Oh-my-pi – The Harness Playbook

(stencil.so)

33 points | by maherbeg 2 days ago ago

11 comments

  • Centigonal 2 days ago ago

    The more people use agents, the more they write like agents. The author seems to have put significant effort into this post, but when I read something like the below, my brain just immediately checks out.

    > # What one authority buys

    > With state and transcript in one tree, several hard problems reduce to the same operation.

    > Rewind is a DOM diff. Diff the current materialization against the target state. A <subagent> element disappeared? Terminate it by destroying the element. One appeared? Resume or spawn it by creating the element. The delta itself is the complete lifecycle work list.

    A sentence like "The delta itself is the complete lifecycle work list" gives me mental indigestion. I have to spend 30 seconds dissecting it to figure out what the author is trying to say. When every other sentence is like this, the post becomes unreadable.

    • jdkoeck 2 days ago ago

      Did the author really put significant effort here? The LLM speak suggests the opposite.

      • solarkraft 2 days ago ago

        > These are not market personas. They are architecture tests.

        Indeed.

    • smcleod 2 days ago ago

      It all smells pretty load-bearing to me.

      • cheikhcheikh a day ago ago

        But is it byte for byte identical ?

        • smcleod a day ago ago

          You're right to push back.

  • localroast 2 days ago ago

    Oh-my-pi is designed to be slim apparently but has a ton of useless features with little empirical justification. Pi is a good harness- probably the best, but OMP not so much.

    One thing I hate about OMP more than anything else though: hash anchored edits. they don't work in practice; most models I've tried have spent more turns on repairing their broken edits than on the actual task.

    • coffeeindex a day ago ago

      From what I’ve read/heard, a lot of the power of Pi is its extensibility but it’s a hard sell for me to try it out just because I can extend it. How is it out of the box?

    • riedel 2 days ago ago

      I like it a bit for the inspiration what could make sense, however, as there is little ablation studies, it is really difficult to understand the effect of most of the features.

  • wolfiesch 2 days ago ago

    BILLIONS MUST OMP

  • poppafuze 2 days ago ago

    Slopmaxxing text.