LLMs changed the way I do software development. Depending on who you ask, admitting that I haven’t hand-coded a feature since the beginning of the year may or may not be a good thing. Regardless of where you fall on the “AI morality” spectrum, one thing is hard to deny: software development has evolved significantly over the past year. With it came agentic skills frameworks like Superpowers that enable agents to code software end-to-end. As a developer myself, why not try to reinvent the wheel and make your own framework? Enter Kantan Dev.

Kidding aside, I enjoyed working with skill-based frameworks like Superpowers. It consistently produced higher-quality results than simply prompting an LLM to generate code. Alas, no tool is all upside, and I noticed a few drawbacks: Continue Reading

We have installed a local LLM in our laptop and used it as a chat bot, and tried coding with it as well. All’s well and good, right? Well, not really. Our local LLM still lacks a fundamental ability: tool calls.

You see, when we downloaded the LLM from HuggingFace and installed it, it comes with just its own set of training data. Meaning the information it has is limited only to the data it was trained on. This isn’t very helpful to us if we want to get up to date information, for example, today’s top entries in Hacker News. The LLM needs to access the internet to get that information, and by its own, it won’t be able to do that. Continue Reading

In Running LLMs in Intel Laptops we installed and ran an LLM in a laptop and use it as as your personal chatbot. Let’s push this further by using the LLM to help us write code by connecting our IDE (Integrated Development Environment) to the model.

In the previous article we installed the Qwen 2.5 7B Instruct model, although for our IDE use case we will be using another variant of the Qwen model called Coder. It is important to understand that a model can have several variants that is more suited for a specific task. For instance: Continue Reading

AI (especially LLMs) are taking over the world right now. The pace of progress has been especially dizzying this year, with every month producing a new breakthrough in the technology (e.g Opus 4.6, OpenClaw). As with all technologies, it is also important to have a grasp of the basics. And what better way to learn the basics than trying to run an LLM in your computer!

We are all familiar with the popular AI tools (LLMs) like ChatGPT and Claude. These services are running on what is called frontier models, which are the best models that is available in the market right now. But these models are usually paid, either per token or through a usage quota. If you want have a “free” LLM, then you have to run your own model using your machine. For this, we need to use open source (or more accurately open weight) models. Fortunately, we have a wide selection of models: Continue Reading