AI Safety × Philosophy: 8-week reading group launches
LessWrong is organizing an 8-week reading group pairing technical AI safety work with philosophy. The premise: technical excellence alone fails if the philosophical assumptions underneath it are flawed.
• Topics: consciousness, agency, alignment, power, metaethics
• Mix of papers, essays, book chapters, and video
• Guest talks from leading researchers and professors
• 100+ applications received in days — open to facilitators too