If they will be useful to you, you are welcome to use these talks. If you do, I’d appreciate:

  1. Before, please let me know that you’re going to use the slides and where (via email or contact me via jamiebernardi.com)
  2. During, please mention that you are using my slides
  3. Afterwards, let me know if you have any feedback, whether you changed anything, and how your audience responded. It’d be great to adapt the talks to your audience.

Problem overview: Intro to AI Safety - why worry?

link to slides

Abstract:

What is AI Safety, and why should we care? In this talk, I’ll introduce the arguments behind AI being a potential source of existential risk in the next century and beyond.

(It doesn’t really talk about potential solutions very much - that is in the next talk.)

Solution space: Alignment field overview

[link to slides]

Abstract:

Who is doing what work to reduce existential risk from advanced AI? In this talk, Jamie answers questions like where can you go, and what can you do, to help to reduce this risk with your own career?