Other interests

Outside of my research I follow work on AI alignment, the problem of ensuring that increasingly capable AI systems reliably pursue what their designers and society actually intend. I think it is both crucial and badly under-attended, and that mathematicians have more to contribute to it than is usually assumed.

I intend to expand this into a proper account of what I find interesting here, and why, together with pointers for anyone who wants to read into the subject. That is still to be written.

In the meantime, if you would like to talk about any of this, in Regensburg or at a conference, do get in touch.