Alejandro Tlaie Boria

Hi there, e-visitor and welcome to my online corner! I have recently started putting some of my thoughts into words (see here).

As you'll notice, a lot of things interest me. Thus, I have put together two short CVs :

a more governance-focused one
a more technical one.

You'll see that, content-wise, this site hosts a wide range of topics (check out my projects, dataviz or writings to know more!): that's because believe in a holistic approach to knowledge (and, of course, because I am interested in a lot of things!).

Before my current endeavor to make Artificial Intelligence safer, I worked in computational and behavioral neuroscience, information theory, complex systems/networks, and even string theory. Along the way, I wrote a MPhil Thesis on Ethics & LLMs (see here if interested) and I have done a bunch of other things related to creating safer AI: studying how to extend the interpretability toolkit to non-Transformer-based architectures, steering SAE representations, or writing about a blueprint for the EU to establish an ecosystem of external auditors for frontier AI models.