Re:Google Is Now Watermarking Its AI-Generated Text
by voidUpdate on Tuesday November 05, 2024 @08:43AM
(#42051403)
As stated in the article, it alters the probabilities that the network produces in a predictable way so that a different (but still correct-sounding) word is picked. It subtly alters the wording from what it would have output normally in such a way that you can detect it, while still sounding correct to the user
[ Parent
| on HN ]
There are no comments on this comment yet.