Some insights from my friend Stefano on alignment.

"Alignment is defined as reducing the misalignment between the value system of the LLM and the value system of who pays to make it / keep it running.

Either there is a single absolute value system, a sort of platonic eigenvector of goodness, or, there isn't.

If there isn't, then alignment for me is propaganda for you.

ust looking at the history of political parties and newspaper editorial rooms in history it suggests that "eigenvector alignment" is a non-starter.

So we're left with just another "what's good for me is evil for you", as predicted."