About

👋 I am a software engineer focusing on correctness of code (testing, verification, program synthesis, keeping coding agents in check). I did my PhD work at the intersection of formal methods and artificial intelligence. Currently, I am collaborating with Beneficial AI Foundation on making AI systems safe.

In this blog I write about interesting computer science topics that I come across in my work or in the work of others. My default topics will be formal methods (and software correctness/security in general), artificial intelligence, and distributed systems.

This blog is using the Ephesus theme by Hakan, with some modifications introduced by danwt.