Rethinking AGI Alignment: Goal-Oriented Minds, Metagoals, and the Uncertain Future

To the point

Yampolskiy and Fox warn that future general AIs could rapidly outpace humans and be utterly unlike human minds, so we need new science of mind and alignment ideas to understand and steer them without assuming they’ll protect human welfare.

Artificial General Intelligence and the Human Mental Model
springer.com

Artificial General Intelligence and the Human Mental Model

When the first artificial general intelligences are built, they may improve themselves to far-above-human levels. Speculations about such future entities are already affected by anthropomorphic bias, which leads to erroneous analogies with human minds. In this...