How I work with Claude Code

aleks — Wed, 10 Jun 2026 00:00:00 +0000

Since 2025, I have been using AI tools as part of my daily work. Not as a replacement for thinking — as a productivity aid. An AI coding agent has become a regular part of how I work on infrastructure, blog posts, and software projects. Most of what follows likely applies to other agents as well — Cursor, Copilot, or whatever comes next. I happen to use Claude.</p>

This post is not a tutorial and not a pitch. It is a reflection on what actually works — for me, on my projects — across months of real use, across 40+ projects, and across months of agent use.</p>

LLM Inference on OVH MKS: Connect IDEs and Web UIs

aleks — Tue, 02 Jun 2026 00:00:00 +0000

The first four parts of this series deployed a vLLM inference endpoint at https://llm.YOUR_DOMAIN/v1</code>, protected by a Bearer token, running on an OVH RTX5000-28 GPU node. This part shows how to connect coding assistants, web UIs, and other OpenAI-compatible clients to that endpoint.</p>

Alek's Blog - vscode

How I work with Claude Code

LLM Inference on OVH MKS: Connect IDEs and Web UIs