on software and programming
What does it take to deploy your own, private LLM? What kind of resources do you need? And how much does it cost? We'll try and answer some of these questions in this post, in the context of one specific use-case: code completion. Tl;dr Price to performance
This is a very quick post on GitHub Copilot's constructs the prompt when serving code completions. Since Copilot isn't open source, the only way to figure this out is by dumping the request/response payloads and examining them. I used mitmproxy to log requests made by
This post is a follow-up to my previous post on fine-tuning an LLM to your own codebase: Build Your Own GitHub Copilot . You don't have to read that one to follow along here, but it would help if you do. In my previous experiment, we found that fine-tuning
How to train your own private coding assistant, on your code GitHub Copilot, Cursor, Windsurf, Cline, Aider, the list goes on. AI-powered coding assistants have established themselves as indispensable tools in software developers' tool-kits in 2025, and for good reason - they undoubtedly make you faster and more productive
The Transformer is foundational to the recent advancements in large language models (LLMs). In this article, we will attempt to unravel some of its inner workings and hopefully gain some insight into how these models function. The only prerequisite for following along with this article is a basic understanding of