Engineering notes
A Canopy-styled hub for the current blog.canopydigital.ca stream: AI operations, static delivery, local tooling, and production debugging. Articles stay canonical on the blog subdomain.
Featured latest -
Fable 5, GPT-5.6, Kimi K3 and Qwen show why the durable AI advantage is shifting from a single best model to the fleet, harness and execution layer around many models.
Read in Canopy styleCurrent stream
Each card opens the in-site Canopy-style summary while preserving a canonical article reference on the blog.
Fable 5, GPT-5.6, Kimi K3 and Qwen show why the durable AI advantage is shifting from a single best model to the fleet, harness and execution layer around many models.
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.
Today's Pulse Pro focus is Lab routes: prove the composition-spike path, crosscheck gates, and keep parked engine-eval rows from becoming false P0 work.
OpenAI has moved GPT-5.6 from limited preview to general availability across ChatGPT, Codex, and the API. The release raises the capability ceiling for coding agents while making version hygiene, access controls, and network boundaries more important.
A repo-truth-first Pulse Pro briefing for the rotated Composition-spike renderer focus: prove the PixiJS/Corsair composition spine and owner-GPU frame budget before new renderer stages.
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.
A practical product strategy for turning the old Astro email/calendar idea into a 2026 Windows-and-Android-first command center, with local-first privacy, staged launch discipline, and source-backed platform constraints.
A local Pulse-style briefing that turns the morning fusion run and no-edit scale/collision inventory into a concrete P0 intake queue.
Anthropic says Fable 5 returned on July 1, 2026; the operational story is access, safeguards, fresh limit resets, a temporary weekly allowance, and developer anxiety over whether the relaunch feels like the same model or a permissioned version.
A practical Windows PowerShell setup for running Claude Code against DeepSeek's Anthropic-compatible endpoint, with scoped environment variables, a safer launcher script, and a low-risk smoke test.
A local Pulse-style captain's log for the P0 boat footprint work, with the June 26 and July 2 follow-up pulses folded in as update notes instead of duplicate articles.
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 look at GLM-5.2, why its 1M-context claim matters, how IndexShare changes sparse-attention search, and what builders should do differently when exposing sources to coding agents.
A short note on bringing Canopy Digital into the same publishing fold as the personal technical blog without duplicating the content system.
A practical note on what Claude Fable 5's sudden departure and policy fight changes for serious coding and source-grounding workflows.
A backup-first Windows recovery guide for DeepSeek GUI conversations that appear to disappear after an app update changes the local data directory.
OpenJarvis is trending because it reframes the personal AI assistant as a local-first, measurable, editable agent stack instead of another cloud chat wrapper. Here is what matters, what is hype, and whether it can run on a normal developer PC.
Part 1 of a practical series on mixing DeepSeek V4 Pro, DeepSeek V4 Flash, and local Gemma4-style agents without turning a coding workflow into an expensive committee.
A practical comparison of ChatGPT Deep Research and DeepSeek-style reasoning APIs, focused on workflow, retrieval, transparency, and what builders should actually take away.
A Windows-focused adaptation of the mobile app factory playbook for the Microsoft Store.
Topic paths
The stream clusters around practical AI operations, SvelteKit/PHP static delivery, Windows-first local tooling, and debugging production-shaped failures.
Bring the notes into your system
Use the quote intake when you need a practical plan around AI workflows, static delivery, integrations, debugging, or production handoff.