Claude Now Watermarks AI-Generated Content

> 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 exactly what I want to happen, it will NOT be OK if those refactors have some kind of weird pattern baked into their text to act as a watermark.

I guess this may be covered by this:

> Content generated by Claude may not carry a detectable mark if, for example: [...] The passage is very short, leaving too little text for a reliable signal;

If I understand correctly, this means that any text with the "watermark" is legally uncopyrightable, including code.

Relevant comment from a few days ago:

https://news.ycombinator.com/item?id=49203613

Many good comments here. It’s somewhat common for me to voice record say a blog post of product updates, more like a ramble. Then have Claude clean it up. Then argue back and forth about certain things until it’s good, then make a final pass sometimes to change a few key words. This is incredibly different than pure ai text. Presumably it will show as ai generated here, even though I would argue it is not really. So I can’t use Claude for this usecase anymore.

I think the solution is assume everything is ai generated unless told otherwise and rely on authorship/brand as a sign of quality.

All big LLMs already visibly watermark all their text with easy to detect annoying phrases and turns of speech that everyone is already sick of hearing. Why do AI companies keep making their products worse to appease anti-AI, it’s not like they’ll suddenly start supporting it if you do so. If you’re worried about European customers, just relax your firewalls to let more VPNs through, if the productivity boost is high they will use it anyway if their rules keep crippling their own models

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 somehow predictably.

Can be either an open algorithm, or not. If not open, then an API could be provided to determine if text is watermarked or not.

How it applies to code - maybe it could be a subtle nudge to symbol names, etc, I'm just speculating (I only read about this in passing very recently).

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.

I 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.

So 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.

A surprising number of people are worried that the code they don’t read will be imperceptibly different.