Grace Altree

Hello and welcome!

My name is Grace, and I have created this site to document my journey into AI research, especially in the areas of interpretability and alignment.

My background is in Data Science and Cognitive Science, and in many ways, mechanistic interpretability feels like the field I was searching for in college before it fully existed. I have always been intrigued by the intersection of neuroscience, psychology, and artificial intelligence, so, especially as AI becomes increasingly integrated into society, contributing to safer, more interpretable AI systems feels exciting and deeply meaningful.

I don't claim to be an expert, but hopefully this is an approachable space for newbies like me, and if nothing else, is a way of organizing my learnings and contributing ideas.

Thanks for being here!