Research

At AI Safety Hong Kong, we conduct and publish original research and writings that engage critically with both international discourse and local realities. Our goal is to bridge the gap between Hong Kong's current understanding of AI safety and the most pressing issues on the global frontier.

From technical alignment challenges to governance frameworks and risk assessments tailored to our region's unique context, our work brings cutting-edge debates home. We translate, synthesize, and contribute, ensuring that Hong Kong's researchers, policymakers, and practitioners are not bystanders but active participants in shaping safe AI development.

​

We are recruiting researchers to join our co-founding team. If you have expertise in AI alignment, AI governance, existential risk, or related fields, and you want to help build Hong Kong's first dedicated AI safety research capacity—reach out. Help us ask the hard questions, produce rigorous work, and make Hong Kong a node in the global safety network.