Jacob Steinhardt

Machine learning is touching increasingly many aspects of our society, and its effect will only continue to grow. Given this, I and many others care about risks from future ML systems and how

The previous post started forecasting the UK hospital peak (based on information through Dec. 21, 2021). We generated several considerations and ultimately focused on the Omicron doubling time, the peak number of cases,

So far, we've focused on individual skills involved in a forecast: extrapolating trends [https://bounded-regret.ghost.io/forecasting-zeroth-and-first-order/], employing reference classes [https://bounded-regret.ghost.io/base-rates-and-reference-classes/], how to combine estimates [https:

For this post, I commissioned Misha Yagudin, a top-ranked forecaster, to provide feedback and commentary. I include selected comments as quotes throughout. For open-ended questions, it's easy to underestimate the number

Often there are multiple ways to forecast the same thing, and we'd like a way of combining the forecasts together. For instance, consider the following question: > Will Will be among