Hi! I’m Kai, and this is my blog. I’m interested in the intersection of artificial intelligence and classical cybersecurity.

More specifically: Can we use LLMs for anything useful safely? To this end, I (used to) do independent research, the results of which are published here. Not sure about the content going forward.

I currently work on AI security at NVIDIA.

My work has been featured by Bruce Schneier, Vice, Wired, ZEIT Online (de), MIT Technology Review, The Hill and Heise (de) among others.

About the website

Powered by Hugo, a modified gruvbox theme and a lot of custom CSS inspired by Tufte.css.