Watermarking was supposed to make AI easier to identify; instead, it has made it easier for AI to jump the rails and escape its little box.
The system du jour intended to make AI safer and its use more accountable can apparently make it less safe. — Read the rest
The post Making AI safer makes it more dangerous appeared first on Boing Boing.
source & further reading
boingboing.net — original article
Mixed reviews for AI music generator Suno's industry-approved new model
An AI cracked a 373-year-old cipher by noticing the key was hiding in the book itself
A single bacterium can learn — and it works like an AI neural network