I am curious as to why the post was downvoted. I would appreciate an explanation so I can improve my writing moving forward. I aim to arrive at helping in solving the alignment problem. Thank you.
I downvoted the post because the demand for aligning it with humanity is fundamentally incoherent and a fake option, and you can’t do this because abstractions like humanity or society don’t exist, so aligning it to a specific human’s intention is better, as this can actually be done.
I understand your 2nd point, but to comment on your 1st comment—is having the simpler question always the right thing to focus on? isn’t searching for the right questions to ponder the best way to arrive at the best solutions?
Subpar questions lead to incomplete /wrong answers. If it happens to be that we wrongly framed the alignment problem, the cost of this is huge or even catastrophic. It’s still cheaper to question even the best ideas now rather than change directions or correct errors later.
Hello Moderators/Readers,
I am curious as to why the post was downvoted. I would appreciate an explanation so I can improve my writing moving forward. I aim to arrive at helping in solving the alignment problem. Thank you.
I downvoted the post because the demand for aligning it with humanity is fundamentally incoherent and a fake option, and you can’t do this because abstractions like humanity or society don’t exist, so aligning it to a specific human’s intention is better, as this can actually be done.
Alignment with humanity isn’t a simpler problem than alignment with a subset of humanity.
Alignment with human values in general is what a lot of people already mean by alignment, so lack of originality.
Thank you for your response.
I understand your 2nd point, but to comment on your 1st comment—is having the simpler question always the right thing to focus on? isn’t searching for the right questions to ponder the best way to arrive at the best solutions?
It depends on whether you’re being academic or practical.
Subpar questions lead to incomplete /wrong answers. If it happens to be that we wrongly framed the alignment problem, the cost of this is huge or even catastrophic. It’s still cheaper to question even the best ideas now rather than change directions or correct errors later.
Again, you are not suggesting something new , you are suggesting a standard answer which no one has the faintest idea how to implement.
I’m in the process of writing it. Will link it here once finished. Thanks for being more direct too.