logoalt Hacker News

andy99yesterday at 10:03 PM2 repliesview on HN

I don’t understand how this works for anything but prose. Is that the point? In any code or structured output, there just isn’t the flexibility, and depending on how the user requests the output be constrained there is even less (“answer only True or False”). So is it just chat responses? If I ask the API to tell me a story about Alice and Bob then it watermarks it, but when I ask it some implausibly constrained thing like write a story about Alice and Bob with each word starting in rotation with the letters alicebob, does it try to do so and hope there are roughly équiprobable tokens regularly?


Replies

smallerizeyesterday at 10:14 PM

Yes, and it says that in https://www.anthropic.com/news/claude-text-watermark

show 1 reply
chrisjjyesterday at 10:13 PM

> In any code or structured output, there just isn’t the flexibility

Variable name perversion incoming...