Stealth endpoint union-alpha 404s now redirect to unbiased/pareto, a multimodal composite model running multiple models per request. Plus a practical model rotation for large-repo TypeScript/Svelte/Android agent work: DeepSeek V4.1 Flash as daily driver, GLM 5.3 for hard reasoning, V4 Flash 0731 for bulk work, Pareto and Big Pickle as free parallel workers, and why GLM 5.3 Flash deserves a spot.
How I built a zero-cost coding-agent fleet using MiMo Pro delegates, OpenRouter free-tier lanes, and the mystery Ox Alpha model that turned out to be GLM-5.3-Flash — now wired into Fugu and T3.
I rebuilt my Fugu/Fusion coding harness around the models that are actually available: GPT-5.6 Sol conducts, Fugu executes through bounded specialist lanes, and a three-model remote Fusion panel reviews important work before the conductor decides.
A case study on treating QBO Mail Dashboard as an internal operations workflow that can sell consulting/productization work without pretending to be a public SaaS product.
A practical case study on narrowing PixelBoats from a broad game prototype into a smaller Android-first animated visual product lane with ASO metadata, proof assets, and conservative sales boundaries.
A self-case study for Keyword Astro: using the ASO workflow, screenshot proof, source-labelled metadata, and RC/final release split to make the product more saleable without overclaiming rank or popularity metrics.
The archived June 2026 version of my local Fusion/Fugu harness, preserved as the historical setup that preceded the GPT-5.6 Sol conductor and three-model remote Fusion panel.
A field note on wiring GLM-5.2 into Hermes through Cloudflare Workers AI, hitting quota pressure quickly, and landing on a safer lead/delegate architecture for expensive reasoning models.
A real setup for driving NVIDIA Nemotron 3 Ultra (550B-A55B) behind a Hermes agent, including the stale-stream timeout fix, thinking-mode tool-use settings, sampling defaults, and the practical 256K vs 1M context-window tradeoff.
A practical comparison of ChatGPT Deep Research and DeepSeek-style reasoning APIs, focused on workflow, retrieval, transparency, and what builders should actually take away.