Manage GRC Faster withDrata’s Agentic Trust Management Platform
When Iwrote this weekabout Anthropic’s announcement that all Claude models, worldwide, would soon begin “watermarking” everything they generate, including text, to comply withthis EU regulation, we were left to speculatehowthis was going to work, because Anthropic offered not even a vague description of how it would work — despite the fact that the title of the announcement was, absurdly and insultingly, “How Claude Marks AI-Generated Content”.
My initial speculation was that maybe they’d hide invisible non-printing Unicode characters in the text. Just spitballing. Turns out that’s not what they’re going to do. What they’re going to do is apply a form of steganography, where the choice of words (or other token output) at inference time will leave fingerprints that can later, maybe, be detected probabilistically.
I initially guessed “invisible characters” not because I didn’t think of the semantic word-choice technique, but because I was a fool who took Anthropic at its word in their description of what they would do. Their original support document claims:
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.
They say “imperceptible” and “doesn’t change the meaning, quality, or readability”. Their words. Notalmostimperceptible. Notslightlychanges the meaning, quality, or readability. That made sense to me, because that’s absolutely what I want — nay, demand — from any tools I use personally. It’s unacceptable for a tool to sacrifice an iota of clarity, coherence, meaning, quality, etc. for the purpose of embedding hidden clues within the text to suggest its provenance. That’s what I would and will demand. And Anthropic’s (original) support document unambiguously claims that’s what their system will enable. So if that were true, I couldn’t see what was left other than hiding invisible characters within the text.
My error was believing Anthropic that their system wouldn’t adulterate and corrupt the semantics of the text their models generate.Thatis in fact exactly what they plan to do. I should have my head examined for believing a single word of a document titled “How Claude Marks AI-Generated Content” that doesn’t explain, at all, how Claude marks (or will mark) AI-generated content.
Yesterday, on an entirely different website thanthe original“How Claude marks AI-generated content” article (the one that didn’t explain anything at all about how it works), Anthropic published “How Claude’s Text Watermark Works”, which does actually explain in layman-accessible terms how it’s going to work. I will return to Anthropic’s new highly euphemistic and slightly misleading description below.
There’s a bunch of research on this topic, some of which I have also linked to below. But the very best description of the general idea behind the technique is an interactive essay by James Padolsey, “How AI Text Watermarking Works”. It’s a wonderfully cogent read, and the interactive elements splendidly illustrate the main concepts. A+ work. If you have any interest in this at all, I dare say you must read — and play with — Padolsey’s piece.
But here’s my stab at a layman’s high-level summary. If you toss a coinNtimes and note the results, you can determine with a degree of certainty whether the coin is fair or biased. LLMs are, in their popular incarnations, non-deterministic. Ask the same question of the same model and you often get at least slightly different answers. Maybe the same meaning, but different phrasing. At each decision point for generating the next token, the model makes a choice. With these semantic watermarking techniques, they make different choices for some tokens based on word lists that could be called “green” and “red”. At each decision point, they’re a little more likely to pick a word from the green list than the red list. That doesn’t mean they never choose words from the red list. Just that they’re less likely to than they would if the adulterated marking technique weren’t in place. (Same way that a crooked 51-49 coin will still land “wrong” side up 49 times out of 100 on average.)
Words or word phrases are sorted into the green and red lists deterministically on the fly, at each “next token” generation point. So sometimes a specific word will be on the green list, and other times it will be on the red list. Someone with the secret key can determine which list a word will be on at each token generation point (which is how the watermarking is detected); those without the secret key cannot. This means there will never be a list of words that Claude prefers or eschews.
With coin flipping, the higherNis — the more times you flip — the more confident you can be that the coin is fair or biased. So too with this semantic watermarking. The more words in the text, the more accurate the analysis will be that the text was generated by a specific AI model or not. With too few coin flips, you can’t achieve any confidence at all regarding a coin’s fairness. With too few words (or tokens), there’s no way to achieve any confidence whether a string of text was AI-generated or not.