Most alignment methods nowadays don't rely on interpretability. And neither do all LLM vendors care about alignment much - especially not in China.
Those things being untrainable at scale is why they aren't around. Alignment is an afterthought.
Most alignment methods nowadays don't rely on interpretability. And neither do all LLM vendors care about alignment much - especially not in China.
Those things being untrainable at scale is why they aren't around. Alignment is an afterthought.
China should care: https://www.forbes.com/sites/boazsobrado/2026/03/11/alibabas...
As is, Chinese labs spend more effort on "rhetorical alignment to the party line" than alignment of any other kind.