Tag Archives: AI

Cold Storage for the AI Age: Remote LTO-4 Magnetic Tape Disaster Recovery for Homelab Infrastructure and Autonomous Agent Memory

By | October 11, 2026
0 Comment

In an era dominated by hyper-converged NVMe arrays, multi-cloud S3 buckets, and instant snapshots, magnetic tape might seem like a relic from 1980s mainframe datacenters. Yet, in modern self-hosted homelabs—particularly those orchestrated by autonomous agentic AI assistants like Google Antigravity (agy)—magnetic tape remains the undisputed king of physical disaster recovery. When your AI assistant operates… Read More: Cold Storage for the AI Age: Remote LTO-4 Magnetic Tape… »

Giving Local AI Assistants Long-Term Memory: Automated Session Archiving and Context Bridging with Antigravity (agy), SQLite, and Obsidian

By | October 11, 2026
0 Comment

When working with terminal-based agentic AI assistants like Google Antigravity (agy), you quickly realize that their raw reasoning power and tool execution are extraordinary. Whether diagnosing a degraded Btrfs array across remote NAS nodes, managing IoT smart home gateways, or optimizing complex build pipelines, an autonomous agent can orchestrate dozens of shell commands, inspect system… Read More: Giving Local AI Assistants Long-Term Memory: Automated Session Archiving and… »

How to Herd AI Models to Be Productive Engineering Partners

By | September 24, 2026
0 Comment

Left to their own devices, AI models are like cats: brilliant, but notoriously difficult to herd. Without a strict framework, even high-reasoning Large Language Models (LLMs) will drift into inefficiency, introducing architectural decay. To build production-grade software instead of a mountain of technical debt, engineers must enforce a methodology that treats AI as a disciplined… Read More: How to Herd AI Models to Be Productive Engineering Partners »

Home Assistant & Smart Infrastructure Setup (12): Off-Grid Smart Home Control, Bridging Meshtastic (LoRa) and Home Assistant Assist

By | June 23, 2026
0 Comment
Man controlling smart home dashboard on tablet connected to LoRa node device on table

Imagine controlling your entire smart home—closing blinds, turning off lights, checking room temperatures, or arming security systems—from miles away, without cellular coverage, internet access, or grid dependencies. By combining Meshtastic (an open-source, decentralized LoRa mesh network) with Home Assistant (the ultimate local home automation hub), you can build a secure, long-range, off-grid control link that… Read More: Home Assistant & Smart Infrastructure Setup (12): Off-Grid Smart Home… »

Home Assistant & Smart Infrastructure Setup (2): Interfacing with the UniFi Site Manager Cloud API

By | June 11, 2026
0 Comment

Goal: Query Ubiquiti’s cloud portal (unifi.ui.com) using custom API keys to track remote WAN status and local IP addresses of UniFi Express (UX) gateways. Before jumping into the script code, it is important to understand why command-line scripts are extremely useful for modern smart homes. Beyond convenience for terminal users, these CLI scripts act as… Read More: Home Assistant & Smart Infrastructure Setup (2): Interfacing with the… »

Hot on the web: AI stupid meter

By | September 18, 2025
0 Comment

This is a free promotion post to a very intelligent initiative: monitoring when AI goes stupid. Tired of AI Models Acting Up? Meet aistupidlevel.info Ever notice how your favorite AI model (Claude, GPT, Gemini, Grok) performs flawlessly one day, then “breaks” the next, giving you refusal after refusal? You’re not alone. We’ve all seen the inconsistent… Read More: Hot on the web: AI stupid meter »

AI clown world

By | June 6, 2025
0 Comment

Tired of all the absurd news that makes me feel we are living in a clown world. The best part I can ask gemini to describe it. Gemini generated clown world! AI will replace us, but we discover that most of the companies just fake it. We have AI companies that get busted for using… Read More: AI clown world »

Coffee, Flip-Flops, and AI Overlords: Maybe We Can Relax?

By | May 12, 2025
0 Comment

I had a bit of an epiphany today. Picture this: me, sipping coffee at some decadent resort in a warm country, contemplating the great existential dread of our time – AI taking all our jobs. It’s the big scare, right? Skynet’s coming for our spreadsheets and our artisanal cheese-making gigs. But you know what? It… Read More: Coffee, Flip-Flops, and AI Overlords: Maybe We Can Relax? »

Be your own media company, do not let others sell your work

By | May 18, 2026
0 Comment

Lately I have seen several good Twitter thread that resonated very well to my own conviction. Traditional media is dead. The printed press, the TV news, the traditional news agencies are all now just chasing the clicks, the sensational, the tabloid news. The quality of reporting is abysmal, the angle of the news is always… Read More: Be your own media company, do not let others sell… »

How to force locally run Ollama AI models to use all your CPU or GPU cores

By | May 12, 2025
3 Comments

Experimenting with different Ollama sourced AI models I discovered that sometimes in a very strange way my CPU or GPU resources are not used efficiently. By looking at the way Ollama models are packed we see that they are basically very similar to docker images where a full environment is specified. For example we can… Read More: How to force locally run Ollama AI models to use… »