‹ BackHN Continuity

Thread

Grok 4.7

609 points · 541 comments · meetpateltech

  1. Saline9515 · · focus · HN ↗
    I tried in Omp (Oh-my-pi), and so far it's really problematic.

    It will loop in thinking mode ("Let me implement those fixes: Fix 1, Fix 2, Fix 3 .... Fix 80, Fix 81"), ignore the AGENTS.md instructions, corrupt plan files, etc etc... I have 5.6 Sol as advisor/watchdog, and it blocks every turn, I never saw this. Quite a shame, 4.6 wasn't so bad.

    1. xmorse · · focus · HN ↗
      OMP is a joke. don't use that garbage
      1. Saline9515 · · focus · HN ↗
        Can you explain your opinion? I'm curious but such vague comments won't convince me.
        1. samtheprogram · · focus · HN ↗
          Probably the same reason as oh-my-zsh, you don't need 90% of it. Further compounding the problem in an agent harness is that you are polluting the context window by throwing the kitchen sink at it.
          1. marwatk · · focus · HN ↗
            I've been experimenting with omp because:

              - it allows different models within one session via roles which helps me save tokens
              - it's much more likely (ime) to use the LSP over grep for determining how code fits together
            
            But I agree a 20k+ starting context is way overkill.

            I find it's very hard to get information on harnesses people are using. I have to stay model agnostic so I avoid claude, codex, cursor, etc. I've used and tried opencode, which worked well, but obviously lacks the above features.

            Does anyone have a resource for following what people are actually being productive with? With so much vibe going on it's hard to separate the wheat from the chaff.

            1. codeIMperfect · · focus · HN ↗
              Exactly! All these harness claims are just trust-me-bro, someone says omp is great for token saving, some other guy says it burns tokens...like dude which is it
        2. xmorse · · focus · HN ↗
          this summarizes the average OMP user and dev

          <a href="https:&#x2F;&#x2F;x.com&#x2F;greg_horvay&#x2F;status&#x2F;2100764473392820433?s=20" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;greg_horvay&#x2F;status&#x2F;2100764473392820433?s=20

          1. raincole · · focus · HN ↗
            What a crazy thread lol. I really can&#x27;t tell who is serious and who isn&#x27;t there.
          2. Saline9515 · · focus · HN ↗
            Again, this is vagueposting, what do you have against snapcompaction? It seems to be a nifty way to save token costs. At least it&#x27;s an interesting innovation. <a href="https:&#x2F;&#x2F;x.com&#x2F;_can1357&#x2F;article&#x2F;2064802476742574459?lang=en" rel="nofollow">https:&#x2F;&#x2F;x.com&#x2F;_can1357&#x2F;article&#x2F;2064802476742574459?lang=en
      2. unrvl22 · · focus · HN ↗
        you are a joke if you think omp is a joke.
      3. polytely · · focus · HN ↗
        what do you use and why do you prefer it over omp
        1. raincole · · focus · HN ↗
          Just pi. `pi install` the packages you actually need or ask LLM to write a package for you. Keeping the harness minimal is the point of pi.
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.