Federico Torrielli
I am a Ph.D. candidate in Generative Artificial Intelligence at the University of Torino, specializing in AI Safety, LLM Alignment, and Human-AI Interaction. My work bridges technical development with interdisciplinary analysis to mitigate risks from general-purpose AI systems. In my free time, I also write on LessWrong, AI Alignment Forum, and Substack under a pseudonym. Holistic AI views are in my blog.