Stefano Fiorucci

What if, instead of learning only from examples, Language Models could explore crafted Environments, little worlds where they can act and improve autonomously? Join me to see how Reinforcement Learning Environments work, how to build them, and how to use them to evaluate and train LLMs/Agents.

It's 2025, AI is still a hot topic and everyone's talking about Agents. Cool stuff, but join me for a dive on Post-Training. I'll share my journey of picking a small open model, customizing it for my needs and running it in my cheap smartphone. Joys, frustrations and lots of learning!

LLMs are an exciting and complex technology. Cut through the hype and learn how to build with them in this talk! Join me for an exploration using Python open-source tools. The examples will cover using different models, prompting, vector databases, RAG, and more.

“Allan Williams was the manager of the Beatles” True or false? Let AI ​​answer! In this talk, we’ll discover how to build a simple fact-checking system for rock music. We will leverage the power of various Python open-source libraries, including Haystack, FAISS, Hugging Face Transformers...

Have you always dreamed of providing knowledge to a computer so that it can answer your questions? It is finally possible and easy to do this, using python and the Haystack library. I'll explain how to quickly implement a Question Answering system, starting from docs about your favorite TV series.