Published 2017-06-30 by Johannes Heidecke
On this blog I share some of my thoughts about artificial intelligence from a variety of different perspectives. Main focus of many posts here will be the existential risk that AI will potentially pose one day for humanity.
Future blog posts will provide a more detailed overview of the control problem and AI safety and shed some light on its philosophical and theoretical arguments, current initiatives against it and potential solutions.
In order to work towards safe AI, I believe that it is important to develop a thorough understanding of current state of the art methods in AI and machine learning, as well as keeping track of the many connected research areas such as (computational) neuroscience, philosophy of mind, game theory, etc.
I am currently a graduate student pursuing a master's degree in artificial intelligence and many of my posts will be about interesting topics and concepts that I came across in my studies and that I think are important to understand actual and future AI systems and how we could potentially control them.
Subscribe to Newsletter
Subscribe here to automatically receive new posts on thinking wires via email:
Back to main page