Possible End of Humanity from AI? Geoffrey Hinton at MIT Technology Review's EmTech Digital

To understand how to prompt an autoregressive language model, we must first consider the context in which it was trained and the function it approximates.

In this study we introduce a semiparametric hazard-based duration model to predict the timing and sequence of theme park visitors’ activity choice behavior. The model is estimated on the basis of observations of consumer choices in various hypothetical theme parks. These parks are constructed by varying the absence and presence of existing and new activities within a theme park as well as their attributes: waiting time, activity duration, and location.

Fernando Flores worked out this understanding of conversations for action.