I agree with your sketch of the alignment problem.
But once you move past the sketch stage the solutions depend heavily on the structure of A, which is why I questioned Rob’s dismissal of the now-dominant non-MIRI safety approaches (which are naturally more connectivist/DL friendly).
I agree with your sketch of the alignment problem.
But once you move past the sketch stage the solutions depend heavily on the structure of A, which is why I questioned Rob’s dismissal of the now-dominant non-MIRI safety approaches (which are naturally more connectivist/DL friendly).