VirtusLab's Articles

Artificial Intelligence|Published: May 12, 2026

We're Building on Quicksand, and Most Teams Don't Know It

Tomek Lelek and I wrote Vibe Engineering because we kept seeing the same mistake everywhere: teams confusing the speed of generation with the speed of delivery. Vibe coding, that intuition-first, prompt-driven mode where you accept what the AI gives you without deep verification, is genuinely valuable. It's the digital sketchpad. It's how you turn a foggy idea into a working interface in an afternoon. I use it. You probably should too.

Scala|Published: Apr 30, 2026

Introduction to Scala 3's Capture Checking and Separation Checking

Languages like Rust mitigate these problems through ownership and lifetimes. But how do we bring these ideas into a GC-based language like Scala in a way that doesn't break existing programs? In other words, we want to track access rights (capabilities) to resources (objects in the object-capability model), while leaving memory management to the GC. Scala 3's answer is Capture Checking + Separation Checking.

Artificial Intelligence|Published: Apr 21, 2026

Visdom: Shadow AI Is Already in Your Codebase

This is post #4 in The Agent-Ready SDLC series. In post #1 we laid out the Ferrari-in-a-Fiat-500 problem - the engine is great, the chassis isn't. In post #2 we covered the first bottleneck: context. In post #3 we covered the second: feedback loops. Now we're at the third piece - and it's the one nobody wants to talk about.

Artificial Intelligence|Published: Apr 15, 2026

Sandboxing LLM coding agents: part 1

LLM coding agents moved fast from cloud demos to tools running on developer workstations. They don't just suggest code anymore. They execute it. They start shells, install packages, edit repos, run tests, and sometimes open PRs. All with the same permissions you have. In the first part of the miniseries, Jakub Bocheński will look at Context, Motivation, and available sandboxing tools.

Artificial Intelligence|Published: Apr 7, 2026

Visdom: Your README Is a Lie

Open any README in your repository. That flagship one. The one that's 800 lines long with a "Getting Started" section written in 2022. Read it with fresh eyes - as if you were a new developer, or better yet - as an AI agent who's never been to a standup, never seen Slack, never heard the legend of why we don't touch the InvoiceReconciler class in the payment service. Now ask yourself one question: based on this README, can you safely modify anything in this service?

Artificial Intelligence|Published: Apr 3, 2026

SFT: Scaling Small Vision-Language Models for High-Load Invoice Processing

While API based LLMs are great for rapid, fast, and easy development, they can be less secure and costly in the long-term horizon for load-intensive applications. The solution are Small Language Models (SLM), self-hosted and finetuned on the downstream task. This article presents a case study of a Supervised Fine-Tuning (SFT) of the SLM on the Invoice Processing task. It shows that while SLMs have higher investment costs at start, they are faster, cheaper, and more secure in the long-term, especially for high-load intensive applications.

Artificial Intelligence|Published: Mar 31, 2026

Visdom: The Ferrari Engine in a Fiat 500

You've probably heard about the first METR study from July 2025 - it made the rounds at every conference and every newsletter. 16 experienced open-source developers, a proper randomized controlled trial (not a vendor survey), and the result: 19% slower with AI. In this article, Artur argues that the problem lies in the environment, not the model. Read on to find out exactly.

Artificial Intelligence|Published: Mar 25, 2026

GitHub All-Stars #16: Project N.O.M.A.D. - Civilization in a Docker Container

Welcome to GitHub All-Stars, our biweekly series where we pick a trending or freshly minted open-source project and put it under the microscope. We focus on new, relatively unknown gems - not another breakdown of the latest React release (because let's be honest, the world has enough of those). This time, we're looking at a project that lives at an unusual intersection of prepper culture, self-hosting enthusiasm, and edge computing philosophy. And it just exploded on Hacker News.

Artificial Intelligence|Published: Mar 25, 2026

Monorepo in Enterprise: Security, Myths, and Real Benefits

Monorepo keeps coming up in conversations about large-scale software architecture. For some organizations, it’s a way to bring order to a growing ecosystem of applications. For others, it raises a lot of concerns. We spoke with Bartek Sądel, an expert who works with enterprise monorepos, about how this approach works in practice, what questions companies ask, and what the real benefits and challenges are.

Artificial Intelligence|Published: Feb 25, 2026

GitHub All-Stars #14: NanoClaw - Your Personal AI Butler in a Container Cage

Today's subject has become one of the most talked-about open-source projects in the AI agent space, racking up over 11,000 GitHub stars in less than a month. We're looking at NanoClaw by Gavriel Cohen - a lightweight, container-isolated personal AI assistant that connects to WhatsApp (and Telegram, Discord, Slack, Signal) and runs on Anthropic's Agent SDK. Written in TypeScript, MIT-licensed, and built around one radical premise: the software that hosts powerful AI agents should be simple enough to read in eight minutes.

Artificial Intelligence|Published: Feb 16, 2026

How to improve your RAG: Move Beyond Flat Vector Stores

Most of the time, the knowledge base we want to chat and reason about with an LLM has strong inter-relations. Even the famous PageRank algorithm, which gave Google a competitive advantage and made it ahead of others, is based on the quantity and quality of links between websites. The relations within a knowledge base are crucial to fully understand it. The problem with classical RAG is that it chunks the text, discarding all internal relations. So can we do better?

Artificial Intelligence|Published: Feb 11, 2026

GitHub All-Stars #13: Matchlock - Your Agent's Bulletproof Cage (With Room Service)

Today's project dropped on Hacker News frontpage just days ago and instantly sparked one of the most interesting security discussions I've seen in a while. We're looking at Matchlock by Jingkai He - a CLI tool for running AI agents in ephemeral microVMs with network allowlisting and secret injection via MITM proxy. Built to answer a question that every developer running claude --dangerously-skip-permissions should be asking: "What's the worst that could happen?"

1 2 3 4