In recent years, the field of Artificial Intelligence has made impressive progress. Machine Learning becomes increasingly relevant in our daily lives and milestones like self-driving cars seem to be on the horizon. Beyond that might lie the possibility of Artificial General Intelligence, which is the explicit mission of organizations like OpenAI or Google DeepMind.
Although we are optimistic that Artificial Intelligence has the potential to solve many of humanities greatest problems, we believe that it is better to be safe than sorry. Luckily, the concrete research questions happen to be really exciting as well!
If you are interested: We will meet every week to discuss literature around aligning AI with human values. The main focus will be on AI Safety, but we will also look at other ethical aspects of Machine Learning such as Fairness, Accountability and Transparency.
Due to the current situation, this will probably be over a platform like Zoom. The exact time is to be determined.