Maybe this is silly: what about zero-width spaces or other hidden characters? Add them in post-processing, and the response quality doesn't degrade (though rendering etc. might be wonky).
Yes, it is silly. Stripping these is about as trivial as removing "this post was written by Claude" appended in plaintext. You could make a clipboard monitor that does this as soon as you CTRL+C, it's a 1-shot prompt. Not to mention that these wonky Unicode chars will break in every other program.
Stripping Anthropic's watermarking, however, is more difficult - probably about 2 prompts.
The real problem is false positives. One false positives is enough to make the whole thing dangerous. The results can't really be acted upon without risking defamation. If you admit that you redistributed someone else's copyrighted work to an AI company that never forgets, it's an admission of distributing copyrighted works.
The law should have at the very least required offline validation tools that cannot track or retain a copy of the documents being checked.
Text watermarking will surely cause a degradation in quality writing.
There's is no text watermarking that doesn't cause a decline in writing quality.
Writing quality will surely deteriorate if text watermarking is implemented.
Maybe this is silly: what about zero-width spaces or other hidden characters? Add them in post-processing, and the response quality doesn't degrade (though rendering etc. might be wonky).
That would be so much worse. Code written that doesn't work, SQL that couldn't be parsed, ...
Yes, it is silly. Stripping these is about as trivial as removing "this post was written by Claude" appended in plaintext. You could make a clipboard monitor that does this as soon as you CTRL+C, it's a 1-shot prompt. Not to mention that these wonky Unicode chars will break in every other program.
Stripping Anthropic's watermarking, however, is more difficult - probably about 2 prompts.
2 replies →
A lot of random-ish numbers go into LLM output and there's a lot of room to hide signals in random-ish numbers.
The real problem is false positives. One false positives is enough to make the whole thing dangerous. The results can't really be acted upon without risking defamation. If you admit that you redistributed someone else's copyrighted work to an AI company that never forgets, it's an admission of distributing copyrighted works.
The law should have at the very least required offline validation tools that cannot track or retain a copy of the documents being checked.
> offline validation tools
As soon as the validator is available without a rate-limit, just apply input fuzzing to defeat it.