‘New models will mark AI-generated content from day one’: Claude will now hide an invisible watermark inside ordinary words

7 days ago by return2ozma to c/technology

Claude will start watermarking everything it writes
load all comments
PotatoesFall 79 points 7 days ago

The year is 2027. A beginner programmer searches how to access the last array element in a programming language she is unfamiliar with. The results come in. "Top 10 array accesses that will make you want to buy our sponsors product". She sighs and asks Claude instead. She pastes the one-liner into her code. Finishes the remaining code. Tests. Double-check. Commit. Push. A notification appears. "Your account has been temporarily suspended for violating GitHub's terms of service". Forgot to mark claude as a co-author. She sighs again

path: 0 25272361, hotness: undefined, score: 79, children: 9
joe 8 points 7 days ago

These watermarks require the text to be long-ish and not too edited from the original. I didn't see this explained in the article, but I only skimmed it. The press release from Anthropic goes into it, without giving many details.

I'm guessing it's going to embed a pattern with punctuation and word/letter choices, so there will need to be a sufficient amount of text to ensure its actually the watermark and not just dumb luck.

path: 0 25272361 25274364, hotness: undefined, score: 8, children: 1
toph 6 points 7 days ago

Yeah it’s exactly a pattern with token choices, by introducing a statistical bias to the randomness in token generation. Quality isn’t affected because the model is still choosing from the best candidates for the next token. You’re right that to be effective they need a long enough input to get enough matches to be.

Computer code is also going to be less effective because code has a much more rigid structure dictated by language syntax rules, coding conventions, linters and formatters, etc.

path: 0 25272361 25274364 25276872, hotness: undefined, score: 6, children: 0
technology
technology

@lemmy.world

login for more options
87355
21246
15760

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


go to feed...