Michael Vaiana

AI safety researcher and neuroscientist who serves as Director of Research at the Flourishing Future Foundation and as a research director / principal researcher in AI safety at AE Studio, with prior academic work on multilayer brain networks and recent papers on language-model deception, self-modeling, and self–other overlap for honest AI systems.

Personal Website

https://github.com/vaiana

Organizations

Flourishing Future Foundation

Director of Research

No grants recorded.