No, this would be literally you (the user) checking "this is AI generated" before you post something publicly. Platforms can auto mark it if they detect a watermark like SynthID but they can also leave the choice up to you.

The point is making it easier to go after bot accounts that spam generated videos to influence politics. They need to disclose that its AI and lose their power or lie and get criminally prosecuted.

It's not the same thing as model providers adding a mandatory watermark to everything, and even worse one you can't verify yourself and have to trust that Anthropic is telling everyone the truth. People should have the option to use undetectable AI tools in private, even if it's illegal to post the outputs on social media.