Michael Bright comments on What will happen when an all-reaching AGI starts attempting to fix human character flaws?

[Michael Bright]

If one believes the orthogonality thesis

Yes, I do.

I would expect an AGI to be more on the far-reaching/​utilitarian end of affecting our lives.

Me too.

But I’m adopting the term “AGI-humans” from today.

But of course a utilitarian-leaning AGI will be more willing to risk actively doing harm if it thinks that the total expected outcome is improved.

...