53
Claude will apply invisible watermarks to AI text and images (www.theverge.com)
submitted 2 weeks ago by [M] to c/technology@lemmy.zip
17 comments fedilink hide all child comments
 

The EU’s AI rules are having an impact.

Archived version: https://archive.is/20260811122405/https://www.theverge.com/ai-artificial-intelligence/977823/anthropic-claude-ai-watermarks-c2pa-text-images

you are viewing a single comment's thread
view the rest of the comments
[–] 12 points 2 weeks ago (1 child)

You 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.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 5 points 2 weeks ago (1 child)

    Unless you're using AI to write books, I can't imagine how you'd implement some secret watermark

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 3 points 2 weeks ago* (1 child)

    As I understand it, you're right that 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. And in code there are usually various options 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 again, it would have to be subtle, so you'd need a large enough sample of its output before you could see the effect.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 2 points 2 weeks 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

  • permalink
  • fedilink
  • source
  • parent