My most cynical take: keeping the feel-good image of Anthropic is a temporary ploy to keep fickle SV tech workers building the technology.

When OpenAI started to move obviously towards commercial and governmental ties, a lot of people left. Those people were necessary to build the tech. Many landed at Anthropic, a company that still attracts the most ideologically strict and capable ML researchers.

But at some point of their choosing, the powers that be will just take it.