Ask HN: Which harness do you use with Qwen3.8 27B? And why?

I tried several but for me the biggest difference is the browser integration tool/skill. Because without that any model is quite limited to debug the code at runtime

2 points | by grigio 4 hours ago

5 comments

  • ezulabs 7 minutes ago
    you shall use CC, serve it via ollama, you need to patch it as CC's timestamp ruins prefill cache.
  • wookmaster 4 hours ago
    I've been mostly drawn to pi simply because I can modify it so easily to have extensions or behavior I want.
  • slipwalker 3 hours ago
    pi.dev with

    "packages": [ "npm:context-mode", "npm:pi-subagents", "npm:pi-web-access", "npm:pi-bar", "npm:pi-opencode-bridge", "npm:@ssweens/pi-leash", "npm:pi-caveman", "npm:@ff-labs/pi-fff", "npm:pi-ui-hephaestus", "npm:@alexanderfortin/pi-zai-usage", "npm:pi-cache-optimizer", "npm:@hypabolic/pi-hypa" ]

  • bilsbie 4 hours ago
    You need a harness? Does llama include one?
  • verdverm 1 hour ago
    opencode, pretty good setup out of the box, no need to go through and find packages for the basics like pi

    there are MCP/skills for browser integration that work in any harness