Essays on research, AI, and life
I’m Thomas Jiralerspong, an AI safety and mechanistic interpretability researcher. This is where I share essays about research, building with AI, and life as a researcher.
Subscribe to get new essays by email. You can also read them here on the web.
New here?
Visit Start here for three essays to begin with, or browse the archive.
Research and other work
My personal website has my research, projects, and mentorship work. Earlier website versions of my essays remain in the blog archive.
