

  11. comment
    Comment #49029791

    looking at it now

  12. comment
  13. comment
  14. comment
    Comment #49027324

    The evaluator is public here: https://echo.tracerml.ai/eval/ It currently exposes 907 stored rows across seven benchmark families, with prompts, outputs, grades, and cost records. …

  15. comment
    Comment #49027304

    Thanks for checking the individual rows. HumanEval+ is one small code slice, not the whole basis for the launch claim. The public evaluator currently contains 907 rows across seven…

  16. comment
    Comment #49027297

    You are right that the privacy wording was too broad. We are fixing it now so it states explicitly that Echo does not use customer prompts, files, chats, or outputs to train or fin…

  17. story
    Show HN: Echo – Fable-level results at 1/3 the cost using open-weight models

    I’ve been building Echo ( https://echo.tracerml.ai/ ), an experiment in making one AI system out of a pool of open-weight models rather than choosing a single model and using it fo…

  18. story
  19. story
  20. story
  21. story
  22. comment
    Comment #48601511

    very cool

  23. comment
    Comment #48530955

    thanks, apologies for the broken link This one should work: https://www.theregister.com/ai-and-ml/2026/06/14/ai-is-code-...

  24. comment
    Comment #48530940

    Apologies, the submitted link seems broken. Actual link: https://www.theregister.com/ai-and-ml/2026/06/14/ai-is-code-...

  25. comment