Among the causes that Effective Altruists support, existential risk stands out as different from ordinary charitable concerns, and existential risk from Artificial Intelligence even more so.
In this talk, which assumes no prior knowledge in artificial intelligence, Vanessa Kosoy will explain the problem in question, and how researchers in the field are trying to solve it. Vanessa is a Research Associate with the Machine Intelligence Research Institute (MIRI) studying the mathematical formalization of general intelligence and value alignment.
The talk is brought to you by Effective Altruism Israel and LessWrong Israel.