You are viewing a single comment's thread:
RE: AI Act: Anthropic first LLM to add invisible watermarks in AI-generated text, not just in images, by manipulating the token probabilities. First tool emerging to remove the watermarks again.
I don't know what to think of it. It's good that we can detect it, but at the same time, it just means that the results aren't the best.
0.01483782 BEE
0 comments