A while back, I decided to train a language model from scratch—not fine-tuning, not LoRA-adapting—but building it all out: initializing weights to noise and building a custom tokenizer from my own corpus. The goal was deeply technical and slightly irrational: I wanted to understand what happens *inside* these models. Not just at the API level, but during those 2 AM moments when the loss curve starts behaving weirdly.
Read more →
I was writing Go applications since 2016 and I was able to go thru various dependencies management systems including famous at some point DEP and now built-in go modules. While go dependency management came long road in language history it still has one major flaw – all dependencies are downloaded from Internet, mostly from github […]
Read more →
Recently, I took on a project to build AChat, a chat application that runs on my local network and operates entirely offline. The challenge was to utilize a powerful AI model, Meta’s LLaMa, while keeping everything on-premise, without relying on cloud services. It turns out, when you have a GPU-equipped server at home, it’s entirely […]
Read more →
What are the limitations of AI currently developed by the biggest companies like Meta, Google, or OpenAI? Since I started developing applications and APIs utilizing various machine learning models to predict local weather, recognize handwriting and translate it to LaTeX, solve mathematical equations, predict cryptocurrency trends, and auto buy/sell BTC, ETH, and others, I have […]
Read more →This blog runs on open, proven tools — chosen for reliability, not popularity.