Anthropic shares details about how Claude's new watermarks will work

Join the discussion

• Hacker News
• you can remove AI company invisible text watermarks at www.demarkify.com - and also perform other tonal text changes like removing AI lexical tells
  by jannw
• From yesterday, 68 comments on the original source: https://news.ycombinator.com/item?id=49303350
  by WalterGR
• If you look at how this works under the hood, “when two words that don’t necessarily matter to the context, it will pick one word over the other and a pattern emerges”

  And that pattern will be reverse engineered in weeks by a startup

  And a downstream agent produced by said startup will be built to roll those dice again and defeat the watermarking

  And a the LLM vendors will combat this

  And a cottage industry shall be born anew

  by n4pw01f
• It seems to me that a model provider who can watermark generated text (unbeknownst to the users) could also specifically watermark generated text prompted by particular users, thus enabling tracking and, consequently, harassment and control of those users and populations as a whole. Bad for anonymity and for free speech.

  I hope to be corrected by someone who knows the tech much better than I do.

  by treetalker