Welcome to my blog 👋

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. ...

“Study, Study, and Study Again!” (c) V.I. Lenin Why bother? So here’s the task: build an AI assistant that uses an SLM (Small Language Model) to extract personalized information about the user. Why SLM? Well, privacy — data doesn’t leave the device, plus cost savings. We don’t need the details here — the point is to figure out whether this is even feasible with acceptable quality, what thorns await us, and what to do about it. Let’s go! ...