Why I write this blog

When I started studying Data Science and AI, I was almost entirely interested in the application of AI in other domains of science such as biology or environmental science. I had never really programmed before and did not see myself as a computer scientist. However, having some knowledge about AI seemed promising in these times and liking STEM subjects more than social science, I decided to give it a try.

Over the past year and as I progressed in my studies, my interest shifted more and more towards AI itself. While I started to understand what is going on in the field, I became aware of how little education there is about AI given how much it is already used in everyday life and the risks and problems it may have. AI is incredibly complex and powerful, and will likely transform society profoundly while posing risks that may even be existential. For these reasons, I believe that everyone should have at least a basic understanding of what AI is, the challenges it brings, and possible solutions.

After many conversations with friends, family, and colleagues over the past few weeks, I decided to create this blog as a space to make discussions about AI safety accessible and easy to understand. At the same time, I see this as an opportunity to document my personal journey into the field of AI safety and to share what I learn along the way.

I plan to begin this blog by introducing the concept of AI safety—exploring why it matters and what it entails. From there, I will dive into different approaches to solving the challenges, addressing both technical and governance aspects. I look forward to sharing this journey with you and hope that you learn as much as I from these posts!