Suppose you have a transformer that handles tokens of dimension Dmodel.D_{model}. And suppose it has ten tokens in the input. The residual stream that’s updated
Suppose you have a transformer that handles tokens of dimension Dmodel.D_{model}. And suppose it has ten tokens in the input. The residual stream that’s updated
I just re-read Max Weber’s essay “Science as a Vocation” in the context of thinking about human and machine intelligence alignment. In particular, I’m thinking
Before and after pictures have always fascinated me. An empty lot and a finished house. A bag of Lego bricks and a finished tower. When
I’m working on a course in which we will examine in parallel solutions to problems of human intelligence alignment (how do we get people to
This is the first in a series of essays in which I try to think through the question of what assumptions social institutions make about
What if we took the production of technologically literate humanists and humanistically enlightened engineers seriously? Just a Thought One month before I was born, C.P.