AI Safety Bergen is a student organization dedicated to advancing research and initiatives in AI safety. We bring together individuals passionate about ensuring the safe and ethical development of artificial intelligence. We host weekly meetups where members collaborate on technical AI safety research (particularly mechanistic interpretability), explore AI governance challenges, and engage in policy discussions. We also organize educational courses and community outreach events to raise awareness about AI safety in the Bergen community. Join us to learn, collaborate, and contribute to meaningful AI safety efforts.
We're excited to announce our AI Safety Fundamentals course! This is a 7-week program (shortened version of the BlueDot AI Safety Fundamentals course) where participants meet once per week in small discussion groups of 6 people, led by a facilitator. You'll be expected to spend 1-2 hours studying the provided materials before each session.
Focus on technological approaches to ensure AI safety. The curriculum covers key concepts in AI alignment and is available for preview at AI Safety Fundamentals - Alignment.
Explore legal and political interventions for safe AI development and deployment. Preview the curriculum at AI Safety Fundamentals - Governance.
Join our Discord community to engage with fellow members, stay updated on the latest AI safety discussions, and participate in exclusive events.
Join our DiscordWe meet every Tuesday from 16:15 to 18:30 at Aktivt rom 3 - Marineholmen
Our weekly meetings are open to everyone interested in AI safety. We typically spend time working on technical AI safety research projects, discussing recent developments in AI, and planning community initiatives. Whether you're new to AI safety or already involved in the field, you're welcome to join us for collaborative work and discussions!