From 6f612f028550fffe0424bde09861f19d0a85764d Mon Sep 17 00:00:00 2001 From: Zero Date: Sun, 25 Oct 2026 19:50:21 -0500 Subject: [PATCH] Model-Best-Practices: Ornith Q8 briefing for planner models --- .../Ornith-q8-best-practices.md | 35 +++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 Model-Best-Practices/Ornith-q8-best-practices.md diff --git a/Model-Best-Practices/Ornith-q8-best-practices.md b/Model-Best-Practices/Ornith-q8-best-practices.md new file mode 100644 index 0000000..f85c9aa --- /dev/null +++ b/Model-Best-Practices/Ornith-q8-best-practices.md @@ -0,0 +1,35 @@ +# Ornith Q8 best practices + +How to get real work out of Ornith 1.5-9B (Qwen3.5-based, 8-bit / Bfp8) on one Tenstorrent p150 through Pantheon + Argus. From the 2026-10-25 runs (social-media doc, K80 MTP Phase 1). + +## What it's good at +- Mechanical engineering work: git merges (incl. a real conflict), detached remote jobs + polling, reading results, pushes. +- Following written rules that are still in its context. +- Writing careful commands with small outputs. + +## What to expect +- **Work is more reliable than its reports.** It mixes up similar events and states them confidently. Never trust its summary or the notes it writes into a plan; check against git and logs. +- **It doesn't explore on its own.** A plain ask gets generic output; "read X first" gets accurate output. +- **It doesn't know when it's done**, and doesn't push back on a task that makes no sense (an hour on an already-finished phase; 42 min re-verifying finished work). +- **Thinking is the cost, not tools.** Reasoning blocks run 4–10k chars. Decode is fast at short context (~50 tok/s greedy with MTP, ~21.5 plain) but ~8 tok/s at 51k context. + +## How to brief it +- [ ] Name the exact files to read, in order. For big files, give the `grep -n` to find the right part. +- [ ] Write every rule down; it misses rules that were only said in conversation. +- [ ] Every step ends in a check that is a command with the exact expected output, not "looks right". +- [ ] Include the stop rules: "if your task is already marked done, say so and stop"; "two failed checks → write `BLOCKED:` and stop". +- [ ] Say where scratch files go (in the repo, never `/tmp`). + +## How to run it +- [ ] **One task card per session; fresh session per card.** Don't keep saying "continue" into a long session. +- [ ] **Keep context small** (well under ~50k tokens): decode slows a lot past that, and when the agent compacts a long context the model can lose its place. +- [ ] **The plan file is the memory**: every step leaves a one-line note in the plan, so a fresh session can resume. +- [ ] For long remote jobs, expect sleep/poll loops that look like a hang; check `argus.log` before assuming it's stuck. +- [ ] Double-check the files you hand it are the right ones (two similarly named plans cost an hour). + +## Before anything lands +- [ ] Verify its claims against git, the logs and the real files: the step that caught every bad note in Phase 1. +- [ ] Only a human (or a stronger model on the human's go) merges or deploys. + +## Split of labour +Ornith executes the long, mechanical, hardware-bound work on our own machines; something stronger verifies before merge.