this post was submitted on 11 Aug 2026
6 points (87.5% liked)

Technology

87045 readers
3895 users here now

This is a most excellent place for technology news and articles.

Our Rules

  1. Follow the lemmy.world rules.
  2. Only tech related news or articles.
  3. Be excellent to each other!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, this includes using AI responses and summaries. To ask if your bot can be added please contact a mod.
  9. Check for duplicates before posting, duplicates may be removed
  10. Accounts 7 days and younger will have their posts automatically removed.

Approved Bots

founded 3 years ago
MODERATORS
L3s@lemmy.world
enu@lemmy.world
technopagan@lemmy.world
L4s@lemmy.world
L3s@hackingne.ws
6
How Claude marks AI-generated content: (1) watermarks embedded in text, and (2) signed provenance metadata attached to files. (support.claude.com)
submitted 2 hours ago by eicker@lemmy.world to c/technology@lemmy.world
4 comments fedilink hide all child comments
top 4 comments
sorted by: hot top controversial new old
[–] Prox@lemmy.world 1 points 22 minutes ago

1. Embedded watermarks in text

When a supported Claude model generates text, it weaves an imperceptible watermark directly into the text itself. You won’t see it, and it doesn’t change the meaning, quality, or readability of Claude’s response.

Because the watermark is part of the text, it will travel with the text when it’s copied and pasted elsewhere, and may persist through some editing. Watermarking will be applied at the model level, which means it will be present no matter which Claude product or surface the text comes from.

Can someone ELI5 how this would actually work, especially with copying and pasting?

[–] MagicShel@lemmy.zip 4 points 1 hour ago (1 children)

The text version must necessarily constrain the output, which will impact readability and semantic meaning, whatever they say.

[–] Dran_Arcana@lemmy.world 3 points 25 minutes ago* (last edited 22 minutes ago) (1 children)

Not necessarily, there are valid "characters" that are not rendered in most text parsers, or are rendered as whitespace. A great example of this is the byte-order-mark (BOM). You can embed a BOM code in the whitespaces of a text string and it looks exactly the same to a human as one without.

I assume that's what they're talking about here

Here's an example of a steganography encoding technique using this method. https://330k.github.io/misc_tools/unicode_steganography.html

[–] MagicShel@lemmy.zip 1 points 2 minutes ago* (last edited 1 minute ago)

Maybe, if it's created after the text is generated. Keep in mind there really is no white space to an LLM. There's a lot of holes here. If it isn't embedded within the text itself, it is trivially easy to strip such markings. If it is, it at least requires a human to paraphrase.

On the other hand, if that's all it is, it would be easily detectable to disallow AI from editing human-written code while allowing it to revise its own output.