So this won't be happening in the US, but in the EU:

"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."

▲

travisgriggs 11 hours ago | parent | next [-]

I would love to see what this looks like in practice. Especially in generated code. I assume this is more than insertion of non visible special unicode whitespace characters, but more in the pattern of the text content itself?

▲

rcxdude an hour ago | parent | next [-]

It essentially looks like the difference between two different runs of the model with the same prompt but different seeds. The watermark is essentially a small bias in the model such that when there's multiple different tokens that could conceivably follow the previous token, the model will only pick some subset of them (the subset is derived from a hash of the previous token). This bias can then be checked for statistically (without needing access to the model and without needing the whole prompt), and for longer text where there's enough freedom in word choice you can show that it would be vanishingly improbable to accidentally follow the rules in the watermark.

▲

toufka 11 hours ago | parent | prev | next [-]

I'm guessing - probably some textual variation on Benford's law? [1]. Trivial for compute, painful for a human.

- "Ensure distribution of vowels is in >99th percentile of human work"

- "Ensure the distribution of the letter "s" is within 99th percentile of human work"

- "Ensure the distribution of the letter "L" is periodic with periodicity within 5% of 1/N characters.

- "Ensure there is a cross-linguistic 'typo' (colour vs color) at 1/N words, where N: 1000 = Model1, 2000 = Model2, 3000 = Model3.

- "Ensure the distribution of tense error is within 99th percentile of human work"

If more than 3 dimensions have a score >99% percentile of human, let's call it watermarked...

- 1) https://en.wikipedia.org/wiki/Benford%27s_law

	▲	Der_Einzige 11 hours ago \| parent \| next [-]
		Models can't reliably follow instructions involving their own logprobs unless they can take agentic control and use quite sophisticated dynamic grammars/structures/constraints to force this behavior in one shot (which can be slow and the dynamic grammar modification feature isn't supported in closed model APIs for safety reasons) or repeated attempts at rewriting which is expensive/slow. Yes they can do this, but it's more likely closer to the original "red token, green token" paper: https://arxiv.org/abs/2301.10226 i.e. take half of your LLMs vocabulary, and upweight its probabilities by ~55% to the other half's ~45%, and scan for overuse of this half of all tokens. You can even choose a different half/slice for every individual user, for every individual action. You can implement this under the hood cheaply with logit-biasing.
	▲	Computer0 11 hours ago \| parent \| prev [-]
		I would hate to have any of these rules effecting my output

▲

wolfy1993 11 hours ago | parent | prev | next [-]

IIRC, watermarking text could be as simple as training the model to use specific words/phrases more frequently than what you would expect to find in human-written text, to the point where it's highly statistically improbable that it wasn't AI generated. I assume similar logic could apply to code in the form of functions/code styling.

That's probably an over simplification. Also a solid defence that can be used against complaints about the way AI writes text.

▲

AtHeartEngineer 11 hours ago | parent | prev [-]

non visible text is extremely easy to filter with a git hook, a post tool call hook, or just a script. I doubt they are doing that

	▲	sixtyj 11 hours ago \| parent [-]
		Or grep, in a skill. /clean-cc-watermark just entered the chat…

▲

tech234a 10 hours ago | parent | prev [-]

Article specifically says "worldwide"

	▲	Computer0 6 hours ago \| parent [-]
		I agree with your reading, I initially misread it.