Comment on Claude will apply invisible watermarks to AI text and images
floofloof@lemmy.ca 20 hours agoYou can’t enforce that with text though, because people will just delete the words. They use a subtle statistical signal because people can’t just spot it and delete it. Unfortunately it raises a problem: either they have to make the signal a secret, in which case only Anthropic and those contracted to keep the secret could detect it, or it’s not, in which case people can use a detector and some other AI to discover how to eliminate the signal. I expect Anthropic would try to keep control over the detection secrets and provide a detection API for third-party software to use.
Ek-Hou-Van-Braai@piefed.social 20 hours ago
Unless you’re using AI to write books, I can’t imagine how you’d implement some secret watermark
floofloof@lemmy.ca 19 hours ago
As I understand it, you need a good length of output to be able to detect the watermark, because only then can you see the statistical effect with confidence. There are usually various options in code for how you get something done, and they could watermark generated code by adding a distinctive pattern to its preferences for certain constructs over others. But it would have to be subtle, so you’d need a large enough sample of its output before you could see the effect.
Ek-Hou-Van-Braai@piefed.social 19 hours ago
It should be fairly easy to stop this detention even in code.
You just need to set very strict “rules” the AI must follow when writing code.
Variable and method names etc. Must follow a specific formula.
Have a different AI write your docs etc.
If you’re just vibe coding everything, the watermark would work. So maybe a good thing. But it’ll be whack a mole, and if you’re careful I’m sure you can stop the detection