1. LLM Fundamentals, from the Next Token to Tools
How does an LLM work? Follow learned parameters, tokens, embeddings, and the Transformer to understand text generation, reasoning, and tool calling.
The world is changing faster than ever.
Since November 2022, AI has become increasingly present in our work. Today, we have reached a point where we have to reimagine everything from the ground up to take advantage of it. We're talking about more than automating a few tasks here and there. We're talking about revamping all our workflows from scratch. For example, developers use agents to write and review code, mathematicians explore proofs with AI, and researchers use it to analyze data.
Our society needs to be reimagined, and there is a vast amount of work to be done. That's really exciting, as we have an opportunity to build the future.
But there's a gap. To shape the future, you have to know how to use these tools and where they can help. That's what I want to address with this series.
How does an LLM work? Follow learned parameters, tokens, embeddings, and the Transformer to understand text generation, reasoning, and tool calling.
Follow a GitHub issue from tool calling to MCP. Learn how applications discover tools, share resources and prompts, and connect with MCP.
While I already have some topics in mind, I would love to know what you want me to cover. The topics don't have to be technical, as I want this series to be accessible to everyone, from beginners to advanced users. I'll adapt my schedule to your requests.
You can also vote for the existing topics you want me to cover. You can vote for several topics, once per topic, and remove your votes at any time while a topic is open.
Loading topics...
New articles, practical web development tips, and updates on my open source projects. Straight to your inbox.