PyCon Lithuania 2026

What if you could watch an AI’s thought take shape? For years, LLMs have been impenetrable "black boxes," but we are finally beginning to find ways to see how the ghost in the machine actually works.

This talk explores mechanistic interpretability, a subfield of AI that aims to understand the internal workings of neural networks. Mapping these internal "circuits" is not only just a philosophical curiosity - or duty: it is a high-stakes engineering necessity for safety, debugging, and trust.

With o1, OpenAI ushered a new era: LLMs with reasoning capabilities. This new breed of models broadened the concept of scaling laws, shifting focus from train-time to inference-time compute. But how do these models work? What do we think their architectures look like, and what data do we use to train them? And finally - and perhaps more importantly: how expensive can they get, and what can we use them for?