Skip to content
Xeron
Go back

Model Orchestration

Published:
Suggest Changes

Max Tokens, Max Thinking

Just bought ChatGPT Pro at $200/month — felt like I had to max it out to get my money’s worth. Plus everyone knows gpt-5.4 xhigh is the strongest coding model. So I cranked everything to max. More thinking must be better, right?

What Broke

After a stretch at high intensity — 500M tokens a day, 2–4 windows, each with 0–3 subagents — the cracks showed.

Slow. xhigh is genuinely stronger, but it’s also genuinely slow. For everyday coding, the idea has already gone cold while the model is still deep in thought.

Premature optimization. Most obvious in glue code: it invents compatibility for legacy logic you don’t need, and plans for contingencies that aren’t on the roadmap. Progress drags, code doesn’t get better.

Wait forever, get a worse result.

Thinking via OMO

I’d brushed past oh-my-opencode before without getting why model orchestration matters.

The point of subagents isn’t more thinking — it’s division of labor. Right agent for the right job.

OMO lets you assign different models to different roles:

RoleResponsibilityModel
Sisyphusoverall coordination, task breakdowngpt-5.4 high
Hephaestushands-on codinggpt-5.4 high
Oraclearchitecture decisionsgpt-5.4 high
Explorefast codebase searchgpt-5.4-mini-fast medium
Prometheus + Metisupfront planninggpt-5.4-mini-fast high
Momusrigorous review, nitpickinggpt-5.4 xhigh
visual-engineeringfrontend visualsgemini-3.1-flash-lite-preview high
Librarianknowledge retrievalgpt-5.4-mini-fast high
Atlasdeploy & opsgpt-5.4-mini-fast high

Simple logic: reserve xhigh only where deep thinking matters.

Speed returns, flow stays intact. And where depth is needed, it’s still deep.


Suggest Changes
Share this post on:

Previous Post
Polymarket Weather Markets — Field Notes
Next Post
Linear or Compounding