What do we know about how to make good predictions?: Neyman Seminar
Seminar | September 11 | 4-5 p.m. | 1011 Evans Hall
Danny Hernandez, OpenAI
Everyone makes bets. Scientists bet years of their lives on research agendas, CEOs bet billions of dollars on new products, and world leaders bet our welfare through their policies. Their decisions often hinge on implicit judgement based predictions about relatively one-off events rather than on data. Well review the most promising existing techniques for improving ones predictions. Ill discuss my experience applying what is known to improve performance in this domain at OpenAI and Twitch (a subsidiary of Amazon). Ill end with some of the open questions and opportunities in the space I see as most interesting.
Berkeley, CA 94720, 5106422781