191
‘New models will mark AI-generated content from day one’: Claude will now hide an invisible watermark inside ordinary words (www.techradar.com)
submitted 2 months ago by to c/technology@lemmy.world
32 comments fedilink hide all child comments
you are viewing a single comment's thread
view the rest of the comments
[–] 4 points 2 months ago* (8 children)

As I’ve said in response to a number of articles about this, all this means is that when someone wants to use Claude’s output for something, they just need to remember to manually type it in now, rather than just copy-paste it. Practically speaking, this changes nothing.

  • permalink
  • fedilink
  • source
  • hideshow 8 child comments
    •
  • [–] 8 points 2 months ago* (5 children)

    The difference between auto-generating hundreds to thousands of words, versus having to manually read and type all of those words out yourself is very obviously a lot more than "nothing".

    And that's not even taking into account the fact that we don't know what their method of watermarking is. From how they're talking it sounds like it will be algorithmically embedded in the text itself somehow, through specific choices of words or something similar. If that's the case, typing it out word for word will retain the watermark.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 5 child comments
    •
  • [–] 5 points 2 months ago* (4 children)

    How tho? Will Claude be looking over our proverbial shoulders now, and if whatever we type just so happens to be word-for-word what it said, it can magically flag it?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 5 points 2 months ago (2 children)

    You have a fundamental misunderstanding of how the watermarking works. There is no hidden metadata, but most likely, the statistical properties of the generated text are being changed.

    If you met someone on Halloween with a face mask, and they'd always use the word cromulent in every sentence, you'd probably assume it's your buddy Mark, who is about the only guy in your circle of friends who does that.

    The model will produce a text where individual words at certain positions, or various n-grams encode a kind of fingerprint that will be an indicator for the text being processed by Claude.

    Like, when people have, like, a specific accent or talk in a certain way, you can totally, like, figure out where they're from, for sure.

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

    So isn't the solution then to just feed the Claude output through a second tiny LLM with the prompt to slightly rewrite the input? I mean you can probably use a 1b model to do that and that can run on practically anything nowadays

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 3 points 2 months ago

    Yes, if the watermarking works like we all assume, significantly editing the output will likely break the watermark. They say this in their press release, as well as that the text must be a certain length to be watermarked. (Probably as a function of how the watermark works.)

    I don't think this is expected to be 100% foolproof. They certainly don't make that claim; they explicitly say that the lack of a watermark isn't conclusive evidence that the text wasn't generated by their models.

  • permalink
  • fedilink
  • source
  • parent
  • [–] 0 points 2 months ago*

    I don't think you will even need to type yourself. Tools removing the watermark will be available 3-4 days after this hits the market, fully able to be automated. Watermarks are not a solution that will prevent someone who wants to deceive you from doing so - only awareness that everything on the web is sus will.

    Edit: The only alternative is an 100% digitally signature authenticated web, from the web login down to the posting. I am not sure this is a better way because it also means 100% transparency of everything someone does.

  • permalink
  • fedilink
  • source
  • parent