141–150 of 446 posts
I notice the "Limitations" section talks about how content only at some point touched by Claude may return a positive, and content that returns a negative may still be Claude generated. But I really would have liked for them to state explicitly that entirely false positives where a piece is fully human-written may still be marked as generated, because too many institutions with the power to ruin someone's life over t…
Maybe it has no false positive rate
> 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. I'd like to know a lot more about how that works. A lot of my interactions with Claude return pretty precise text. If I ask it to edit a project and refactor a specific function in several places I know ex…
My guess is it will be similar to how Genius watermarked lyrics, using things like variants of punctuation https://www.pcmag.com/news/genius-we-caught-google-red-hande...
Earlier quoted context omitted.
Just double checking my understanding: If this is true then only Anthropic will be able to detect if text was generated by one of its models, correct?
Likely yes.
Seems like this would only catch the most unsophisticated cases.
We need to just stop pretending we can reliably tell if plain text is written by an LLM. It’s just not a reasonable ask.
True, but what you can do is a one-sided guarantee. If it bears the mark, it is likely generated (or someone deliberately made it look generated). Thus, if a news article, research article, book, student paper submission, blog post , HN comment, etc, bears the mark, it could be automatically flagged as such. It helps detect low effort slop. --- Caveat. If you write your own creative work and send it to Claude for "cl…
It seems it would get as simple as:
outputText = promptLLM(prompt)
scrubbedText = scrubWatermark(outputText)
We need to just stop pretending we can reliably tell if plain text is written by an LLM. It’s just not a reasonable ask.
True, but what you can do is a one-sided guarantee. If it bears the mark, it is likely generated (or someone deliberately made it look generated). Thus, if a news article, research article, book, student paper submission, blog post , HN comment, etc, bears the mark, it could be automatically flagged as such. It helps detect low effort slop. --- Caveat. If you write your own creative work and send it to Claude for "cl…
One could even say, the mark is load-bearing.
I've heard that this kind of watermarking process works by biassing the statistical sampling towards a partition of the set of possible next tokens (red set and green set), at each position. It might only be a slight nudge each time, but over a sequence of tokens, the likelihood of repeating the bias by chance is increasingly improbable. The bias is different for each position and follows a defined RNG, seeded someho…
Gotta be hard to tune that.
Earlier quoted context omitted.
Maybe it has no false positive rate
That's essentially impossible, unless you mean they didn't measure a false positive rate.
Earlier quoted context omitted.
That's essentially impossible, unless you mean they didn't measure a false positive rate.
For watermarked long-form text, it is actually possible. Makes the watermark more fragile, but the math is considerably more forgiving than usual.
What about "watermarked long-form code"? I'm having a hard time understanding how a model could watermark not prose, but functional/semantic text like code, that actually has meaning. You can't switch our the characters, you can't use various types of whitespace, you can't add arbitrary code comments, and a lot of other restrictions. Is there any state of the art methods for watermarking code without affecting the quality/correctness?