Short overview of me:
I am currently doing my PhD in Machine Learning under the supervision of Philipp Hennig at the University of Tuebingen. I'm excited about what ML can achieve but want to ensure that it is done in a safe and aligned manner. I consider myself an Effective Altruist. I do/did university debating. I want to work on AI safety in the future and already do it a bit on the side.
In my PhD I work on making Bayesian ML faster and more scalable. For the remainder of my PhD, I intend to work on combining Deep Learning and Probabilistic Graphical Models because I think it could be relevant for interpretability and alignment.
In my freetime I think and write about Effective Altruism and AI safety. I sometimes go cycling.
If you want to know more about my personality, my posts on opinions I changed (part I, part II, part III) or Effective Altruism would be a good start. For an overview of my career you can look at my ‘CV’.
Machine Learning Projects:
In the ML projects section I explain papers I have written, projects I have completed and find worth talking about, and essays regarding the topic of Machine Learning in general. For a more detailed overview of the purpose of that part of the blog see my 'What is the ML Projects part about' article.
In the Opinions section I mainly post essays and opinion pieces on ethics and policy that I think are useful to share. For a more detailed overview of the purpose of this part of the blog see my ‘What is the Opinions part about’ article.
One last note:
If you have any feedback regarding anything (i.e. layout, code or opinions) please tell me in a constructive manner via your prefered means of communication.