Instrumental Convergence

Both Bostrom and Omohundro argue these values should be used in trying to predict a superintelligence's behavior, since they are likely to be the only set of values shared by most superintelligences. They also note that these values are consistent with safe and beneficial AIs as well as unsafe ones. Omohundro says:

In the 'Relevance' section there's a sentence that begins "Omohundro says:" but then there's no text, so I have no idea what Omohundro says.

2jimrandomh7moI thought this might be an editing artifact, but it looks like that fragment was there and dangling that way in the revision where it was first inserted, so I just took it out.