No mention of what data they are specifically encoding. Will it be like printing dots, traceable to the exact account that generated the text?
How Claude marks AI-generated content
171–180 of 446 posts
Re: How Claude marks AI-generated content
#172I cannot wait for the inevitable "I've always used Claude watermarks in my writing, even before we had LLMs!" when someone gets caught using an LLM.
Re: How Claude marks AI-generated content
#173Earlier quoted context omitted.
>I'd like to know a lot more about how that works. My guess is that it works like Gemini's SynthID: by altering the logprobs of the next token. Like, for every 10th token, instead of outputting the most probable, it outputs the 17th most probable, or something. (Obviously it's way more complicated but I think conceptually this is how it works.) No human will notice this, but a classifier trained on Claude's output wi…
They still need to choose when to do that though. When I prompt the program to e.g. alter a bash script in a specific way or to recite a longer known text it can't go round and randomly exchange tokens. It has to somehow define what is a simple repeated text from a different origin and what is a novel generation.
I cannot imagine the code with well defined specification will have extra watermarks unless the watermark is requested as part of the harness instructions.
If it works like people describe - on the every nth token or something - then the mark will be left in the chain of thought and discussion with the model - not in the code artifacts.
Re: How Claude marks AI-generated content
#174[flagged]
Re: How Claude marks AI-generated content
#175People with dyslexia and dystrophia, commonly use LLMs to proofread content. Even Anthropic admits this is a limitation.
Yes, I’m audhd and dyslexic. I am cancelling my Claude max 5x subscription and moving to ChatGPT pro. I have difficulty enough trying to ensure my meaning comes through correctly, along with everything else; to now have to look out for/analyse watermarks too? I feel shamed enough by society, thanks Anthropic.
Paradoxically, one of those two firms puts considerably more effort into accommodating such differences, and the other has signed the same EU law and just hasn't performed as well rolling it out.
Both points suggest your subscription support was well chosen before.
Re: How Claude marks AI-generated content
#176We 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…
The problem with pretending is that people who k ow what they’re doing get away with it while people who don’t (and don’t even use ai) get unfairly accused of using it.
There just isn’t enough information in plain text to do this and we should stop pretending there is.
If we need to verify something isn’t made with ai then we need other ways of doing so - eg looking at a document edit history, doing it as an exam, oral defense.
There are options! But pretending you can tell if text is ai will only catch out people who make no effort to hide it and will inevitably have false positives.
Re: How Claude marks AI-generated content
#177> 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…
Off the top of my head I would have thought zero width characters (eg: U+200B, U+200C) making some unique identifier sprinkled in amongst the output. But obviously far from foolproof since they could simply be removed.
Re: How Claude marks AI-generated content
#178Earlier quoted context omitted.
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' (co…
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'…
Considering how weirdly detuned tokens selections have become in Anthropic's LLM prose in recent models, there is a chance this goes unnoticed in everyday use.
Re: How Claude marks AI-generated content
#179So my code that Claude makes, which previously was using the best (most probable) tokens for the job, will now be getting worse in random positions, to appease a voluntary EU suggestion. Love that.
Your "code that Claude makes..."?
Oh, how I laughed. That was never your code, my friend.
Re: How Claude marks AI-generated content
#180> 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…
>I'd like to know a lot more about how that works. My guess is that it works like Gemini's SynthID: by altering the logprobs of the next token. Like, for every 10th token, instead of outputting the most probable, it outputs the 17th most probable, or something. (Obviously it's way more complicated but I think conceptually this is how it works.) No human will notice this, but a classifier trained on Claude's output wi…
Less probable also means less optimal and you get a subpar response. More so if it's baked into its reasoning. It's intelligence will suffer unless this is some post processing thing.