Remmelt comments on Ten Levels of AI Alignment Difficulty

[Remmelt]

Regarding level 10 ‘impossible’, here is a summary of arguments.

10

Impossible

Alignment of a superintelligent system is impossible in principle.

Alignment is theoretically impossible, incoherent or similar.

[Sammy Martin]

Thanks for this! Will add to the post, was looking for sources on this scenario