Welcome to my blog 👋

Agentic AI: the agent engineer’s stack This piece grew out of the job ads for agentic Python engineers - those requirement lists where PydanticAI/CrewAI/LangGraph, MCP/A2A, evaluation frameworks and vector databases all sit next to each other. I keep running into them, and I’ve noticed that most candidates are hopelessly lost in these questions. Even the prospect of switching to manual labour in the near future doesn’t seem to motivate them to pick up the skills, and there really isn’t that much to pick up. Sure, there is a category of geniuses who mostly live in anonymous comment threads, but I’m talking about ordinary earthly people, the ones I actually meet, and they are who this is written for. So, dear nobody-in-particular, this should help you get through the interview and keep yourself fed for a while longer in these lean times. ...

Dissecting the Transformer. Part 1 In this article the author attempts to make sense of the transformer architecture — everyone has heard of it, everyone “knows” it, yet hardly anyone truly understands it. So the goal here is to explain things at a conceptual level, without arcane mathematical formulas and unreadable definitions. Let’s admit that explaining theory in simple, clear words is a true art, accessible to few of the Landau-and-Lifshitz caliber — but in our age of decadence and postmodernism we shall try as best we can. And yes, the author does not guarantee 100% accuracy of what follows — only his own understanding of it. ...

On-Prem LLM Deployment: Our Cow, Our Milk Who’s to blame? What’s to be done? (classic Russian questions) We’ve been noticing that in our turbulent, multipolar-world-in-the-making era, more and more requests are coming in for on-prem LLM deployments. There are plenty of hidden pitfalls and not much accumulated experience — so let’s try to work through it. — How’s the project going? — We’re in the final stage! — Great, are you wrapping up? — No, we’re looking for someone to blame! ...

Agent Teams: The Commander and His Crew In one of my previous posts I wrote about how our role as IT people is shifting — as we desperately try to stay afloat a little longer before inevitably having to retrain for more practical professions. The question then is: how do we manage agents that, in terms of behavioral patterns, closely resemble the chaotic crew of a rattling jalopy barreling across the steppe? The Commander managed them just fine — so let’s give it a shot ourselves. ...

How Transformers Work: A Plain Explanation Let’s revisit transformers and try to figure out how they actually work — as usual, minimal math and no AI-generated filler. The author makes no claims to absolute truth and may occasionally get things slightly wrong. 1. Let’s Start Simple Let’s refresh our memory on how recurrent networks worked — the ones that “loop back to themselves”. Hard not to think of Hegel’s Absolute Spirit, which travels a path of self-alienation only to return to itself — pure Hegelian recurrence. ...