Yixiong Hao

Co-Director of the AI Safety Initiative at Georgia Tech, overseeing the group’s funding and strategy and conducting technical AI safety research on representation engineering, applied interpretability, and agentic misalignment.

No endorsements yet.

Personal Website

https://yixiong.dev/

LinkedIn

-

Twitter / X

-

LessWrong

yix

EA Forum

-

No grants recorded.