Live data from Hacker News

Viewing profile — fractorial

fractorial

HN member
Joined
Wed, Feb 09, 2022, 12:46 AM UTC
HN karma
120
Public activity
53 items

About fractorial

No profile information was provided.

Recent public activity

  1. story
  2. comment
    Comment #49157725

    For context, I've rolled my own research harness in Go; I've been trying very hard to keep the non-test LOC around ~30k lines. To me, I consider this large, but necessary, especial…

  3. comment
    Comment #49148731

    I’m not quite sure why the harness itself needs to be small. Isn’t the system prompt and management of system prompt the bit you want lightweight?

  4. comment
    Comment #49138924

    I similarly find it interesting; I do not understand why it is not the default to just generate the thing as a draft, research anything you aren’t clear on, and re-write it in your…

  5. comment
  6. comment
    Comment #49113343

    Cosmically apt username given the substance of this comment.

  7. comment
    Comment #49113335

    It would appear that rolling my own Anthropic-free harness / serving stack with a closed-weight carve out for Codex models is an absolute win.

  8. comment
    Comment #49108949

    > Do anti-LLM types expect to be vindicated in an orgy of copyright lawsuits that resets the industry back to 2022? What do people pushing expect to accomplish? You weren’t kidding…

  9. comment
    Comment #49078862

    > Google is less full of crap about the open weights stuff because of Gemma 4, but they are full of crap for a zillion other things I can't exactly feel good about them. So everyon…

  10. comment
    Comment #49065031

    Pretty much this. I designed my own research harness and infra for theorem proving and conjecturing; however, you still need to review formulations!

  11. comment
    Comment #49062451

    Yes, and I use them often in the context of writing adversarial ‘go vet’ style anti-slop analyzers that run pre-commit.

  12. comment
  13. comment
    Comment #49053167

    I’ve rolled a small program to enforce consistency, lint rules, and human-authored files for Claude Memory. It’s insanely powerful when doing by a human 100%. It’s conversely harmf…

  14. comment
    Comment #49053154

    Opus 5 broke me; I can’t cognitively deal with Anthropic’s bullshit anymore. I am thankful for the kick in the ass for me to switch full-time into my bespoke harness utilizing open…

  15. comment
    Comment #49036549

    Funny how rule #3 is > No nudity, lewdness, or sexually suggestive imagery. If it wouldn’t be appropriate for a workplace or younger audience, don’t post it here. NSFW tags are not…

  16. comment
    Comment #49030036

    Please, no.

  17. comment
    Comment #48972239

    > once the sub-matrices get small enough, the next rabbit hole starts when you try to start lifting F_2 into Z for a given tensor.

  18. comment
  19. comment
    Comment #48956758

    Now, stuff like _this_ is why I keep coming back to HN.

  20. comment
  21. comment
    Comment #48948980

    tl;dr CLAUDE_AFK_TIMEOUT_MS=2147483647 I built in Human blockers into my agentic workflows with great intention, so naturally this annoyed me deeply. 14d ago, I was elated to see a…

  22. comment
    Comment #48920017

    Valid question. If I were further along and had the time to succinctly write up all my contributions, I would just point you at my blog post. I’m generally a poor communicator, so …

  23. comment
    Comment #48915570

    My mouth is agape at the fact that this project is basically what I have been working on non-stop for the last three weeks and just yesterday gotten to the point of evaluating; hat…

  24. comment
    Comment #48894257

    Even better: you can fork the exeuntu image & make it immediately more relevant to the things you do in addition to just dropping in your programs and such.

  25. comment
    Comment #48894124

    I’m shocked I had to scroll this far to find the first sensible reply.