Moral Graphs and Human Values

Getting here: Enter the lobby at 100 University Ave (right next to St Andrew subway station), and message Giles Edkins on the meetup app or call him on 647-823-4865 to be let up to room 6H.

When we say we want to align AI to human values, what do we really mean - especially if different people and groups value different things? OpenAI has funded some research which aims to tackle this question head-on, posing some divisive questions and attempting to find more abstract principles that people can agree are fair.

While the research is US-focused, it's promising that researchers are looking at ways to find values that people can agree on and instill those values into an AI model. This presentation will take a look at the research, and we'll apply our usual healthy and lively skepticism. Is this the right approach? Is it at least a step in the right direction?

We welcome a variety of backgrounds, opinions and experience levels.