Advanced Reading Group

We read and discuss important papers in AI Alignment and related research. We also host talks from alignment researchers from time to time. We assume general AI Safety knowledge, but prior participation in an Intro to AI Alignment seminar is not necessary. 

Each week, we will decide on a paper to read from this list (!) Consider putting a public Google Sheet here, or as seen below. We will meet for approximately 1.5 hours per week, around 45 mins individual reading and the rest for discussion, although this may vary depending on the difficulty of the material. Propose papers to read here! (!) Insert hyperlink to Google Form or other suggestion method


<<APPLY HERE>> (!) Insert hyperlink by Friday December 15th 11:59PM



Featured papers: