Anthropic is working on a watermark for Claude-generated text that could follow the text even after you copy, paste, or edit it 👀
They haven’t revealed exactly how this watermark works yet, but one way could be by creating a statistical pattern in Claude’s word choices that humans can’t see, but a detector potentially could.
And the implications of this have taken the internet by storm.
People are wondering what happens if Claude only edits something that you originally wrote? Does that now get flagged as AI-generated? What about code, copyright, privacy, or people simply rewriting the text enough to remove the watermark entirely?
And then there’s the bigger debate: Do people have a right to know when something was created with AI?
Curious where you land on this one. Let me know in the comments 👇
And follow for more AI news and updates.
#AI #ainews #anthropic #claude
source
