Our mission is to get academics, students and professionals in Japan thinking about and working in AI safety, whether through technical alignment research, developing good policies for AI governance, or otherwise. Our central activity is a weekly seminar series / reading group / 勉強会, keeping our attendees’ fingers on the pulse of the AI safety literature.

AI Safety 東京 works alongside other groups like AI Alignment Network and Effective Altruism Japan to create a world where AI is safe, robust, and aligned by default.

AI Safety 東京 was founded in January 2023 and is headquartered in Shibuya.