Building an API to Control Glue Heads on a Machine. It Was... Complicated
Recently I got a very practical engineering task: build an API for several industrial glue units.
Technical Writing
Notes and case studies on machine learning, AI systems and engineering practice.
How to Build a Local AI Agent for Factory Documentation
In manufacturing, we have a typical factory problem: there is a lot of documentation, it comes in different formats, some of it is in Russian, some in English, some in Chinese, and you need to search through it quickly and preferably without mistakes.
Shadow Inference at the Factory: How to Test ML on a Real Machine Without Breaking Anything?
In my previous article, I wrote about how I cleaned PLC signals, removed leakage, separated real precursors from the usual machine modes, and generally tried to understand what exactly the model found.
Cleaning PLC Signals for ML and the Trap with Machine Modes
So, we have a few thousand signals from the PLC, and the first thought is: great. A lot of data means the models will have plenty to choose from. But it turned out to be almost the opposite.
Manufacturing Defect Prediction: The Real Problem Was Data Accuracy, Not the Model
The ML model starts with the question: do we even understand what our equipment is giving us?
Auditing Manufacturing Defects: A Less Obvious but Important ML Task
As counterintuitive as it may seem, an ML model doesn’t start with Python. It starts with the question: what do we even consider a defect?
Setting Up Grafana for PLC Monitoring: How I Made It Work with ClickHouse
If you have a lot of data (whether you're collecting it or working with big data), you need not only to store it but also to display it properly.
How I Dealt with PLC Signals: From "Some Bit is On" to Proper Diagnostics
Continuing the series of articles "ML at the Factory." Before building models, forecasts, and pretty graphs, you need to learn to understand what actually comes from the equipment.
How I Organized Factory Data: Documentation, Migration, and ClickHouse
I recently started working as an ML engineer at a factory, and I quickly realized one simple thing: a model is not just a notebook, features, and metrics.
Preparing an Industrial Machine for ML: Reading Less, Extracting What Matters
When I started getting into embodied AI, I thought I would quickly bump into neural networks, datasets, and model architectures. But reality turned out to be different: first, I bumped into the factory.
Vibe Coding, or Why It's Now Important Not Just to Write Code
There's a feeling that development has gone a bit crazy over the last couple of years.
OpenEffect Is Out in the World
A couple of months ago, I announced a new project.
Building a Russian Passport OCR Service
Recently, I was building a small OCR service for recognizing Russian passports.
PaddleOCR - Recognizing Text in Photos
About a year ago, I started working on a small commercial product with a telling name, Zada4kin...
Models for Video Generation — Kling and Wan
How it works and why prompts are critically important here (unlike LLMs)
How Credit Scoring Really Works (A Simple Example)
The other day, I decided to Google my credit history. Just for general knowledge. Here's what came out of it.
Debugging and Reading Other People's Code: A Key Skill in the Age of Neural Networks
Nowadays, almost everyone has heard of the trendy term "vibecoding." But can we call everyone who generates code using neural networks a vibecoder?
Pipeline: How to Create a RAG Service from Video
Here, I will detail what I encountered during the creation of my N-GPT RAG LLM Service.
RAG - what is it?
You encounter this every day, but you probably don't fully understand what it is.
Automated Job Search on Yandex Career
I got tired of manually sifting through irrelevant job postings and put together a simple tool that parses job listings, filters them through an LLM, and leaves only those that really match my stack.
Chunking in RAG
Why ML engineers often underestimate it. How chunk size affects the quality of the entire LLM+RAG system.
Dynamic Taxi Pricing: Why?
A simple explanation of why taxi prices are constantly changing: demand, supply, coefficient, adjustments, and the role of machine learning...
AI Has Already Taken Over the World…
How machine learning algorithms decide which videos and posts you see in your feed.
So, What Is This AI Everyone Keeps Talking About?
A simple explanation of what machine learning is and how artificial intelligence really works.