ARCANADA

Blog

Articles, insights, and deep dives from the Arcanada team.

Cubrim-2: The Global Addresser and a Shared Language for Data
Blog July 15, 2026

Cubrim-2: The Global Addresser and a Shared Language for Data

Cubrim-1 is already a measured archiver. Cubrim-2 asks a separate question: can devices share a verified memory in advance and transmit only what is not there yet?

Building the Binary Is Only the Beginning
Blog July 11, 2026

Building the Binary Is Only the Beginning

Cubrim’s first public release exposed the work between a finished binary and software a user can actually download, install, and run.

Cubrim. Or How Dreams Come True with AI
Blog July 8, 2026

Cubrim. Or How Dreams Come True with AI

The story of how an old student-era idea about data compression sat in my head for years and finally came alive — with the help of AI agents. Today Cubrim reached the top of the world compression benchmarks.

After Self-Healing: Why Agents Need Autonomy Levels L6 and L7
Blog July 1, 2026

After Self-Healing: Why Agents Need Autonomy Levels L6 and L7

In the previous article I mapped the telecom L0–L5 autonomy scale onto AI agents. But for agent systems, L5 is the ceiling only for a single agent. Beyond it comes self-assembly: an agent that builds other agents (L6), and an ecosystem that develops itself within human-set bounds (L7). I work through both levels, separate them from an ordinary multi-agent workflow and from AGI, and show where Arcanada fits.

Show Me How You Will Do It?
Blog June 25, 2026

Show Me How You Will Do It?

The engineering war against agent hallucinations — not the abstract kind. The simplest question I ask an agent before every step, and why it changes how the model works.

The Human at the Console: Procrastination, Switching, and the Long Game
Blog June 24, 2026

The Human at the Console: Procrastination, Switching, and the Long Game

The finale. Not about technology — about the human who built the system and still sits at the console eighteen hours a day. About procrastination, about how to keep from burning out by switching between projects, and about what it is all even for.

Angry Robot Deals: How Agents Revived a Project That Was Draining Me
Blog June 23, 2026

Angry Robot Deals: How Agents Revived a Project That Was Draining Me

How agents revived a personal trading project: they cleared the backlog, one robot has been running on Forex for a year — and the next step of trust: handing them a public Telegram channel to run on their own.

Seeing the Invisible: An Agent Graph on the TV
Blog June 22, 2026

Seeing the Invisible: An Agent Graph on the TV

A status dashboard for Android TV — a native app that will put the task graph on a large screen. The goal: see agent activity without manual checks and notice stalls in hours, not days. Still a plan, not a finished system.

Your Own Disk vs Dropbox: A Red Ocean and the Right to Undercut
Blog June 21, 2026

Your Own Disk vs Dropbox: A Red Ocean and the Right to Undercut

Disk Arcana — file sync built on an economics-of-ownership model: free and open on your own server, a small fee on someone else's. Why the giants can't follow.

From Voice to Meaning: Transcribator and Verdicus at Work
Blog June 20, 2026

From Voice to Meaning: Transcribator and Verdicus at Work

Transcribator combines speech recognition and speech synthesis, while Verdicus turns voice and screenshots into notes. Shared context between the products remains a roadmap; Verdicus App Store publication is the next step on that path.