About

I'm Perucy Mussiba. A human thinking seriously about artificial intelligence, safety, and what it means to build systems that are actually good.

I work on projects at the intersection of AI and real-world problems. This blog is where I think out loud about alignment, interpretability, and the bigger questions around where AI is headed.

I'm not an academic researcher at the moment, and I don't write like one. I'm an engineer who takes these ideas seriously and wants to engage with them honestly.

You can find me on GitHub or LinkedIn.