Tim Duffy
@timfduffy
I like utilitarianism, consciousness, AI, EA, space, kindness, liberalism, progressive rock, economics, most people. Substack:
819 Following 1.4K Followers
So, we have a couple reasons to expect to be getting emotional representation related to the assistant response, even under the hypothesis that the pain axis works roughly like Anthropic's emotion concepts do: that is, not picking out a ‘self’ representation but rather a ‘current speaker’ representation.
And I think this is plausible, given the similar experimental design.
Show more
