Right now I’m interested in and working on:

  • MATS 9 and MATS 9 extension with Alex Turner (GDM) and Alex Cloud (Anthropic), working on methods to detect deceptively misaligned AI.

  • ListenToAnything.com, a service that lets you convert any webpage/PDF into a podcast episode, so you can listen to your reading list and actually close some of those open tabs. I discuss the goals behind it in more detail here.

  • Writing essays about expertise, how AI will impact the economy, and the nature of competition.

  • Public speaking and talks about AI safety and the economic impact of white-collar job automation.

  • Independent AI Safety Research

Please reach out! I’m interested in talking with interesting people, even if you don’t know exactly what to talk about.