I care about building useful systems that help people and are safe. I like to understand how convoluted programs work and decipher what is going on inside. I'm also a tinkerer and love starting random code-based projects or other exciting ventures where I can learn new things and do something useful with my time.I do research in ML interpretability, capabilities, and ethics. In the past I've worked on advanced materials, numerical methods and sustainable architecture.You can read some of my public research work here: https://scholar.google.com/citations?user=1jpQzAYAAAAJ&hl=en&oi=aoSome of my other interests include (but not limited to) metascience, human psychology, history, cooking and endurance running.(LinkedIn is another social media app, I do not need to be looking for a job and you do not need to be offering one, feel free to send a message! Bonus points for taking the time to screenshot my header image and asking gpt about it.)