📰 Dev.to · Ai developer

"Vnedryaem" — The Universal Engineering Mood in One Word No text. Just the word...

The Open Source Illusion: Why "Free" AI Models Are Getting Expensive Everyone's watching...

I Tried the "Colleague Skill" — Digital Cloning an Employee The Colleague Skill project...

RAG SOTA: I Built SEQUOIA and Tested 7 Pipelines — Full Results After 20+ hours of compute...

AI Conf 2026 Moscow: Why I'm Attending (and You Should Too) April 20, Moscow. AI Conf 2026...

Most discussions about LLM performance focus on the model architecture and prompting. But there's a hidden factor: the tokenizer. It determines how much of your

Most discussions about LLM performance focus on the model architecture and prompting. But there's a hidden factor: the tokenizer. It determines how much of your

Spent two days at AI Conf in Moscow. The shift is complete: nobody talks about traditional ML anymore. It's all agents, RAG, and voice systems.

I wanted a local AI assistant. Expected: 2 hours. Reality: 2 days of edge cases, broken dependencies, and discovering that "local" doesn't mean "free."

After 20+ hours of compute time on local hardware, I benchmarked 7 RAG configurations against real-world tasks. SEQUOIA (RAPTOR tree + step-back prompting) cons

After tracking open-weight LLM releases for the past two months, here's what's actually moving the needle. Not hype — architecture and data decisions that matte

RAG SOTA: I Tested 7 Pipelines and Built SEQUOIA (Open Source) After 20+ hours of compute...