Alignment problems
Whose values are they anyway?
There’s another big problem with AI alignment that we haven’t considered yet…
How can we get AI to align with human interests, when humans can’t make their interests and ethics align with each others’?
Consider, for example, the differing priorities of Boomers and Zoomers, or between Reformers and supporters of the Green Party.
What about people from different countries, continents, religions…
Do Silicon Valley billionaires share the same values with broader society? Are they the best people to be deciding what our future looks like?