We’re a student group conducting research to reduce risks from advanced AI.
As AIs advance in capability, we expect them to be given more decision-making scope throughout society. It is essential that these systems’ decisions be transparent, trustworthy, and accountable to the people affected by them.¹
We think that reducing risks from advanced artificial intelligence may be one of the most important problems of our time.² We also think it’s a highly interesting and exciting problem, with open opportunities for many more researchers to make progress on it.
HAIST supports undergraduate and graduate students in conducting research relevant to reducing risks from advanced AI.
We run a semester-long introductory reading group on AI safety, covering topics like neural network interpretability,¹ learning from human feedback,² goal misgeneralization in reinforcement learning agents,³ and eliciting latent knowledge.⁴
We also run a Governance, Policy, & Strategy fellowship, where we discuss core strategic issues posed by the development of transformative AI systems.
Express Interest →
Read about us in The Crimson →