When Should the Fire Alarm Go Off: A model for optimal thresholds
In this post I consider a model where there is a possible bad outcome, and the chance of it happening is related to something we can measure. We need to… Read more »
In this post I consider a model where there is a possible bad outcome, and the chance of it happening is related to something we can measure. We need to… Read more »
I read Andrew Critch and David Krueger’s AI Research Considerations for Human Existential Safety (ARCHES) recently, which is a report that outlines and discusses 29 research directions which might be… Read more »
I like clothing with birds on it. I also like birds, as well as other animals. I have previously said that I like bird clothing, more than I like bird… Read more »
The other day I saw one of the ways in which things are tragically broken. Broken in such a way that it seems better to sacrifice maybe the most important thing, because the alternative is currently worse.