Artificial Intelligence (AI) systems are rapidly becoming more powerful and deeply ingrained into the fabric of society. AI alignment deals with the problem of building powerful AI systems that adhere to their intended goals and are "helpful, harmless and honest".
Our goal is to provide a network for professionals working on AI alignment in Vienna and Austria, and to strengthen the global visibility of Vienna among global AI stakeholders.
- Matthias Samwald, Associate Professor, Institute of Artificial Intelligence, Medical University of Vienna
- Jason Hoelscher-Obermaier, Research Lead Apart Research
- Michael Pieler, DL researcher
- Sebastian De Ro, Co-founder & CTO @ Magic
- Egor Zverzev, ISTA / Institute of Science and Technology Austria
- Attila Kaplan
- Mihai Truta
- Contact for inquiries: matthias.samwald (at) meduniwien.ac.at
- We use the
#λ-vienna
channel on the AI alignment slack for discussion and coordination. To join the discussion, please:- join the AI alignment slack
- inside the AI alignment slack, find and join the
#λ-vienna
channel
To connect with the wider European AI alignment community
- join the
#λ-europe
channel on the AI alignment slack - check the homepage of the European Network for AI Safety