Archives
All the articles I've archived.
Running My Own Authoritative DNS — Seven Servers, Four Continents, One Git Repository
7 min readA look inside my self-hosted authoritative DNS infrastructure: Knot DNS, a hidden master, six public secondaries, automatic DNSSEC and Ansible-driven deployments.
Superset — When One Coding Agent Is No Longer Enough
7 min readAI coding is moving from one assistant in one terminal to several agents working in parallel. Superset shows what this new orchestration layer looks like — and where its limits begin.
One Week, Three Frontier Models — and a New Normal for AI Releases
9 min readFable 5 is back, OpenAI shipped GPT-5.6 Sol, Terra and Luna, and Grok 4.5 landed a day earlier — all in one week. A look at what each release actually is, and at the quieter pattern underneath: frontier models now launch through a government checkpoint.
Claude Fable 5 — Locked Out of a Model, Even Its Makers
6 min readI barely got to use Claude Fable 5 before a US export-control directive cut off access for every foreign national — including, in effect, the people who helped build it. A few honest thoughts on the potential I glimpsed, what happened, and why I hope it comes back the right way.
Quoven — Building the Evidence Layer for Product Decisions
9 min readA build-in-public look at Quoven, my SaaS that turns a freeform brief into a sourced, structured dossier on a product decision — the multi-probe research pipeline, the stack, and the decisions I'm proud of.
Claude Design — The First AI UI Tool That Doesn't Feel Like AI
8 min readA hands-on look at Claude Design: what it is, why Anthropic built it, the results that surprised me, the unmistakable feeling that a real designer was in the loop, and the two ways out — Figma to keep designing, or Claude Code to ship.
LLM Inference — Where Your VRAM Goes and How to Get It Back
10 min readA practical look at LLM inference: how context, KV cache, and model weights compete for VRAM, why Q8 on the KV cache is a free win, how quantization formats like GGUF and MLX compare, and why vLLM beats Ollama or LM Studio when you actually need throughput.
OpenClaw — An Open-Source Personal AI Agent You Actually Own
9 min readA hands-on look at OpenClaw: what it is, how MEMORY and SOUL give it a personality that sticks, why the brain is swappable but the architecture isn't, how to keep it secure, and why Telegram is the ideal gateway.
BMAD Method — Structured AI Development From Idea to Code
9 min readA practical look at the BMAD method: what it is, how its specialized agents guide you through a real development workflow, why it pairs perfectly with Claude Code, and an honest comparison with vibe coding.
Claude Code — The AI Coding Companion That Changed My Workflow
9 min readA deep dive into Claude Code: what it is, how it differs from Claude.ai, why the Max subscription is a bargain compared to API costs, and how MCP servers and built-in tools make it a genuine productivity multiplier.
Building an MCP Server for Switzerland's Public Procurement Platform
5 min readHow I built simap-mcp, an open-source MCP server that lets AI assistants search and browse public tenders on SIMAP.ch.
Hello World — Why I'm Starting This Blog
Updated:2 min readA quick introduction to who I am, why I decided to start a blog, and what you can expect to find here.