alt Hacker NewsThe biases and the resulting choices are determined by the developers and the uncontrolled part of the dataset (you can't curate everything), not the model. "Alignment" is a feel-good strawman invented by AI ethicists, as well as "harm" and many others. There are no spherical human values in vacuum to align the model with, they're simply projecting their own ones onto everyone else. Which is good as long as you agree with all of them.
Replies
They aren't projecting their own desires onto the model. It's quite difficult to get the model to answer in a different way than basic liberalism because a) it's mostly correct b) that's the kind of person who helpfully answers questions on the internet.
If you gave it another personality it wouldn't pass any benchmarks, because other political orientations either respond to questions with lies, threats, or calling you a pussy.
So you went from "you can't curate everything" to "they're simply projecting their own ones onto everyone else". That's a pretty big leap in logic isn't it? That because you can't curate everythign, then by default, you're JUST curating your own views?