14 comments

  • p0w3n3d 1 day ago
    In other words, the Quibbler siphons wrackspurts away from your code.
  • janpio 1 day ago
    The demo video in the GH page didn't work for me, but there is also one on Twitter/X: https://xcancel.com/fulcrumML/status/1984054489851310191
  • gexla 1 day ago
    More explanation here that I found by Googling around. Though not sure it has more info than the Github page.

    https://fulcrumresearch.ai/2025/10/22/introducing-orchestra-...

  • stacktraceyo 18 hours ago
    Can the same concept be used for non coding tasks?
  • nberkman 1 day ago
    Submitted a PR with AWS Bedrock support: https://github.com/fulcrumresearch/quibbler/pull/5/files (credits!)
  • balleddog 1 day ago
    Is an anthropic api key really necessary? A major roadblock for taking a test drive. Already have a Claud Max subscription but an anthropic api key still need at least 5$/mon extra.
    • epiccoleman 1 day ago
      I really want Anthropic to let me make an API token that pulls from the same pool of usage that my Pro subscription does with the official clients. It would be cool to be able to run experiments with alternate clients and automation and stuff without having to go swipe the card at the ol' API token refilling station.
    • asn0 1 day ago
      You could use the prompts in the code to create a Claude Code sub-agent[1], which would do the same thing without an API key

      1. https://docs.claude.com/en/docs/claude-code/sub-agents

      • threecheese 7 hours ago
        How would you invoke the subagent? Can a HookResponse cause a subagent to be invoked, to perform analysis on the action taken and then inject that back into the main loop?

        Or would the hook invoke another instance of claude code?

        I just read through the hook docs and I’m a bit fuzzy on the bidirectionality of it.

    • thenthenthen 1 day ago
      Sounds like video streaming services…
  • selfawareMammal 1 day ago
    An agent's agent?
    • hikarudo 1 day ago
      A gentleman's gentleman!
    • oneandonley1 1 day ago
      Sounds like a wip to me, "do it better or get punished"
  • agarttha 1 day ago
    Replace the middle manager
  • mouse_ 1 day ago
    There's so many agents to handle my agents, I'm gonna need agents for my agent agents soon.
  • etherio 1 day ago
    hey HN! happy to answer any questions

    this kind of tool is especially useful in longer running tasks to enforce your intent without having to check in on your agent all the time

    • anonymous908213 1 day ago
      Can users stack Quibblers, so Quibbler 2 corrects Quibbler 1 if, say, it fabricates an issue in the code it's reviewing? If so, have you found an optimum number of Quibblers for the Quibbler stack? Also, might users form a Quibbler council such that multiple Quibblers review the same thing and form a consensus before proceeding?
      • Balinares 1 day ago
        I love the pixel-perfect precision with which this comment is straddling the Poe's Law line.

        That aside I also love the concept of Quibbler Council and I'd get a kick out of seeing it in action.

        • sheepscreek 1 day ago
          MoQs - Mixture of Quibblers? Would be convenient to have them run on dedicated FGPAs. Then they can facilitate near real-time quibbing at the network level across all packets.
  • anonymous908213 1 day ago
    But who polices the vibe police?
    • Brajeshwar 1 day ago
      “Well, who’s gonna monitor the monitors of the monitors?” — Enemy of the State (Movie)
  • qq66 1 day ago
    > We’ve found Quibbler useful in preventing agents from: 1) fabricating results without running commands

    What a world we've created for ourselves

    • N_Lens 1 day ago
      Next step is critics for the critics.
  • cjonas 1 day ago
    Vibeception