Integrity for consequentialists
Paul Christiano
22

So, since a reputation for trustworthiness/integrity has value, it seems that there are a few options:

  1. Figure out how to incorporate that value into a consequentialist decision-making framework.
  2. Just act with integrity. (Your suggestion, I believe.)
  3. Look into Virtue Ethics.

I think you make a good case for a person doing #2. But that’s probably not very clear for an A.I. agent. I discuss how #3 could relate to A.I. agents:

https://arxiv.org/abs/1701.02388

Like what you read? Give Gabriel Murray a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.