In my biased opinion, my AI safety course has been going very well. Students are great, and I have been learning a lot from the guest speakers. We've had students write scribe notes, and when guest speakers are OK with it, I've also been posting videos of lectures. Each week, students have been doing an experiment related to the topic, some of these are really great and I hope will evolve into papers! See the course webpage for experiments, as well as for links to the readings for each lecture.

(As will be pretty easy to see, I've been maintaining the webpage with chatgpt, so there is some slopolisms in it.)

Here are the current lectures (including planned future ones), with scribe notes and videos when they are available.

1. September 3, Introduction, Boaz Barak. Scribe notes · Video
2. September 10, Cyber Capabilities, Nicholas Carlini. Scribe notes
3. September 17, Modern LLM Training and Inference, Boaz Barak. Scribe notes · Video
4. September 24, Recursive Self-Improvement and AI Trajectories, Dwarkesh Patel and Daniel Kokotajlo. Scribe notes
5. October 1, Economic Impact of AI, Chad Jones and Erik Brynjolfsson. Scribe notes · Video
6. October 8, Grading, Reward Hacking, and Alignment, John Schulman. Scribe notes
7. October 15, Model Policies, Ziad Reslan.
8. October 22, Q&A with Sam Altman; Open-Source Models by Nathan Lambert. Video—Nathan Lambert and student experiment only
9. October 29, Frontier AI Regulation Under Uncertainty, Helen Toner. Specs and constitutions, Boaz Barak.
10. November 5, AI Interpretability by Jack Lindsey, Model Welfare by Jeff Sebo. Video—Jeff Sebo only
11. November 12, AI emerging risks, Jakub Pachocki.
12. November 19, AI Biosecurity and Threat Modeling, Luca Righetti, AI policy Brad Carson.
13. December 3, Titles TBD, Ajeya Cotra , Roy Rinberg.