The safety and reliability of the AI systems we build is no longer of theoretical concern. Emmett Shear explores what it takes to design systems capable of learning to align themselves with others, and with our society as a whole. From measuring the amount of care a being has for another or what environment they'd need to learn to care in the first place, can the field find its own alignment around what a good future with AI might look like?"

Get direct access to Emmett Shear in this Q&A discussion. Come early to secure your spot, seating is first come, first served. Bring your questions and join the conversation.