When Jan Leike (OAI’s head of alignment) appeared on the AXRP podcast, the host asked how they plan on aligning the automated alignment researcher. Jan didn’t appear to understand the question (which had been the first to occur to me). That doesn’t inspire confidence.
When Jan Leike (OAI’s head of alignment) appeared on the AXRP podcast, the host asked how they plan on aligning the automated alignment researcher. Jan didn’t appear to understand the question (which had been the first to occur to me). That doesn’t inspire confidence.